# real-time

A real-time system is an information-processing system that performs application functions within predictable, specific time constraints.

This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles.

## Achieving Near-Zero-Overhead Multi-Model Hierarchical Classification in Real-Time Detection Pipelines

DevFeed: [Achieving Near-Zero-Overhead Multi-Model Hierarchical Classification in Real-Time Detection Pipelines](<https://devfeed.tech/articles/achieving-near-zero-overhead-multi-model-hierarchical-classification-in-real-time-detection-pipelines-144919.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2608.11770>)

Author: Vaishnav Raju

Published: 2026-11-20T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Distributed Computing](<https://devfeed.tech/sources/arxiv-distributed-computing.md>), [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [quantization](<https://devfeed.tech/topics/quantization.md>), [Jetson Orin](<https://devfeed.tech/topics/jetson-orin.md>), [AI Integration Strategies](<https://devfeed.tech/topics/ai-integration-strategies.md>), [real-time](<https://devfeed.tech/topics/real-time.md>)

Tags: [accelerators](<https://devfeed.tech/tags/accelerators.md>), [analysis](<https://devfeed.tech/tags/analysis.md>), [architecture](<https://devfeed.tech/tags/architecture.md>), [arxiv](<https://devfeed.tech/tags/arxiv.md>), [autonomous](<https://devfeed.tech/tags/autonomous.md>), [autonomous-vehicles](<https://devfeed.tech/tags/autonomous-vehicles.md>), [bottleneck](<https://devfeed.tech/tags/bottleneck.md>), [classification](<https://devfeed.tech/tags/classification.md>), [classifier](<https://devfeed.tech/tags/classifier.md>), [classifiers](<https://devfeed.tech/tags/classifiers.md>), [compilation](<https://devfeed.tech/tags/compilation.md>), [concurrent](<https://devfeed.tech/tags/concurrent.md>), [cs-cv](<https://devfeed.tech/tags/cs-cv.md>), [cs-dc](<https://devfeed.tech/tags/cs-dc.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [custom](<https://devfeed.tech/tags/custom.md>), [deployment](<https://devfeed.tech/tags/deployment.md>), [detection](<https://devfeed.tech/tags/detection.md>), [drone](<https://devfeed.tech/tags/drone.md>), [edge](<https://devfeed.tech/tags/edge.md>), [overhead](<https://devfeed.tech/tags/overhead.md>), [pipelines](<https://devfeed.tech/tags/pipelines.md>), [real-time](<https://devfeed.tech/tags/real-time.md>)

### AI overview

The paper reports that a GPU detector paired with DLA classification on a Jetson Orin NX ran at 12.5 FPS at 1080p, compared with 13.3 FPS for the detector alone. Its five-step deployment method covers adapting classification architectures, repairing TensorRT implicit quantization ranges for pipeline validation (raising reported accuracy from 75% to 94%), quantization-aware training, ONNX graph surgery, and concurrent GPU/DLA inference. The authors also describe nine engineering constraints and report dual-DLA scaling without additional cost. Evidence here is limited to the abstract.

### Source excerpt

arXiv:2608.11770v2 Announce Type: replace-cross Abstract: Edge-deployed vision systems in target recognition, surveillance, autonomous vehicles, and drone domains require hierarchical inference pipelines where a detection model identifies objects of interest and downstream classifiers provide fine-grained attribute analysis. Running all models on the GPU creates a serial bottleneck that limits real-time throughput as pipeline stages grow. Modern edge SoCs pair GPUs with dedicated neural accelerators (NPUs, DLAs) capable of concurrent execution, yet deploying custom models on these accelerators remains impractical due to strict operator constraints, quantization incompatibilities, and an undocumented end-to-end pipeline. We target NVIDIA Jetson DLA cores as the representative platform. We present a five-step methodology for zero GPU fallback DLA INT8 deployment of classification backbones, comprising architecture adaptation, manual dynamic range workaround to rescue TensorRT's implicit quantization (recovering 94.0% accuracy from implicit quantization's 75%) for rapid pipeline validation before explicit quantization, quantization-aware training, ONNX graph surgery for DLA compilation, and a concurrent GPU-detection/DLA-classification inference pipeline. We document nine engineering constraints with root-cause analysis and generalizable solutions. Validation on a dual-head person attribute classifier running on DLA alongside a GPU object detector on a Jetson Orin NX demonstrates near-zero pipeline overhead (12.5 vs. 13.3~FPS detector-only at 1080p), with dual-DLA scaling at no additional cost. The methodology is backbone-agnostic and generalizes to any detection-classification edge pipeline.

## Enabling Real-Time AI for Scientific Instruments with GPU-Native Data Acquisition

DevFeed: [Enabling Real-Time AI for Scientific Instruments with GPU-Native Data Acquisition](<https://devfeed.tech/articles/enabling-real-time-ai-for-scientific-instruments-with-gpu-native-data-acquisition-143888.md>)

Original publisher: [Read original article](<https://developer.nvidia.com/blog/enabling-real-time-ai-for-scientific-instruments-with-gpu-native-data-acquisition/>)

Author: Cara Laasch

Published: 2026-11-19T17:00:00Z

Content type: article

Language: en

Sources: [NVIDIA Developer](<https://devfeed.tech/sources/nvidia-developer.md>), [NVIDIA Technical Blog](<https://devfeed.tech/sources/nvidia-technical-blog.md>)

Topics: [Holoscan](<https://devfeed.tech/topics/holoscan.md>), [streaming data analytics](<https://devfeed.tech/topics/streaming-data-analytics.md>), [real-time](<https://devfeed.tech/topics/real-time.md>), [data-engineering](<https://devfeed.tech/topics/data-engineering.md>)

Tags: [acquisition](<https://devfeed.tech/tags/acquisition.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agent](<https://devfeed.tech/tags/ai-agent.md>), [ai-inference](<https://devfeed.tech/tags/ai-inference.md>), [analysis](<https://devfeed.tech/tags/analysis.md>), [bandwidth](<https://devfeed.tech/tags/bandwidth.md>), [batch](<https://devfeed.tech/tags/batch.md>), [benchmarks](<https://devfeed.tech/tags/benchmarks.md>), [communication](<https://devfeed.tech/tags/communication.md>), [configuration](<https://devfeed.tech/tags/configuration.md>), [connectx](<https://devfeed.tech/tags/connectx.md>), [control](<https://devfeed.tech/tags/control.md>), [cpu](<https://devfeed.tech/tags/cpu.md>), [data](<https://devfeed.tech/tags/data.md>), [developer-tools-techniques](<https://devfeed.tech/tags/developer-tools-techniques.md>), [dgx-spark](<https://devfeed.tech/tags/dgx-spark.md>), [edge-computing](<https://devfeed.tech/tags/edge-computing.md>), [gpu](<https://devfeed.tech/tags/gpu.md>), [instruments](<https://devfeed.tech/tags/instruments.md>), [measurements](<https://devfeed.tech/tags/measurements.md>), [networking-communications](<https://devfeed.tech/tags/networking-communications.md>), [processes](<https://devfeed.tech/tags/processes.md>), [real-time](<https://devfeed.tech/tags/real-time.md>), [sc26](<https://devfeed.tech/tags/sc26.md>), [science](<https://devfeed.tech/tags/science.md>), [sensor](<https://devfeed.tech/tags/sensor.md>)

### AI overview

NVIDIA DAQIRI moves high-bandwidth sensor data directly into GPU memory so it can be processed during acquisition, enabling real-time inspection and feedback without first writing measurements to disk. At Lawrence Berkeley National Laboratory's Molecular Foundry, a high-dynamic-range electron microscopy camera streams over 500 Gbps; DAQIRI and GPU processing assemble and correct detector frames, derive energy-loss spectra, and improve spatial resolution from 5-micrometer sensor pixels to submicron resolution. The latest release adds packet reordering on supported NVIDIA ConnectX-7-or-newer NICs, an ibverbs backend, and direct polling. The ibverbs engine benchmarks at about twice the previous DPDK backend's per-core throughput for packets up to 1,024 bytes at rates above 200 Gbps on specified NVIDIA platforms. Direct polling avoids a separate I/O-worker handoff; cabled loopback tests demonstrated roughly 2-4 μs application send-to-receive latency. These results are benchmark-specific, and the excerpt recommends evaluating throughput and latency on the target hardware.

### Source excerpt

In science and industry, analyzing sensor measurements in real time can enable AI to adjust processes, guide experiments, and search for better operating...

## Disney's new Star Wars robots use AI to react to guests in real time, but can't go off-script

DevFeed: [Disney's new Star Wars robots use AI to react to guests in real time, but can't go off-script](<https://devfeed.tech/articles/disney-s-new-star-wars-robots-use-ai-to-react-to-guests-in-real-time-but-can-t-go-off-script-143632.md>)

Original publisher: [Read original article](<https://www.techspot.com/news/114620-disney-new-star-wars-robots-use-ai-react.html>)

Author: Skye Jacobs

Published: 2026-11-19T14:04:00Z

Content type: news

Language: en

Sources: [TechSpot](<https://devfeed.tech/sources/techspot.md>)

Topics: [Real-time AI interactions](<https://devfeed.tech/topics/real-time-ai-interactions.md>), [Humanoid Robots](<https://devfeed.tech/topics/humanoid-robots.md>), [real-time](<https://devfeed.tech/topics/real-time.md>), [The Three Main Cloud Service Models](<https://devfeed.tech/topics/the-three-main-cloud-service-models.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [aliens](<https://devfeed.tech/tags/aliens.md>), [amazon-aws](<https://devfeed.tech/tags/amazon-aws.md>), [animatronic](<https://devfeed.tech/tags/animatronic.md>), [animatronics](<https://devfeed.tech/tags/animatronics.md>), [aws](<https://devfeed.tech/tags/aws.md>), [aws-cloud](<https://devfeed.tech/tags/aws-cloud.md>), [aws-re-invent](<https://devfeed.tech/tags/aws-re-invent.md>), [camera](<https://devfeed.tech/tags/camera.md>), [compute](<https://devfeed.tech/tags/compute.md>), [conference](<https://devfeed.tech/tags/conference.md>), [content](<https://devfeed.tech/tags/content.md>), [context](<https://devfeed.tech/tags/context.md>), [decision-making](<https://devfeed.tech/tags/decision-making.md>), [decision-model](<https://devfeed.tech/tags/decision-model.md>), [disney](<https://devfeed.tech/tags/disney.md>), [electronics](<https://devfeed.tech/tags/electronics.md>), [guests](<https://devfeed.tech/tags/guests.md>), [park](<https://devfeed.tech/tags/park.md>), [real-time](<https://devfeed.tech/tags/real-time.md>), [robots](<https://devfeed.tech/tags/robots.md>), [script](<https://devfeed.tech/tags/script.md>), [star-wars](<https://devfeed.tech/tags/star-wars.md>), [tech-culture](<https://devfeed.tech/tags/tech-culture.md>), [the-mandalorian](<https://devfeed.tech/tags/the-mandalorian.md>)

### AI overview

Disney's three Anzellan robots use cameras and microphones to react to guests and one another, while staying within material approved by Imagineers. AWS cloud models divide the work: a fast model handles immediate reactions such as eye contact, while larger models plan slower exchanges using more context. The system selects prerecorded dialogue and designed animations; it does not generate new speech or motion. This preserves creative control and keeps responses predictable, though whether reactions feel immediate in a noisy crowd remains to be tested. The robots are due to appear at AWS re:Invent, and Disney has not committed to a theme park debut.

### Source excerpt

The characters are named Vilo Vele, Kado Bre'a and Jibu Bre'a. Their first public appearance will be at AWS re:Invent in Las Vegas later this month, where conference attendees can interact with them. Disney has not committed to a park debut. However, the characters and the technology behind them could... Read Entire Article

## Think Offline, Act in Real Time: Self-Improving Visual Game Agents through Code

DevFeed: [Think Offline, Act in Real Time: Self-Improving Visual Game Agents through Code](<https://devfeed.tech/articles/think-offline-act-in-real-time-self-improving-visual-game-agents-through-code-142811.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.24590>)

Author: Zipeng Qiu, Shusheng Xu, Jiale Li, Yukun Zhou, Chenyue Li, Wenshuang Li, Tongkai Yang, Binhang Yuan

Published: 2026-11-19T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>)

Topics: [World models](<https://devfeed.tech/topics/world-models.md>), [AI-assisted coding](<https://devfeed.tech/topics/ai-assisted-coding.md>), [real-time](<https://devfeed.tech/topics/real-time.md>)

Tags: [agents](<https://devfeed.tech/tags/agents.md>), [code](<https://devfeed.tech/tags/code.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [game](<https://devfeed.tech/tags/game.md>), [improvement](<https://devfeed.tech/tags/improvement.md>), [model](<https://devfeed.tech/tags/model.md>), [models](<https://devfeed.tech/tags/models.md>), [play](<https://devfeed.tech/tags/play.md>), [policy](<https://devfeed.tech/tags/policy.md>), [program](<https://devfeed.tech/tags/program.md>), [progress](<https://devfeed.tech/tags/progress.md>), [real-time](<https://devfeed.tech/tags/real-time.md>), [tasks](<https://devfeed.tech/tags/tasks.md>)

### AI overview

The study compares two ways for agents to improve at unfamiliar real-time visual games from a few attempts. In "model as policy," a trained 2B controller selects actions during play, with committed action chunks continuing while it reasons. In "code as policy," a model writes, tests, and revises a program between attempts, and that program acts during play. Across 170 GameWorld tasks, limited to at most eight one-minute executions per run, code as policy achieved 47.80% mean progress versus 30.90% for the controller and led in all five game categories. Improving the controller's weights on one game brought only modest gains. The authors conclude that learning offline into a program can work better in this setting.

### Source excerpt

arXiv:2611.24590v1 Announce Type: new Abstract: Pre-trained models can read screens and reason about games, yet on an unfamiliar game, an agent still has to learn to play. We ask how an agent can self-improve on such a game from a few of its own attempts, in real-time visual games where the agent sees only the screen and the game keeps running while the agent thinks. We study two kinds of policy that can carry this improvement. In model as policy, a model selects actions during play; we adapt real-time chunking so that committed actions keep executing while the model reasons, and train a 2B controller for this interface. In code as policy, a model writes, tests, and revises a program between attempts, and the program acts during play. Across 170 GameWorld tasks, with at most eight one-minute executions per run, code as policy reaches 47.80% mean progress, against 30.90% for our trained controller, and leads in all five game categories. Improving the controller's weights on a single game, by contrast, yields only modest gains. These results favor letting a model think offline and storing what it learns in a program that acts in real time. Project repository: https://github.com/TabibitoQZP/SIGame

## Continuum: Boundary-State-Aware Deterministic Scheduling in Dynamic LEO Networks

DevFeed: [Continuum: Boundary-State-Aware Deterministic Scheduling in Dynamic LEO Networks](<https://devfeed.tech/articles/continuum-boundary-state-aware-deterministic-scheduling-in-dynamic-leo-networks-142998.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.24021>)

Author: Siqi Yang, Zonghui Li, Chaoqun You, Yue Gao

Published: 2026-11-19T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Networking](<https://devfeed.tech/sources/arxiv-networking.md>)

Topics: [scheduling](<https://devfeed.tech/topics/scheduling.md>), [real-time](<https://devfeed.tech/topics/real-time.md>), [performance-engineering](<https://devfeed.tech/topics/performance-engineering.md>)

Tags: [boundary](<https://devfeed.tech/tags/boundary.md>), [consistency](<https://devfeed.tech/tags/consistency.md>), [cs-ni](<https://devfeed.tech/tags/cs-ni.md>), [framework](<https://devfeed.tech/tags/framework.md>), [horizon](<https://devfeed.tech/tags/horizon.md>), [inheritance](<https://devfeed.tech/tags/inheritance.md>), [jitter](<https://devfeed.tech/tags/jitter.md>), [latency](<https://devfeed.tech/tags/latency.md>), [leo](<https://devfeed.tech/tags/leo.md>), [low-earth-orbit](<https://devfeed.tech/tags/low-earth-orbit.md>), [mission](<https://devfeed.tech/tags/mission.md>), [networks](<https://devfeed.tech/tags/networks.md>), [node](<https://devfeed.tech/tags/node.md>), [optimizing](<https://devfeed.tech/tags/optimizing.md>), [performance](<https://devfeed.tech/tags/performance.md>), [scheduling](<https://devfeed.tech/tags/scheduling.md>), [timing](<https://devfeed.tech/tags/timing.md>), [topology](<https://devfeed.tech/tags/topology.md>), [traffic](<https://devfeed.tech/tags/traffic.md>), [transmission](<https://devfeed.tech/tags/transmission.md>)

### AI overview

Continuum uses boundary-state-aware rolling-horizon scheduling for time-triggered traffic in dynamic LEO networks. At topology transitions, it carries forward buffered-node and arrival-time information, then jointly optimizes remaining routes and transmission slots. The approach refines latency to improve timing consistency while preserving original timing constraints. In ablations, boundary-state inheritance improved schedulability by up to 16.6 percentage points, while joint alignment reduced mean jitter by 10.9-37.7 times. The abstract also reports scalability experiments on workloads of up to 10,000 flows, but gives no synthesis performance results.

### Source excerpt

arXiv:2611.24021v1 Announce Type: new Abstract: Low Earth Orbit (LEO) constellations support mission-critical services requiring bounded latency and predictable delivery. However, conventional snapshot-based schedulers discard the forwarding progress of unfinished time-triggered traffic across topology transitions, degrading schedulability and timing consistency. We present Continuum, aboundary-state-aware rolling-horizon scheduling framework. Continuum inherits buffered-node and arrival-time information, jointly optimizing remaining routes and transmission slots, and refines latency to improve timing consistency while preserving original timing constraints. Ablations show up to 16.6 percentage points higher schedulability from boundary-state inheritance and a 10.9-37.7 times reduction in mean jitter from joint alignment. Scalability experiments evaluate synthesis performance for workloads of up to 10K flows.

## OCTR2A: Real-Time RGB-to-BEV Trajectory Projection and Forecasting at Urban Intersections

DevFeed: [OCTR2A: Real-Time RGB-to-BEV Trajectory Projection and Forecasting at Urban Intersections](<https://devfeed.tech/articles/octr2a-real-time-rgb-to-bev-trajectory-projection-and-forecasting-at-urban-intersections-142782.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.24352>)

Author: Emanuele Iacobelli, Simone Teglia, Francesco Pro, Claudia Melis Tonti, Irene Amerini

Published: 2026-11-19T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>), [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [Time Series](<https://devfeed.tech/topics/time-series.md>), [real-time](<https://devfeed.tech/topics/real-time.md>)

Tags: [architecture](<https://devfeed.tech/tags/architecture.md>), [benchmark](<https://devfeed.tech/tags/benchmark.md>), [blender](<https://devfeed.tech/tags/blender.md>), [camera](<https://devfeed.tech/tags/camera.md>), [cameras](<https://devfeed.tech/tags/cameras.md>), [cascade](<https://devfeed.tech/tags/cascade.md>), [class](<https://devfeed.tech/tags/class.md>), [configuration](<https://devfeed.tech/tags/configuration.md>), [consumer](<https://devfeed.tech/tags/consumer.md>), [cross](<https://devfeed.tech/tags/cross.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-cv](<https://devfeed.tech/tags/cs-cv.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [datasets](<https://devfeed.tech/tags/datasets.md>), [deployment](<https://devfeed.tech/tags/deployment.md>), [detection](<https://devfeed.tech/tags/detection.md>), [domains](<https://devfeed.tech/tags/domains.md>), [existing](<https://devfeed.tech/tags/existing.md>), [experiments](<https://devfeed.tech/tags/experiments.md>), [forecasting](<https://devfeed.tech/tags/forecasting.md>), [projection](<https://devfeed.tech/tags/projection.md>), [real-time](<https://devfeed.tech/tags/real-time.md>), [rgb](<https://devfeed.tech/tags/rgb.md>)

### AI overview

OCTR2A reconstructs and forecasts agents' bird's-eye-view trajectories from paired opposite-corner RGB cameras, avoiding reliance at inference time on LiDAR, aerial views, HD maps, or calibrated infrastructure. Its cascade combines per-view detection and class refinement, geometric cross-camera matching, transformer-based BEV projection, and egocentric GRU forecasting. The authors introduce R3ST++, a Blender-based synthetic benchmark built from SIND trajectories, with synchronized views, cross-view correspondences, and BEV ground truth; it also supports site-specific fine-tuning. With 12 observed and 12 predicted frames at 10 Hz, the system reports projection-to-forecasting ADE/FDE of 0.144/0.140 to 0.154/0.241 meters in real time on one consumer GPU. On ground-truth BEV histories, its forecasting module improves ADE/FDE over the strongest compared methods on SIND by 66.7%/41.7%. Transfer experiments indicate R3ST++ pretraining supports adaptation to TUMTraf-V2X roadside domains with different sensing configurations.

### Source excerpt

arXiv:2611.24352v1 Announce Type: cross Abstract: Trajectory forecasting at urban intersections is often studied assuming that reliable bird's-eye-view (BEV) motion histories are available, which in practice requires costly resources such as LiDAR, aerial views, HD maps, or calibrated infrastructure. We address this upstream perception-to-forecasting problem by reconstructing and predicting agents' BEV trajectories only from paired opposite-corner RGB cameras mounted on existing urban infrastructure at variable heights at inference time. We introduce the Opposite-Corner Trajectory Reconstruction and Anticipation Architecture (OCTR2A), a modular pipeline integrating per-view detection with class refinement, geometric cross-camera matching, transformer-based BEV projection, and egocentric GRU forecasting, trained in cascade and mainly supervised with a soft multi-scale spatial-overlap loss. Since no public benchmark provides this sensing configuration, we introduce R3ST++, a Blender-based synthetic benchmark built from SIND trajectories that provides synchronized opposite-corner views, cross-view correspondences, and BEV ground truth, while also serving as a deployment-support simulator for site-specific fine-tuning. Experiments on these datasets show that, with 12 observed and 12 predicted frames at 10\,Hz, OCTR2A achieves projection~-~forecasting ADE/FDE of 0.144/0.140~-~0.154/0.241~meters in real time on a single consumer GPU. Evaluated on ground-truth BEV histories, the forecasting module improves over the strongest state-of-the-art methods on SIND by 66.7\%/41.7\% ADE/FDE. Transfer experiments on TUMTraf-V2X show that R3ST++ pretraining supports adaptation to real-world roadside domains with different sensing configurations.

## RoboTeam: Benchmarking Vision-Based Multi-Agent Control of Many Robot Arms in Real Time

DevFeed: [RoboTeam: Benchmarking Vision-Based Multi-Agent Control of Many Robot Arms in Real Time](<https://devfeed.tech/articles/roboteam-benchmarking-vision-based-multi-agent-control-of-many-robot-arms-in-real-time-139969.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.22138>)

Author: Changxuan Fan, Zhongwei Xie, Boyi Zhang, Shaoli Hu, Chang Xu, Xiyu Ren, Yufei Li, Qiao Xiao, Huihao Jing, Kawai Chung, Wenbin Hu, Hongyu Luo, Lingyun Xie, Yisen Gao, Chunyang Li, Haoyu Huang, Wuganjin

Published: 2026-11-18T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>)

Topics: [Multi Agent Systems](<https://devfeed.tech/topics/multi-agent-systems.md>), [Benchmark](<https://devfeed.tech/topics/benchmark.md>), [Computer vision](<https://devfeed.tech/topics/computer-vision.md>), [hierarchical agent systems](<https://devfeed.tech/topics/hierarchical-agent-systems.md>), [real-time](<https://devfeed.tech/topics/real-time.md>)

Tags: [adaptive](<https://devfeed.tech/tags/adaptive.md>), [agent](<https://devfeed.tech/tags/agent.md>), [agent-control](<https://devfeed.tech/tags/agent-control.md>), [agents](<https://devfeed.tech/tags/agents.md>), [benchmark](<https://devfeed.tech/tags/benchmark.md>), [benchmarking](<https://devfeed.tech/tags/benchmarking.md>), [benchmarks](<https://devfeed.tech/tags/benchmarks.md>), [camera](<https://devfeed.tech/tags/camera.md>), [control](<https://devfeed.tech/tags/control.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-ro](<https://devfeed.tech/tags/cs-ro.md>), [multi-agent](<https://devfeed.tech/tags/multi-agent.md>), [real-time](<https://devfeed.tech/tags/real-time.md>), [robot](<https://devfeed.tech/tags/robot.md>), [robot-arms](<https://devfeed.tech/tags/robot-arms.md>), [system](<https://devfeed.tech/tags/system.md>), [systems](<https://devfeed.tech/tags/systems.md>), [tasks](<https://devfeed.tech/tags/tasks.md>), [vision](<https://devfeed.tech/tags/vision.md>)

### AI overview

RoboTeam benchmarks agents controlling 4-16 robot arms across 36 long cooperative tasks, using camera images alone while simulated time continues during agent reasoning. In its adaptive setup, gpt-6.1-sol and opus-5.5 complete 28 and 27 tasks; four other tested models complete at most 3. Performance is costly and failure-prone: a typical gpt-6.1-sol task takes 3.5 hours and 218 million input tokens, with about a third of steps failing at least once and requiring retries. Four agent systems complete similar numbers of tasks but trade speed against token use: hierarchical and decentralized systems are faster and use up to 1.9 times the tokens, while single-agent uses fewer tokens but takes 1.6 times as long. The abstract concludes that no tested model or system is simultaneously fast, inexpensive, and reliable.

### Source excerpt

arXiv:2611.22138v1 Announce Type: cross Abstract: Multimodal agents can now control robot arms by calling tools and writing code. Existing benchmarks fall short in three ways: most test one or two arms on short tasks, many pause the world while the agent thinks, and many give it ground-truth object positions. We present RoboTeam, a simulated benchmark where agents control 4 to 16 robot arms in real time from camera images alone. Its 36 tasks are long jobs that the arms must do together, such as passing timbers or building a picture from hundreds of cubes. We start from the most flexible agent system, the adaptive system, where one agent decides when to fork delegates. With it, gpt-6.1-sol and opus-5.5 complete 28 and 27 tasks, and four other models at most 3. But at a high price: a typical task takes gpt-6.1-sol 3.5 hours and 218 million input tokens, and a third of its steps fail at least once and must be retried. We then compare it with three fixed systems: single-agent, hierarchical, and decentralized. All four complete a similar number of tasks but differ in time and tokens. The hierarchical and decentralized systems are faster but use up to 1.9 times the tokens, and the single agent uses fewer tokens but takes 1.6 times as long, so the adaptive system lies between them. Even so, no model or system is yet fast, cheap, and reliable at once. RoboTeam measures these limits where earlier benchmarks cannot: long multi-arm jobs, camera images only, and a world that never pauses.

## Real-time fall detection based on vision for low-power edge platforms

DevFeed: [Real-time fall detection based on vision for low-power edge platforms](<https://devfeed.tech/articles/real-time-fall-detection-based-on-vision-for-low-power-edge-platforms-139790.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2607.12909>)

Author: Wenjun Xia, Zhicheng Peng, Haopeng Li, Zhengdi Zhang

Published: 2026-11-18T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>)

Topics: [tinyml](<https://devfeed.tech/topics/tinyml.md>), [real-time](<https://devfeed.tech/topics/real-time.md>)

Tags: [continuous](<https://devfeed.tech/tags/continuous.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-cv](<https://devfeed.tech/tags/cs-cv.md>), [detection](<https://devfeed.tech/tags/detection.md>), [devices](<https://devfeed.tech/tags/devices.md>), [early-warning](<https://devfeed.tech/tags/early-warning.md>), [edge](<https://devfeed.tech/tags/edge.md>), [edge-devices](<https://devfeed.tech/tags/edge-devices.md>), [elderly](<https://devfeed.tech/tags/elderly.md>), [elderly-care](<https://devfeed.tech/tags/elderly-care.md>), [fall](<https://devfeed.tech/tags/fall.md>), [fall-detection](<https://devfeed.tech/tags/fall-detection.md>), [framework](<https://devfeed.tech/tags/framework.md>), [inference](<https://devfeed.tech/tags/inference.md>), [low-power](<https://devfeed.tech/tags/low-power.md>), [physics](<https://devfeed.tech/tags/physics.md>), [physics-informed](<https://devfeed.tech/tags/physics-informed.md>), [prediction](<https://devfeed.tech/tags/prediction.md>), [q-bio-nc](<https://devfeed.tech/tags/q-bio-nc.md>), [real-time](<https://devfeed.tech/tags/real-time.md>), [vision](<https://devfeed.tech/tags/vision.md>)

### AI overview

The paper proposes vision-based fall detection as a loss of stability in a coupled human support system. Its dual-LTC architecture models Center-of-Mass motion and Base-of-Support adjustment, connects those subsystems with a learnable coupling module, and uses a Stability Manifold classifier with Lyapunov-inspired metrics; counterfactual trajectories and Time-to-Collision estimates are intended to assess irreversibility and provide early warning. The authors report a network under 50K parameters for real-time inference on low-power edge devices and competitive accuracy with greater physical interpretability than conventional CNN-RNN pipelines. Although designed for Normal, Falling and Fallen states, this preliminary study validates only Normal versus Falling; full three-state temporal transitions remain future work.

### Source excerpt

arXiv:2607.12909v2 Announce Type: replace-cross Abstract: Falling detection is vital for elderly care and intelligent surveillance; however, prevailing vision-based approaches predominantly frame it as static pose classification or discrete temporal pattern matching, fundamentally overlooking the instability dynamics of the human support system. This paper proposes a physics-informed falling detection framework that recasts falling as a stability-loss event in a coupled dynamical system. We introduce a novel dual-LTC architecture comprising a Center-of-Mass (CoM) subsystem and a Base-of-Support (BoS) subsystem, both instantiated as Liquid Time-Constant (LTC) neural networks to continuously model inertial trajectory evolution and ground-contact adjustment through adaptive time constants, Physical interpretability of falling motion. A learnable coupling module emulates physical interaction between the two subsystems, while a Stability Manifold classifier operates in the joint latent space to detect boundary crossing via Lyapunov-inspired stability metrics. Complementary counterfactual trajectory projection and Time-to-Collision (TTC) estimation further enable irreversibility assessment and early warning. The architecture is designed to support a three-state prediction paradigm (Normal, Falling, Fallen); in this preliminary study, we validate the core stability discrimination capability on a two-class dataset (Normal vs. Falling), leaving the full three-state temporal transition to future work. Unlike conventional CNN--RNN pipelines, the proposed formulation encodes continuous-time mechanical inertia, yielding a sub-50K-parameter network capable of real-time inference on resource-constrained edge devices. Extensive experiments demonstrate competitive accuracy with superior physical interpretability, validating its efficacy for low-compute visual fall detection.

## Get real-time updates on your data pipelines with Fivetran webhooks | Blog | Fivetran

DevFeed: [Get real-time updates on your data pipelines with Fivetran webhooks | Blog | Fivetran](<https://devfeed.tech/articles/get-real-time-updates-on-your-data-pipelines-with-fivetran-webhooks-blog-fivetran-140234.md>)

Original publisher: [Read original article](<https://wf.fivetran.com/blog/get-real-time-updates-on-your-data-pipelines-with-fivetran-webhooks>)

Author: Jimmy Hooker

Published: 2026-11-18T03:12:14Z

Content type: release

Language: en

Sources: [Fivetran Blog](<https://devfeed.tech/sources/fivetran-blog.md>)

Topics: [Event-Streaming](<https://devfeed.tech/topics/event-streaming.md>), [Data pipelines](<https://devfeed.tech/topics/data-pipelines.md>), [data-engineering](<https://devfeed.tech/topics/data-engineering.md>), [real-time](<https://devfeed.tech/topics/real-time.md>)

Tags: [alerts](<https://devfeed.tech/tags/alerts.md>), [api](<https://devfeed.tech/tags/api.md>), [code](<https://devfeed.tech/tags/code.md>), [connectors](<https://devfeed.tech/tags/connectors.md>), [data](<https://devfeed.tech/tags/data.md>), [data-ingestion](<https://devfeed.tech/tags/data-ingestion.md>), [data-integration](<https://devfeed.tech/tags/data-integration.md>), [data-pipeline](<https://devfeed.tech/tags/data-pipeline.md>), [data-pipelines](<https://devfeed.tech/tags/data-pipelines.md>), [dbt](<https://devfeed.tech/tags/dbt.md>), [devops](<https://devfeed.tech/tags/devops.md>), [devops-tools](<https://devfeed.tech/tags/devops-tools.md>), [documentation](<https://devfeed.tech/tags/documentation.md>), [end-user](<https://devfeed.tech/tags/end-user.md>), [events](<https://devfeed.tech/tags/events.md>), [fivetran](<https://devfeed.tech/tags/fivetran.md>), [pipelines](<https://devfeed.tech/tags/pipelines.md>), [real-time](<https://devfeed.tech/tags/real-time.md>), [updates](<https://devfeed.tech/tags/updates.md>), [webhooks](<https://devfeed.tech/tags/webhooks.md>)

### AI overview

Fivetran webhooks push updates to a configured endpoint when selected events occur, replacing repeated API polling or workflows built from platform connector data. The excerpt lists beta events for sync start and end, connector status, transformation runs, and dbt runs, each with start, success, or failure events where applicable. Suggested uses include notifying users when synced data is ready, triggering orchestration, and alerting PagerDuty or other DevOps tools when a pipeline breaks. The article points to an Express and Ngrok sample project for setup; the excerpt does not detail configuration requirements or limitations.

### Source excerpt

With Fivetran webhooks, developers can use real-time messages to power user experiences, transform data, drive error alerting and more.

## With $5M in funding, Pretxt launches runtime oversight layer to supervise AI agents in real time

DevFeed: [With $5M in funding, Pretxt launches runtime oversight layer to supervise AI agents in real time](<https://devfeed.tech/articles/with-5m-in-funding-pretxt-launches-runtime-oversight-layer-to-supervise-ai-agents-in-real-time-136716.md>)

Original publisher: [Read original article](<https://siliconangle.com/2026/11/17/with-5m-in-funding-pretxt-launches-runtime-oversight-layer-to-supervise-ai-agents-in-real-time/>)

Author: Mike Wheatley

Published: 2026-11-17T08:00:53Z

Content type: news

Language: en

Sources: [SiliconANGLE](<https://devfeed.tech/sources/siliconangle.md>)

Topics: [ai-governance](<https://devfeed.tech/topics/ai-governance.md>), [agentic workflows](<https://devfeed.tech/topics/agentic-workflows.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [real-time](<https://devfeed.tech/topics/real-time.md>)

Tags: [aaron-costello](<https://devfeed.tech/tags/aaron-costello.md>), [agent-runtime](<https://devfeed.tech/tags/agent-runtime.md>), [agent-task-execution](<https://devfeed.tech/tags/agent-task-execution.md>), [agentic-ai](<https://devfeed.tech/tags/agentic-ai.md>), [agents](<https://devfeed.tech/tags/agents.md>), [agents-in-production](<https://devfeed.tech/tags/agents-in-production.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agent-safety](<https://devfeed.tech/tags/ai-agent-safety.md>), [ai-agent-security](<https://devfeed.tech/tags/ai-agent-security.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [ai-supervision](<https://devfeed.tech/tags/ai-supervision.md>), [artificial-intelligence](<https://devfeed.tech/tags/artificial-intelligence.md>), [autonomous](<https://devfeed.tech/tags/autonomous.md>), [autonomous-agents](<https://devfeed.tech/tags/autonomous-agents.md>), [brian-soby](<https://devfeed.tech/tags/brian-soby.md>), [company](<https://devfeed.tech/tags/company.md>), [contain](<https://devfeed.tech/tags/contain.md>), [created](<https://devfeed.tech/tags/created.md>), [early-access](<https://devfeed.tech/tags/early-access.md>), [environments](<https://devfeed.tech/tags/environments.md>), [funding](<https://devfeed.tech/tags/funding.md>), [launches](<https://devfeed.tech/tags/launches.md>), [layer](<https://devfeed.tech/tags/layer.md>), [news](<https://devfeed.tech/tags/news.md>), [oversight](<https://devfeed.tech/tags/oversight.md>), [pioneer](<https://devfeed.tech/tags/pioneer.md>), [pretxt](<https://devfeed.tech/tags/pretxt.md>), [real-time](<https://devfeed.tech/tags/real-time.md>), [runtime](<https://devfeed.tech/tags/runtime.md>), [runtime-supervision](<https://devfeed.tech/tags/runtime-supervision.md>), [security](<https://devfeed.tech/tags/security.md>), [seed-funding](<https://devfeed.tech/tags/seed-funding.md>), [the-latest](<https://devfeed.tech/tags/the-latest.md>), [top-story-5](<https://devfeed.tech/tags/top-story-5.md>)

### AI overview

Pretxt AI launched with $5 million in seed funding and offers an early-access runtime layer that checks agents' actions against company policies and can intervene before a violation proceeds. Its near-deterministic engine is intended to avoid the latency, compute cost and guesswork of using a second LLM as a judge; the company claims it runs up to 60 times faster. On Zapier's AutomationBench, the article reports, Pretxt reduced policy violations from about one in five to zero. Users set guardrails, track approvals and roll back plan versions; when rules do not cover an edge case, the system halts the agent and asks a human to decide. The company targets high-stakes regulated industries. The performance and benchmark figures are reported claims, and the excerpt does not provide independent validation.

### Source excerpt

Artificial intelligence supervision pioneer Pretxt AI is launching with $5 million in seed funding today as it tries to contain the very real risk of unleashing autonomous agents in production environments. It has created a new kind of "AI Supervision" tool that applies oversight at runtime to ensure those agents follow a company's rules at [...] The post With $5M in funding, Pretxt launches runtime oversight layer to supervise AI agents in real time appeared first on SiliconANGLE.

## Machine Learning for Near Real-Time Identification of Wildfire Burned Areas

DevFeed: [Machine Learning for Near Real-Time Identification of Wildfire Burned Areas](<https://devfeed.tech/articles/machine-learning-for-near-real-time-identification-of-wildfire-burned-areas-138981.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.20036>)

Author: Khoi Nguyen, Adam W. Bargteil, Milton Halem

Published: 2026-11-17T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [Machine learning](<https://devfeed.tech/topics/machine-learning.md>), [real-time](<https://devfeed.tech/topics/real-time.md>)

Tags: [cs-cv](<https://devfeed.tech/tags/cs-cv.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [eess-iv](<https://devfeed.tech/tags/eess-iv.md>), [machine-learning](<https://devfeed.tech/tags/machine-learning.md>), [model](<https://devfeed.tech/tags/model.md>), [real-time](<https://devfeed.tech/tags/real-time.md>), [satellite](<https://devfeed.tech/tags/satellite.md>), [satellite-images](<https://devfeed.tech/tags/satellite-images.md>), [wildfire](<https://devfeed.tech/tags/wildfire.md>)

### AI overview

The proposed method uses pix2pix to convert a preprocessed index derived from Landsat 8/9 imagery into an approximate per-pixel USGS Burn Probability estimate. The authors describe it as automatable with little human intervention and as reducing delays and geographic restrictions relative to contemporary methods. They report comparing its estimates with USGS Burn Probability using RMSE; the supplied excerpt gives no results or performance figures.

### Source excerpt

arXiv:2611.20036v1 Announce Type: new Abstract: In this article, we present a near real-time method that estimates burned probability anywhere in the world using satellite images. Our approach takes advantage of the state-of-the-art pix2pix model to translate a preprocessed index calculated from Landsat 8/9 images into an approximate of USGS Burn Probability indicating per pixel burn probability. Since this is a machine learning-based approach, it can be automated with a minimum amount of human intervention with significantly less time delays and geographic restrictions compared to other contemporary methods. We include results from our experiments and compare our approximation with the USGS Burn Probability using RMSE score.

## CaMBRAIN: Real-time, Continuous EEG Inference with Causal State Space Models

DevFeed: [CaMBRAIN: Real-time, Continuous EEG Inference with Causal State Space Models](<https://devfeed.tech/articles/cambrain-real-time-continuous-eeg-inference-with-causal-state-space-models-137258.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2605.28792>)

Author: Abhilash Durgam, Nyle Siddiqui, Jeffrey A. Chan-Santiago, Qiushi Fu, Elakkat D. Gireesh, Mubarak Shah

Published: 2026-11-17T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>), [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [Mamba](<https://devfeed.tech/topics/mamba.md>), [streaming data analytics](<https://devfeed.tech/topics/streaming-data-analytics.md>), [real-time](<https://devfeed.tech/topics/real-time.md>)

Tags: [continuous](<https://devfeed.tech/tags/continuous.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-hc](<https://devfeed.tech/tags/cs-hc.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [deep-learning](<https://devfeed.tech/tags/deep-learning.md>), [eeg](<https://devfeed.tech/tags/eeg.md>), [inference](<https://devfeed.tech/tags/inference.md>), [mamba](<https://devfeed.tech/tags/mamba.md>), [memory](<https://devfeed.tech/tags/memory.md>), [range](<https://devfeed.tech/tags/range.md>), [real-time](<https://devfeed.tech/tags/real-time.md>), [state-space-models](<https://devfeed.tech/tags/state-space-models.md>), [streaming](<https://devfeed.tech/tags/streaming.md>), [throughput](<https://devfeed.tech/tags/throughput.md>), [time-complexity](<https://devfeed.tech/tags/time-complexity.md>), [train](<https://devfeed.tech/tags/train.md>), [training](<https://devfeed.tech/tags/training.md>), [variable](<https://devfeed.tech/tags/variable.md>)

### AI overview

CaMBRAIN is a causal Mamba state space model designed to process variable-length EEG continuously in real time. It addresses the quadratic sequence scaling of attention-based models and the limited context of fixed-length sliding windows, using linear-time inference. Because brief EEG events may be separated by minutes, the authors introduce a multi-stage self-supervised training pipeline intended to teach the model's hidden state to retain long-range context; they argue reconstruction-focused objectives do not do this adequately for streaming models. The abstract reports state-of-the-art results on three EEG datasets and throughput over ten times higher than existing models. These claims are reported in the abstract; detailed methods and evaluation evidence are not included in the supplied excerpt.

### Source excerpt

arXiv:2605.28792v2 Announce Type: replace Abstract: Electroencephalography (EEG) is a critical, non-invasive method to monitor electrical brain activity. EEGs can span anywhere from a couple seconds to multiple hours, posing a major hurdle for existing deep learning methods due to two major factors: (1) existing EEG models are predominantly built upon the attention mechanism, incurring quadratic scaling as the sequence length increases, and (2) raw EEG signals must be processed in a sliding-window fashion due to fixed-length input requirements, preventing global understanding of the entire signal. To this extent, we propose CaMBRAIN - the first Causal, Mamba-based state space model (SSM) capable of real-time inference of EEG signals, arguing that bidirectional approaches are needlessly expensive given the causal, unidirectional nature of EEG. However, training such a model is non-trivial, as crucial EEG events can be extremely brief - within fractions of a second - yet separated by long intervals spanning minutes. Current EEG methods use self-supervised objectives that optimize for signal reconstruction, but these are not well suited for streaming SSMs; they fail to explicitly train the hidden state to retain the salient long-range context needed for streaming inference. We therefore introduce a multi-stage self-supervised training pipeline specifically tailored to encourage long-range memory retention and strong performance on EEG signals, while preserving the linear-time complexity of state space models. CaMBRAIN achieves state-of-the-art (SOTA) results across 3 different EEG datasets with >10x higher throughput than existing models, enabling the first model capable of long-range, continuous inference of variable-length EEG signals.

## Acting by Intent, Reacting by Sight: Visual Conditioned Reflexes for Real-Time VLM Agents

DevFeed: [Acting by Intent, Reacting by Sight: Visual Conditioned Reflexes for Real-Time VLM Agents](<https://devfeed.tech/articles/acting-by-intent-reacting-by-sight-visual-conditioned-reflexes-for-real-time-vlm-agents-137332.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.18723>)

Author: Qiancheng Zhou, Wenhua Zhang

Published: 2026-11-17T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>)

Topics: [Real-time AI interactions](<https://devfeed.tech/topics/real-time-ai-interactions.md>), [real-time](<https://devfeed.tech/topics/real-time.md>), [real-time 3D](<https://devfeed.tech/topics/real-time-3d.md>)

Tags: [acting](<https://devfeed.tech/tags/acting.md>), [agents](<https://devfeed.tech/tags/agents.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-cv](<https://devfeed.tech/tags/cs-cv.md>), [games](<https://devfeed.tech/tags/games.md>), [guidance](<https://devfeed.tech/tags/guidance.md>), [latency](<https://devfeed.tech/tags/latency.md>), [motion](<https://devfeed.tech/tags/motion.md>), [planner](<https://devfeed.tech/tags/planner.md>), [real-time](<https://devfeed.tech/tags/real-time.md>), [reflex](<https://devfeed.tech/tags/reflex.md>), [scripts](<https://devfeed.tech/tags/scripts.md>), [token](<https://devfeed.tech/tags/token.md>), [token-consumption](<https://devfeed.tech/tags/token-consumption.md>), [token-cost](<https://devfeed.tech/tags/token-cost.md>), [video-games](<https://devfeed.tech/tags/video-games.md>), [vision](<https://devfeed.tech/tags/vision.md>), [vlm](<https://devfeed.tech/tags/vlm.md>)

### AI overview

ViCoR pairs deliberate VLM gameplay control with a fast visual reflex branch: the main model sets and updates lightweight guidance for recurring situations, while a no-thinking VLM checks live local views and motion cues to choose sub-second actions. The authors report that the reflex branch handled 67.8% of high-frequency reactions, with 680 ms per check; average decision latency fell from 14.0 to 5.4 seconds and token use by 36.9%. Across 17 2D and 3D GameWorld games, task success rose from 52.9% to 64.7% and normalized progress from 66.5% to 80.4%, compared with the strongest deliberative VLM and script baselines. In fast-paced games, refining reflexes across episodes increased progress by 1.67x. The abstract also reports that a low-effort planner exceeded high-effort deliberative baselines by 8.1% at one-third the token cost.

### Source excerpt

arXiv:2611.18723v1 Announce Type: cross Abstract: Vision-Language Models (VLMs) have shown strong capabilities as generalist agents that perceive, reason, and act in interactive environments. Yet real-time environments such as video games demand both deliberate control for exploration and split-second reactions to fast-moving hazards. Existing agents struggle to handle both: relying solely on direct VLM actions is too slow for sudden events, whereas delegating execution to fixed scripts leaves the agent blind at the moment of action, leading to frequent misfires whenever the scene shifts. Humans overcome this by pairing normal conscious control with conditioned reflexes-while the mind handles deliberate actions and shapes reflex rules, the reflex itself still relies on live vision to make the final instant decision. Emulating this mechanism, we propose ViCoR (Visual Conditioned Reflex). Alongside normal gameplay actions, the main VLM defines and updates lightweight situational guidance for recurring events, while a fast visual reflex branch (invoking the VLM in no-thinking mode) inspects live local views with motion cues to make the final sub-second action decisions. By offloading 67.8% of high-frequency reactions to the reflex branch (680 ms per check), ViCoR reduces average per-action decision latency by 2.6x (from 14.0 s to 5.4 s) and cuts token consumption by 36.9%. Across 17 diverse 2D and 3D games in the GameWorld benchmark, ViCoR achieves state-of-the-art performance, improving task success rate by +11.8% (from 52.9% to 64.7%) and average normalized progress by +13.9% (from 66.5% to 80.4%) over the strongest deliberative VLM and script baselines. In fast-paced real-time games, ViCoR refines its reflexes across episodes to boost progress by 1.67x, and even with a low-effort main planner, surpasses high-effort deliberative baselines by +8.1% at one-third of the token cost.

## Build a real-time next-best-offer recommender using Databricks Feature Views

DevFeed: [Build a real-time next-best-offer recommender using Databricks Feature Views](<https://devfeed.tech/articles/build-a-real-time-next-best-offer-recommender-using-databricks-feature-views-136415.md>)

Original publisher: [Read original article](<https://www.databricks.com/blog/build-real-time-next-best-offer-recommender-using-databricks-feature-views>)

Author: Tian Tan; Sixuan He; Nick Joung; Julia Powell

Published: 2026-11-16T17:30:00Z

Content type: article

Language: en

Sources: [Databricks](<https://devfeed.tech/sources/databricks.md>)

Topics: [databricks](<https://devfeed.tech/topics/databricks.md>), [streaming data analytics](<https://devfeed.tech/topics/streaming-data-analytics.md>), [Event-Streaming](<https://devfeed.tech/topics/event-streaming.md>), [real-time](<https://devfeed.tech/topics/real-time.md>)

Tags: [2](<https://devfeed.tech/tags/2.md>), [3](<https://devfeed.tech/tags/3.md>), [after](<https://devfeed.tech/tags/after.md>), [aggregate](<https://devfeed.tech/tags/aggregate.md>), [all](<https://devfeed.tech/tags/all.md>), [also](<https://devfeed.tech/tags/also.md>), [amazon](<https://devfeed.tech/tags/amazon.md>), [amazon-msk](<https://devfeed.tech/tags/amazon-msk.md>), [best](<https://devfeed.tech/tags/best.md>), [build](<https://devfeed.tech/tags/build.md>), [customers](<https://devfeed.tech/tags/customers.md>), [data-science-and-ml](<https://devfeed.tech/tags/data-science-and-ml.md>), [databricks](<https://devfeed.tech/tags/databricks.md>), [feature](<https://devfeed.tech/tags/feature.md>), [financial-services](<https://devfeed.tech/tags/financial-services.md>), [next](<https://devfeed.tech/tags/next.md>), [offer](<https://devfeed.tech/tags/offer.md>), [personalization](<https://devfeed.tech/tags/personalization.md>), [platform](<https://devfeed.tech/tags/platform.md>), [real-time](<https://devfeed.tech/tags/real-time.md>), [time](<https://devfeed.tech/tags/time.md>), [using](<https://devfeed.tech/tags/using.md>), [want](<https://devfeed.tech/tags/want.md>)

### AI overview

The accelerator shows how Databricks Feature Views can keep training and online serving feature definitions aligned for a retail banking next-best-offer ranker. Its `create_training_set` point-in-time joins reconstruct historical values without future leakage; for inference, Model Serving retrieves customer features from the online store. The notebooks start with batch features and add Kafka clickstream aggregates, avoiding separate hand-written streaming feature logic. In the stated benchmark setup, the ranking endpoint handled about 56 requests per second and stayed within a 50 ms p95 service budget; adding streaming features increased latency by 3-4 ms. Events became model-visible in about 0.1 seconds. Results used a small, untuned configuration, and scale-to-zero can cause cold starts of tens of seconds. The data is synthetic, so the accelerator does not establish revenue or conversion gains, and teams must add eligibility, consent, suitability, and suppression controls before production. Part 2 requires a Unity Catalog Kafka connection and Amazon MSK connectivity.

### Source excerpt

Real-time personalization depends on understanding what customers want in the moment...

## StreamEmbed: Real-Time Indexing from Pixels for Screenshot Retrieval

DevFeed: [StreamEmbed: Real-Time Indexing from Pixels for Screenshot Retrieval](<https://devfeed.tech/articles/streamembed-real-time-indexing-from-pixels-for-screenshot-retrieval-135913.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.18516>)

Author: Dayoon Ko, Yichuan Wang, Soyeong Jeong, Joseph E. Gonzalez, Gunhee Kim, Sewon Min

Published: 2026-11-16T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [screenshot](<https://devfeed.tech/topics/screenshot.md>), [real-time](<https://devfeed.tech/topics/real-time.md>), [search-engines](<https://devfeed.tech/topics/search-engines.md>), [Cache](<https://devfeed.tech/topics/cache.md>), [Machine learning](<https://devfeed.tech/topics/machine-learning.md>), [Vectors & LLMs](<https://devfeed.tech/topics/vectors-llms.md>)

Tags: [adapter](<https://devfeed.tech/tags/adapter.md>), [agent](<https://devfeed.tech/tags/agent.md>), [agents](<https://devfeed.tech/tags/agents.md>), [benchmark](<https://devfeed.tech/tags/benchmark.md>), [blocks](<https://devfeed.tech/tags/blocks.md>), [computer-use](<https://devfeed.tech/tags/computer-use.md>), [cs-cv](<https://devfeed.tech/tags/cs-cv.md>), [cs-ir](<https://devfeed.tech/tags/cs-ir.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [embedding](<https://devfeed.tech/tags/embedding.md>), [embeddings](<https://devfeed.tech/tags/embeddings.md>), [encoding](<https://devfeed.tech/tags/encoding.md>), [exploits](<https://devfeed.tech/tags/exploits.md>), [fast](<https://devfeed.tech/tags/fast.md>), [faster](<https://devfeed.tech/tags/faster.md>), [foundation](<https://devfeed.tech/tags/foundation.md>), [frontier](<https://devfeed.tech/tags/frontier.md>), [gpu](<https://devfeed.tech/tags/gpu.md>), [indexing](<https://devfeed.tech/tags/indexing.md>), [pixels](<https://devfeed.tech/tags/pixels.md>), [real-time](<https://devfeed.tech/tags/real-time.md>), [retrieval](<https://devfeed.tech/tags/retrieval.md>), [screenshot](<https://devfeed.tech/tags/screenshot.md>)

### AI overview

StreamEmbed speeds up visual indexing of incoming screenshots by exploiting repeated pixels: it skips spatial blocks that duplicate a neighbor and reuses cached keys and values for blocks unchanged between screenshots. A learned adapter helps preserve fidelity to embeddings computed from full screenshots. On ScreenMemEval, with 10,426 questions over 184 hours of histories, it encoded up to 3.7x faster than full-screenshot encoding on an M2 Pro GPU without sacrificing accuracy, and improved Recall@10 by up to 6.3 points over OCR indexing at matched latency. Its vector index used 0.13 GB of RAM for a simulated year of screenshots. These are reported benchmark results; the supplied text does not describe evaluation beyond that setup.

### Source excerpt

arXiv:2611.18516v1 Announce Type: cross Abstract: Screen history can serve as searchable visual memory for people and agents, but unlike an offline corpus, it must be encoded and indexed as each screenshot arrives. OCR-based indexing is fast but loses visual information; visual encoding takes over two seconds. Yet screens change incrementally: most pixels repeat within and across screenshots. This raises a question: do visual encoders need to recompute their representations from scratch for every new screenshot? We present StreamEmbed, a system for incremental visual embedding that exploits this redundancy. Guided solely by pixel differences, it combines spatial token pruning, which skips blocks that repeat a neighbor, with temporal KV reuse, which reuses cached keys and values for blocks unchanged across screenshots. A small learned adapter compensates for pruning and reuse to preserve fidelity to full-screenshot embeddings. On ScreenMemEval, our benchmark of 10,426 questions over 184 hours of screen histories from two humans and a computer-use agent, StreamEmbed sets a new accuracy-latency Pareto frontier on an M2 Pro GPU: it encodes up to 3.7x faster than full-screenshot encoding without sacrificing accuracy and improves accuracy over OCR-based indexing by up to 6.3 Recall@10 points at matched latency. A memory-efficient vector index stores a simulated year of screenshots in 0.13 GB of RAM. Together, these results make real-time indexing of screen history in its native visual form practical, laying a foundation for fully local visual assistants.

## What is Real-Time Mode in Apache Spark?

DevFeed: [What is Real-Time Mode in Apache Spark?](<https://devfeed.tech/articles/what-is-real-time-mode-in-apache-spark-136421.md>)

Original publisher: [Read original article](<https://www.databricks.com/blog/what-is-real-time-mode>)

Author: Databricks Staff

Published: 2026-11-13T07:49:12Z

Content type: article

Language: en

Sources: [Databricks](<https://devfeed.tech/sources/databricks.md>)

Topics: [Apache Spark](<https://devfeed.tech/topics/spark.md>), [streaming data analytics](<https://devfeed.tech/topics/streaming-data-analytics.md>), [real-time](<https://devfeed.tech/topics/real-time.md>), [Apache Kafka](<https://devfeed.tech/topics/apache-kafka.md>), [Apache Flink](<https://devfeed.tech/topics/apache-flink.md>)

Tags: [17](<https://devfeed.tech/tags/17.md>), [2026](<https://devfeed.tech/tags/2026.md>), [aggregation](<https://devfeed.tech/tags/aggregation.md>), [apache](<https://devfeed.tech/tags/apache.md>), [apache-flink](<https://devfeed.tech/tags/apache-flink.md>), [apache-spark](<https://devfeed.tech/tags/apache-spark.md>), [api](<https://devfeed.tech/tags/api.md>), [architecture](<https://devfeed.tech/tags/architecture.md>), [autoscaling](<https://devfeed.tech/tags/autoscaling.md>), [availability](<https://devfeed.tech/tags/availability.md>), [batch](<https://devfeed.tech/tags/batch.md>), [batches](<https://devfeed.tech/tags/batches.md>), [benchmark](<https://devfeed.tech/tags/benchmark.md>), [benchmarks](<https://devfeed.tech/tags/benchmarks.md>), [blocking](<https://devfeed.tech/tags/blocking.md>), [data-plus-ai-foundations](<https://devfeed.tech/tags/data-plus-ai-foundations.md>), [real-time](<https://devfeed.tech/tags/real-time.md>), [spark](<https://devfeed.tech/tags/spark.md>), [streaming](<https://devfeed.tech/tags/streaming.md>), [structured](<https://devfeed.tech/tags/structured.md>), [trigger](<https://devfeed.tech/tags/trigger.md>)

### AI overview

Apache Spark Structured Streaming Real-Time Mode processes records continuously through long-running tasks, reducing latency from seconds to milliseconds without changing the query's core code. It is suited to workloads that need sub-second responses; micro-batch or availableNow costs less when seconds or minutes suffice. On Databricks, classic compute requires Runtime 16.4 LTS or later, Photon, autoscaling and spot instances disabled, plus an enablement setting; serverless use is limited to continuous Lakeflow Spark Declarative Pipelines. Capacity must cover concurrently running tasks. Kafka sources and sinks, foreach sinks, and most operators including stateful ones are supported. Delta output requires Kafka followed by a separate micro-batch query. Monitor Real-Time Mode latency metrics rather than batch duration; the end-to-end metric excludes sink write time. Latency varies with workload and capacity. The text says Databricks has GA support, while open-source availability is rolling out; it also notes stateful support arrives in Spark 4.3.

### Source excerpt

Real-Time Mode is a trigger for Apache Spark™ Structured Streaming that processes...

## STeP-C: Real-Time Neural Compression for Distributed Fiber-Optic Sensing at Scale

DevFeed: [STeP-C: Real-Time Neural Compression for Distributed Fiber-Optic Sensing at Scale](<https://devfeed.tech/articles/step-c-real-time-neural-compression-for-distributed-fiber-optic-sensing-at-scale-133178.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.17126>)

Author: Tingfeng Li, Ming-Fang Huang, Shaobo Han, Yue Tian

Published: 2026-11-13T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [Compression](<https://devfeed.tech/topics/compression.md>), [real-time](<https://devfeed.tech/topics/real-time.md>)

Tags: [acoustic-sensing](<https://devfeed.tech/tags/acoustic-sensing.md>), [acquisition](<https://devfeed.tech/tags/acquisition.md>), [arithmetic](<https://devfeed.tech/tags/arithmetic.md>), [arithmetic-coding](<https://devfeed.tech/tags/arithmetic-coding.md>), [buffer](<https://devfeed.tech/tags/buffer.md>), [compression](<https://devfeed.tech/tags/compression.md>), [cs-cv](<https://devfeed.tech/tags/cs-cv.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [distributed](<https://devfeed.tech/tags/distributed.md>), [entropy](<https://devfeed.tech/tags/entropy.md>), [entropy-coding](<https://devfeed.tech/tags/entropy-coding.md>), [fiber](<https://devfeed.tech/tags/fiber.md>), [fp16](<https://devfeed.tech/tags/fp16.md>), [gpu](<https://devfeed.tech/tags/gpu.md>), [inference](<https://devfeed.tech/tags/inference.md>), [live](<https://devfeed.tech/tags/live.md>), [neural](<https://devfeed.tech/tags/neural.md>), [offline](<https://devfeed.tech/tags/offline.md>), [optimized](<https://devfeed.tech/tags/optimized.md>), [real-time](<https://devfeed.tech/tags/real-time.md>), [scale](<https://devfeed.tech/tags/scale.md>), [sensing](<https://devfeed.tech/tags/sensing.md>)

### AI overview

STeP-C demonstrates real-time neural compression on a live distributed acoustic sensing system, reporting 98.85% file-size reduction at 31.04 dB full-band PSNR and 535 MB/s throughput, above the stated 324 MB/s requirement for 1 kHz, 81 km streams. Its design separates spatial encoding, temporal prediction, and residual coding. To address entropy coding as the streaming bottleneck, it uses GPU-side symbol computation, cached probability tables, parallel GIL-free arithmetic coding, FP16 inference, batched coding, and a GPU ring buffer. The abstract reports better performance than conventional codecs at practical streaming bitrates, transfer to unseen channel ranges within the same acquisition system without retraining, and detector consistency of 96.62% high-confidence class agreement and 100% Jaccard similarity on detected event types. These claims are limited to the reported testbed and excerpt.

### Source excerpt

arXiv:2611.17126v1 Announce Type: cross Abstract: Distributed fiber-optic sensing (DFOS) technologies such as Distributed Acoustic Sensing (DAS) generate continuous, high-resolution spatio-temporal data at rates exceeding hundreds of megabytes per second, creating severe challenges for real-time storage and transmission. While neural compression methods can achieve strong rate-distortion performance on sensing data, prior approaches either require per-segment retraining incompatible with streaming, or have only been validated offline. None have been demonstrated end-to-end on a continuously streaming DAS acquisition system at scale. We present STeP-C (Spatio-Temporal Predictive Compression), a neural compression framework that decouples spatial encoding, temporal prediction, and entropy-optimized residual coding, trained end-to-end with a rate-distortion objective motivated by conditional entropy reduction. Critically, we identify entropy coding as the dominant bottleneck for streaming deployment. We address it through GPU-side symbol computation, cached probability tables, and parallel GIL-free arithmetic coding, together with FP16 inference and batched entropy coding, enabling a full real-time pipeline built around a GPU ring buffer. We validate this pipeline on a live DAS testbed, achieving a 98.85% file size reduction at 31.04 dB full-band PSNR and an average throughput of 535 MB/s, exceeding the 324 MB/s requirement for 1 kHz, 81 km DAS streams. We further show that STeP-C substantially outperforms conventional codecs at practical streaming bitrates, can be applied to unseen channel ranges within the same acquisition system without retraining, and largely maintains downstream detector consistency, with 96.62% high-confidence class agreement and 100% Jaccard similarity on detected event types.

## Scaling VLA Serving Under Robotic Execution Constraints

DevFeed: [Scaling VLA Serving Under Robotic Execution Constraints](<https://devfeed.tech/articles/scaling-vla-serving-under-robotic-execution-constraints-131528.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.14969>)

Author: Yue Zhang, Zicong Ye, Lufang Chen, Dance Yang, Mingyang Li, Zhenwei Duan, Michael Zhao, Ziye Deng, Starrick Liu, Ruizhi Chengze, YongHua Chen, SongAo Han, Yu Sun, Ran Yu, Xiaofan Li, Ruyi Gan, Hao Wan

Published: 2026-11-13T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Distributed Computing](<https://devfeed.tech/sources/arxiv-distributed-computing.md>)

Topics: [Robot Manipulation](<https://devfeed.tech/topics/robot-manipulation.md>), [Physical AI](<https://devfeed.tech/topics/physical-ai.md>), [LLM optimization](<https://devfeed.tech/topics/llm-optimization.md>), [GPU](<https://devfeed.tech/topics/gpu.md>), [real-time](<https://devfeed.tech/topics/real-time.md>)

Tags: [capacity](<https://devfeed.tech/tags/capacity.md>), [cost](<https://devfeed.tech/tags/cost.md>), [critical](<https://devfeed.tech/tags/critical.md>), [cs-dc](<https://devfeed.tech/tags/cs-dc.md>), [cs-ro](<https://devfeed.tech/tags/cs-ro.md>), [deployments](<https://devfeed.tech/tags/deployments.md>), [efficiency](<https://devfeed.tech/tags/efficiency.md>), [execution](<https://devfeed.tech/tags/execution.md>), [fleet](<https://devfeed.tech/tags/fleet.md>), [gpu](<https://devfeed.tech/tags/gpu.md>), [gpu-efficiency](<https://devfeed.tech/tags/gpu-efficiency.md>), [inference](<https://devfeed.tech/tags/inference.md>), [infrastructure](<https://devfeed.tech/tags/infrastructure.md>), [language](<https://devfeed.tech/tags/language.md>), [large](<https://devfeed.tech/tags/large.md>), [manipulation](<https://devfeed.tech/tags/manipulation.md>), [models](<https://devfeed.tech/tags/models.md>), [parallelism](<https://devfeed.tech/tags/parallelism.md>), [production](<https://devfeed.tech/tags/production.md>), [robotic](<https://devfeed.tech/tags/robotic.md>), [serving](<https://devfeed.tech/tags/serving.md>), [vla](<https://devfeed.tech/tags/vla.md>)

### AI overview

XInfer is a production-deployed serving system intended to lower inference infrastructure costs for fleets of VLA-powered robots. It coordinates heterogeneous VLA computation with changing response requirements during robotic execution, using parallelism while managing interference to improve GPU efficiency and protect time-critical feedback. Evaluated on three VLA models with production-derived workloads under physical-execution constraints, it achieved 1.26-3.75x the effective robot capacity of state-of-the-art systems. The supplied excerpt does not specify the compared systems or evaluation details.

### Source excerpt

arXiv:2611.14969v1 Announce Type: cross Abstract: Vision-language-action (VLA) models have emerged as a promising paradigm for general-purpose robotic manipulation. In our production setting, hundreds of VLA-powered robots are already operating in real-world environments, creating an immediate need for efficient fleet serving. We present XInfer, a production-deployed VLA serving system designed to reduce the inference infrastructure cost of large-scale robotic deployments. XInfer jointly coordinates heterogeneous VLA computation with the evolving response requirements of robotic execution. By exploiting computational parallelism while managing interference, XInfer improves GPU efficiency while protecting time-critical robotic feedback. We evaluate XInfer across three VLA models using production-derived workloads, achieving 1.26-3.75 times the effective robot capacity (ERC) of state-of-the-art systems under physical-execution constraints. Our implementation is publicly available at https://github.com/X-Square-Robot/xinfer.

## An Integrated Architecture for Data-Efficient Real-Time Neural Imitation of Nonlinear Time-Optimal Model Predictive Control

DevFeed: [An Integrated Architecture for Data-Efficient Real-Time Neural Imitation of Nonlinear Time-Optimal Model Predictive Control](<https://devfeed.tech/articles/an-integrated-architecture-for-data-efficient-real-time-neural-imitation-of-nonlinear-time-optimal-model-predictive-control-133163.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.17005>)

Author: Maarten De Baecke, Flavia Sofia Acerbo, Andrea Giusti, Wilm Decr\\'e

Published: 2026-11-13T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [Neural Network](<https://devfeed.tech/topics/neural-network.md>), [real-time](<https://devfeed.tech/topics/real-time.md>)

Tags: [aggregation](<https://devfeed.tech/tags/aggregation.md>), [architecture](<https://devfeed.tech/tags/architecture.md>), [constraint](<https://devfeed.tech/tags/constraint.md>), [constraint-satisfaction](<https://devfeed.tech/tags/constraint-satisfaction.md>), [control](<https://devfeed.tech/tags/control.md>), [controller](<https://devfeed.tech/tags/controller.md>), [correlation](<https://devfeed.tech/tags/correlation.md>), [cost](<https://devfeed.tech/tags/cost.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [cs-ro](<https://devfeed.tech/tags/cs-ro.md>), [cs-sy](<https://devfeed.tech/tags/cs-sy.md>), [data](<https://devfeed.tech/tags/data.md>), [dataset](<https://devfeed.tech/tags/dataset.md>), [eess-sy](<https://devfeed.tech/tags/eess-sy.md>), [generation](<https://devfeed.tech/tags/generation.md>), [hardware](<https://devfeed.tech/tags/hardware.md>), [horizon](<https://devfeed.tech/tags/horizon.md>), [imitation](<https://devfeed.tech/tags/imitation.md>), [model](<https://devfeed.tech/tags/model.md>), [network](<https://devfeed.tech/tags/network.md>), [neural](<https://devfeed.tech/tags/neural.md>), [neural-network](<https://devfeed.tech/tags/neural-network.md>), [real-time](<https://devfeed.tech/tags/real-time.md>), [time](<https://devfeed.tech/tags/time.md>)

### AI overview

The paper imitates a long-horizon, nonconvex time-optimal MPC controller with a neural network to make control fast enough for hardware. Its self-informed sampling (SIFS) uses a learned time-to-go to request expert labels where the policy departs from time-optimal behavior; it reportedly matches standard dataset aggregation in about one-third of the training time and with less than half the data. The broader architecture addresses dataset correlation, suboptimal labels, covariate shift, constraint satisfaction and model mismatch. On a Furuta pendulum, the resulting controller reportedly matches the expert's region of attraction, increases control frequency from 1.4 Hz to 1 kHz, and swings up and stabilizes the system along trajectories close to the expert solution.

### Source excerpt

arXiv:2611.17005v1 Announce Type: cross Abstract: Nonlinear time-optimal model predictive control (TOMPC) enables highly performant control of constrained systems, but its computational cost prohibits real-time use on fast dynamical systems. Neural network imitation of the TOMPC control law can reduce online computational costs, yet existing work mostly targets quadratic cost formulations in simulation and addresses the challenges of neural controllers in isolation. This work imitates a long-horizon nonconvex TOMPC with hard terminal constraints, whose high computational cost limits training-data generation. We present (i) \emph{self-informed sampling (SIFS)}, a data-efficient expert-sampling strategy that uses a learned time-to-go to query the expert only where the policy deviates from time-optimal behavior, (ii) a complete training and control architecture that jointly addresses dataset correlation, suboptimal expert labels, covariate shift, constraint satisfaction and model mismatch, and (iii) real-world validation on a Furuta pendulum. SIFS matches standard dataset aggregation performance in roughly one-third of the training time and with less than half the training data. The resulting controller matches the region of attraction of the expert TOMPC while raising the control frequency from 1.4~Hz to 1~kHz. On hardware, the controller swings up and stabilizes the pendulum along trajectories closely matching the expert TOMPC solution.

## TransGHOST: Real-Time, Synthesis-Free Reconstruction of Instrument-Occluded Regions in Ophthalmic Microsurgery

DevFeed: [TransGHOST: Real-Time, Synthesis-Free Reconstruction of Instrument-Occluded Regions in Ophthalmic Microsurgery](<https://devfeed.tech/articles/transghost-real-time-synthesis-free-reconstruction-of-instrument-occluded-regions-in-ophthalmic-microsurgery-128380.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.13971>)

Author: Niran Nataraj, Maina Sogabe, Masamichi Yamashita, Norihiko Ito, Kenji Kawashima

Published: 2026-11-11T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>)

Topics: [Image processing](<https://devfeed.tech/topics/image-processing.md>), [Medical imaging](<https://devfeed.tech/topics/medical-imaging.md>), [real-time](<https://devfeed.tech/topics/real-time.md>)

Tags: [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-cv](<https://devfeed.tech/tags/cs-cv.md>), [cs-ro](<https://devfeed.tech/tags/cs-ro.md>), [eess-iv](<https://devfeed.tech/tags/eess-iv.md>), [evaluation](<https://devfeed.tech/tags/evaluation.md>), [latency](<https://devfeed.tech/tags/latency.md>), [online](<https://devfeed.tech/tags/online.md>), [pixel](<https://devfeed.tech/tags/pixel.md>), [provenance](<https://devfeed.tech/tags/provenance.md>), [real-time](<https://devfeed.tech/tags/real-time.md>), [reference](<https://devfeed.tech/tags/reference.md>), [robot](<https://devfeed.tech/tags/robot.md>), [synthesis](<https://devfeed.tech/tags/synthesis.md>), [validation](<https://devfeed.tech/tags/validation.md>)

### AI overview

TransGHOST reconstructs instrument-occluded tissue in ophthalmic surgery video by resampling recorded frames, avoiding synthesized pixels. Its causal safe mode fits geometric transforms to visible regions, reports pixel-level confidence and provenance, and abstains where support is insufficient. On a canine cataract surgery corpus, it achieved 31.89 dB masked PSNR and 0.915 masked SSIM, with 51.7 ms median latency; a held-out cohort result was 29.83 dB masked PSNR. In validation, matched-mask evaluation showed a 3.45 dB advantage over LaMa. Region-aware reference selection improved masked PSNR by 3.60 dB over recency when candidate frames could also be occluded. The excerpt describes a method aimed at brief, repeated occlusions and does not establish performance beyond the evaluated setting.

### Source excerpt

arXiv:2611.13971v1 Announce Type: cross Abstract: Intraoperative scene perception in ophthalmic microsurgery is limited by instrument occlusion: when a tool enters the high-magnification field, it conceals tissue from both the surgeon and the perception components of robot-assisted systems that process the video. Generative inpainting can remove the occluder but replaces the missing image content with synthesis, which is unsuitable when visual provenance matters. Many video inpainters also depend on future frames and cannot operate online. We present TransGHOST, a causal reference-guided reconstruction pipeline whose non-generative safe mode operates in real time. Every restored value is obtained by resampling a recorded frame using geometric transforms fitted only to visible regions. The system provides per-pixel confidence and provenance and marks unsupported pixels as abstentions. We evaluate TransGHOST on a new veterinary clinical corpus of canine cataract surgery with pixel-level instrument and anatomy labels. Only the occluded region is scored, and each scoring target is verified to differ from the reference supplied to the system. Safe mode reaches 31.89 dB masked PSNR and 0.915 masked SSIM at 51.7 ms median and 85.5 ms 95th-percentile latency. On a pre-declared held-out cohort using instrument cutouts excluded from segmentation training, it reaches 29.83 dB masked PSNR, while matched-mask evaluation on validation shows a 3.45 dB advantage over LaMa. Region-aware reference selection improves masked PSNR by 3.60 dB over recency when candidate references can themselves be occluded. Reference-age analysis further defines the operating interval for the brief, repeated occlusions targeted by TransGHOST.

## CAppleNet: A Coordinate Attention-Based YOLO11 for Real-Time Apple Stem Cavity and Calyx Detection

DevFeed: [CAppleNet: A Coordinate Attention-Based YOLO11 for Real-Time Apple Stem Cavity and Calyx Detection](<https://devfeed.tech/articles/capplenet-a-coordinate-attention-based-yolo11-for-real-time-apple-stem-cavity-and-calyx-detection-128370.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.13920>)

Author: Alican G\\"une\\c{s}, Robert Selim Hill, G\\"okhan Hasano\\u{g}lu, Murat Kurt

Published: 2026-11-11T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>)

Topics: [real-time](<https://devfeed.tech/topics/real-time.md>)

Tags: [ablation](<https://devfeed.tech/tags/ablation.md>), [alignment](<https://devfeed.tech/tags/alignment.md>), [apple](<https://devfeed.tech/tags/apple.md>), [architecture](<https://devfeed.tech/tags/architecture.md>), [attention](<https://devfeed.tech/tags/attention.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-cv](<https://devfeed.tech/tags/cs-cv.md>), [custom](<https://devfeed.tech/tags/custom.md>), [data-augmentation](<https://devfeed.tech/tags/data-augmentation.md>), [dataset](<https://devfeed.tech/tags/dataset.md>), [deployment](<https://devfeed.tech/tags/deployment.md>), [detection](<https://devfeed.tech/tags/detection.md>), [enhancement](<https://devfeed.tech/tags/enhancement.md>), [experiment](<https://devfeed.tech/tags/experiment.md>), [orientation](<https://devfeed.tech/tags/orientation.md>), [real-time](<https://devfeed.tech/tags/real-time.md>), [stem](<https://devfeed.tech/tags/stem.md>), [yolo11](<https://devfeed.tech/tags/yolo11.md>)

### AI overview

On a self-collected dataset of 1,506 apples imaged under controlled, fixed-camera conditions, replacing YOLO11s's C2PSA block with Coordinate Attention reduced parameters by 10.2%, matched baseline overall F1 (0.9038 versus 0.9047), and achieved the best mAP@0.5 (0.935) and stem-cavity F1 (0.8217). Higher input resolution, six tested augmentation variants, and manual optimizer tuning did not improve on the default baseline. The authors identify a confidence threshold of 0.15 for the CA model; combining that architecture with the best augmentation variant reversed its gain, so the effects were not additive. These findings target real-time apple landmark detection for orientation-aware sorting, but the images were captured in controlled conditions.

### Source excerpt

arXiv:2611.13920v1 Announce Type: cross Abstract: Automated fruit grading, sorting, and orientation systems require real-time, accurate detection of fruit-level morphological landmarks rather than the fruit boundary alone. This paper presents a custom, fully self-collected and self-annotated dataset of 1506 apple images (1054 training, 301 validation, 151 test) captured under controlled, fixed-camera conditions and annotated for three target classes: fruit body, stem cavity, and calyx. A YOLO11s detector trained with default hyperparameters is adopted as the baseline, and a systematic, one-factor-at-a-time ablation study is conducted across input resolution, data augmentation policy, optimizer configuration, and lightweight architectural enhancement to identify the factors that most improve detection of these fine-grained landmarks under high inter-cultivar color and texture variability. Neither increased input resolution, nor any of six tested augmentation variants, nor manual optimizer tuning improved on the untuned baseline (F1 = 0.9047); only a same-slot architectural substitution of the backbone's C2PSA block with Coordinate Attention (CA) matched the baseline's overall F1 (0.9038) while reducing parameter count by 10.2% and achieving the study's best mAP@0.5 (0.935) and best stem-cavity F1 (0.8217). A confidence-threshold sweep identified 0.15 as the deployment operating point for this model, and a confirmatory experiment combining the CA-swap architecture with the best-performing augmentation variant showed the two effects do not combine additively, reversing the architectural gain rather than compounding it. The resulting design recommendations --- the CA-swap architecture alone, at a 0.15 confidence threshold --- target real-time apple landmark detection for orientation-aware industrial sorting and alignment systems.

## Programmable GPU-Accelerated dApps for Real-Time Edge Inference and ISAC on NVIDIA Aerial Testbed

DevFeed: [Programmable GPU-Accelerated dApps for Real-Time Edge Inference and ISAC on NVIDIA Aerial Testbed](<https://devfeed.tech/articles/programmable-gpu-accelerated-dapps-for-real-time-edge-inference-and-isac-on-nvidia-aerial-testbed-127830.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2512.06493>)

Author: Davide Villa, Mauro Belgiovine, Nicholas Hedberg, Michele Polese, Chris Dick, Tommaso Melodia

Published: 2026-11-11T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Networking](<https://devfeed.tech/sources/arxiv-networking.md>)

Topics: [real-time](<https://devfeed.tech/topics/real-time.md>), [TensorRT](<https://devfeed.tech/topics/tensorrt.md>), [network-intelligence](<https://devfeed.tech/topics/network-intelligence.md>), [Transformers](<https://devfeed.tech/topics/transformers.md>), [Nvidia](<https://devfeed.tech/topics/nvidia.md>)

Tags: [5g](<https://devfeed.tech/tags/5g.md>), [6g](<https://devfeed.tech/tags/6g.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-applications](<https://devfeed.tech/tags/ai-applications.md>), [ai-logic](<https://devfeed.tech/tags/ai-logic.md>), [ai-native](<https://devfeed.tech/tags/ai-native.md>), [artificial-intelligence](<https://devfeed.tech/tags/artificial-intelligence.md>), [artificial-intelligence-ai](<https://devfeed.tech/tags/artificial-intelligence-ai.md>), [backends](<https://devfeed.tech/tags/backends.md>), [bandwidth](<https://devfeed.tech/tags/bandwidth.md>), [cells](<https://devfeed.tech/tags/cells.md>), [cellular](<https://devfeed.tech/tags/cellular.md>), [cs-ni](<https://devfeed.tech/tags/cs-ni.md>), [dapps](<https://devfeed.tech/tags/dapps.md>), [edge](<https://devfeed.tech/tags/edge.md>), [edge-inference](<https://devfeed.tech/tags/edge-inference.md>), [gpu-accelerated](<https://devfeed.tech/tags/gpu-accelerated.md>), [inference](<https://devfeed.tech/tags/inference.md>), [nvidia](<https://devfeed.tech/tags/nvidia.md>), [real-time](<https://devfeed.tech/tags/real-time.md>), [testbed](<https://devfeed.tech/tags/testbed.md>)

### AI overview

The paper presents an open-source framework that feeds physical-layer signals from an NVIDIA Aerial Testbed GPU-accelerated gNB to edge AI applications using the Open RAN dApp architecture. It reports about 84 μs of framework latency per slot and about 123 μs for control loops with lightweight TensorRT inference, and evaluates two GPU platforms under different sharing modes as the number of cells and dApps increases. Its cuSense demonstration uses uplink DMRS channel estimates, removes static multipath, and applies a neural network to locate a moving person without dedicated sensing hardware or changes to 5G signals. On a 3GPP-compliant 5G NR deployment, cuSense reports 73 cm mean error on runs unseen during training, 79% of predictions within 1 m, and 241 μs live runtime. The framework and dataset are released as open source.

### Source excerpt

arXiv:2512.06493v3 Announce Type: replace Abstract: The transition of cellular networks to (i) software-based systems on commodity hardware and (ii) platforms for services beyond connectivity introduces critical system-level challenges. As sensing emerges as a key feature toward 6G standardization, supporting Integrated Sensing and Communication (ISAC) with limited bandwidth and piggybacking on communication signals, while maintaining high reliability and performance, remains a fundamental challenge. In this paper, we provide two key contributions. First, we present a programmable, open-source framework for processing PHY signals through real-time, GPU-accelerated Artificial Intelligence (AI) applications on the edge Radio Access Network (RAN) infrastructure. Building on the Open RAN dApp architecture, the framework interfaces with a GPU-accelerated gNB based on NVIDIA Aerial Testbed (ATB), feeding PHY data to custom AI logic with about 84 $\mu$s of framework latency per slot and control loops with inference in about 123 $\mu$s for lightweight TensorRT models, multiple inference engines, and support for several AI backends. We evaluate the framework on two GPU platforms, with different GPU sharing modes and an increasing number of cells and dApps. Second, we demonstrate the framework capabilities through cuSense, an indoor localization dApp that consumes uplink DMRS channel estimates, removes static multipath components, and runs a neural network to infer the position of a moving person. Evaluated on a 3GPP-compliant 5G NR deployment, cuSense achieves a mean localization error of 73 cm on runs unseen during training, with 79% of predictions falling within 1 meter, and runs live in 241 $\mu$s, without dedicated sensing hardware or modifications to the 5G signals. The framework is released as open source, together with the cuSense dataset, providing a reference design for future AI-native RANs and ISAC applications.

## Running AV Reasoning Models Within Onboard Compute and Latency Limits

DevFeed: [Running AV Reasoning Models Within Onboard Compute and Latency Limits](<https://devfeed.tech/articles/running-av-reasoning-models-within-onboard-compute-and-latency-limits-127099.md>)

Original publisher: [Read original article](<https://developer.nvidia.com/blog/running-av-reasoning-models-within-onboard-compute-and-latency-limits/>)

Author: Marco Pavone

Published: 2026-11-10T16:00:00Z

Content type: release

Language: en

Sources: [NVIDIA Developer](<https://devfeed.tech/sources/nvidia-developer.md>), [NVIDIA Technical Blog](<https://devfeed.tech/sources/nvidia-technical-blog.md>)

Topics: [NVIDIA DRIVE](<https://devfeed.tech/topics/nvidia-drive.md>), [llm-reasoning](<https://devfeed.tech/topics/llm-reasoning.md>), [performance-engineering](<https://devfeed.tech/topics/performance-engineering.md>), [real-time](<https://devfeed.tech/topics/real-time.md>), [Post-training optimization](<https://devfeed.tech/topics/post-training-optimization.md>)

Tags: [autonomous-vehicles](<https://devfeed.tech/tags/autonomous-vehicles.md>), [av](<https://devfeed.tech/tags/av.md>), [compute](<https://devfeed.tech/tags/compute.md>), [cosmos](<https://devfeed.tech/tags/cosmos.md>), [developer-tools-techniques](<https://devfeed.tech/tags/developer-tools-techniques.md>), [drive-agx](<https://devfeed.tech/tags/drive-agx.md>), [latency](<https://devfeed.tech/tags/latency.md>), [models](<https://devfeed.tech/tags/models.md>), [reasoning](<https://devfeed.tech/tags/reasoning.md>), [reasoning-models](<https://devfeed.tech/tags/reasoning-models.md>), [robotics](<https://devfeed.tech/tags/robotics.md>), [simulation-modeling-design](<https://devfeed.tech/tags/simulation-modeling-design.md>), [thor](<https://devfeed.tech/tags/thor.md>)

### AI overview

Alpamayo 2 Edge combines a 2B Nemotron-based reasoning backbone with a diffusion action expert to produce causal reasoning traces and driving trajectories from surround-camera, temporal, and navigation inputs. It generates reasoning adaptively, and closed-loop reinforcement learning in AlpaGym improved closed-loop driving performance by 48.9% over the best checkpoint without that training. Deployment on DRIVE AGX Thor requires an optimization workflow including FP8 calibration, ONNX export, and TensorRT engine builds; the stated pixel-to-trajectory latency is 160-190 ms depending on reasoning. AlpaJudge-RB scores candidate reasoning against a reference, while AlpaJudge-RF needs synchronized visual evidence and meta-action context but no reference rationale. The text recommends reviewing low scores because they may mark failures or difficult cases, and reporting reasoning scores alongside separate trajectory and safety measures. These results and workflows are presented as development guidance, not a guarantee of vehicle performance.

### Source excerpt

Autonomous vehicle (AV) developers need reasoning models that can operate within the compute and latency constraints of an onboard system. Larger models provide...

## Adapting Multi-Stage Distributed Real-Time Systems Design to Vehicular Edge Computing

DevFeed: [Adapting Multi-Stage Distributed Real-Time Systems Design to Vehicular Edge Computing](<https://devfeed.tech/articles/adapting-multi-stage-distributed-real-time-systems-design-to-vehicular-edge-computing-126745.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.12370>)

Author: Niraj Kumar, Anant Gautam

Published: 2026-11-10T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Distributed Computing](<https://devfeed.tech/sources/arxiv-distributed-computing.md>)

Topics: [real-time](<https://devfeed.tech/topics/real-time.md>), [scheduling](<https://devfeed.tech/topics/scheduling.md>), [distributed algorithm](<https://devfeed.tech/topics/distributed-algorithm.md>), [resource orchestration](<https://devfeed.tech/topics/resource-orchestration.md>)

Tags: [cs-dc](<https://devfeed.tech/tags/cs-dc.md>), [distributed](<https://devfeed.tech/tags/distributed.md>), [edge-computing](<https://devfeed.tech/tags/edge-computing.md>), [real-time](<https://devfeed.tech/tags/real-time.md>), [stage](<https://devfeed.tech/tags/stage.md>)

### AI overview

The paper models remotely processed vehicular applications as multi-stage pipelines that access heterogeneous resources in sequence. It proposes a joint mapping and scheduling heuristic that extends optimal priority assignment to account for vehicle mobility and real-time constraints, aiming to build feasible schedules, minimize local-device energy use, and meet deadlines for offloaded jobs. In simulations, the approach consistently outperformed a baseline using the same delay-composition framework and a deadline decomposition-based approach. The supplied text reports simulation results but gives no numerical performance gains.

### Source excerpt

arXiv:2611.12370v1 Announce Type: new Abstract: Vehicular Edge Computing (VEC) aims to support computation-intensive applications in intelligent transportation systems while meeting stringent latency requirements. When processed remotely, applications require access to different resource types in a specific sequence, forming a multi-stage processing pipeline. This structure closely resembles multi-stage distributed applications executing across heterogeneous resources, making established multi-stage distributed real-time scheduling techniques well suited for modeling VEC systems. The resulting model accommodates diverse resource configurations and access patterns. Building on this model, we propose a joint mapping and scheduling approach that accounts for vehicle mobility and real-time constraints. The proposed heuristic extends optimal priority assignment for multi-stage systems to the VEC setting, to construct feasible schedules while minimizing local-device energy consumption and ensuring that offloaded jobs meet their deadlines. Extensive simulations show that the proposed approach consistently outperforms both a baseline based on the same delay-composition framework and a deadline decomposition-based approach.

[Next page](<https://devfeed.tech/topics/real-time.md?cursor=WyIyMDI2LTExLTEwVDA1OjAwOjAwKzAwOjAwIiwgIjY3YmM0MWM4LWY1OWUtNDFlNy04YTMwLTM3ZDA5Mzc1ODNhMSJd>)