# lunar foundation model

Open-source AI foundation model for lunar-science data analysis, with a public fine-tuning and inference software release.

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

## Pairing AIS with RF: Analysis of a Markovian Approach for Maritime Data Fusion

DevFeed: [Pairing AIS with RF: Analysis of a Markovian Approach for Maritime Data Fusion](<https://devfeed.tech/articles/pairing-ais-with-rf-analysis-of-a-markovian-approach-for-maritime-data-fusion-135922.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.18563>)

Author: Daniel Grimm, Kyra Jongman, Renato Cordeiro Ferreira, Giuseppe Cascavilla, Alfredo Cuzzocrea, Willem-Jan Van Den Heuvel

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

Content type: article

Language: en

Sources: [arXiv: Cryptography and Security](<https://devfeed.tech/sources/arxiv-cryptography-and-security.md>), [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [lunar foundation model](<https://devfeed.tech/topics/lunar-foundation-model.md>), [Data analysis](<https://devfeed.tech/topics/data-analysis.md>)

Tags: [ais](<https://devfeed.tech/tags/ais.md>), [bias](<https://devfeed.tech/tags/bias.md>), [cs-cr](<https://devfeed.tech/tags/cs-cr.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [data-fusion](<https://devfeed.tech/tags/data-fusion.md>), [detection](<https://devfeed.tech/tags/detection.md>), [fusion](<https://devfeed.tech/tags/fusion.md>), [maritime](<https://devfeed.tech/tags/maritime.md>), [markov](<https://devfeed.tech/tags/markov.md>), [model](<https://devfeed.tech/tags/model.md>), [nearest-neighbor](<https://devfeed.tech/tags/nearest-neighbor.md>), [noise](<https://devfeed.tech/tags/noise.md>), [pairing](<https://devfeed.tech/tags/pairing.md>), [precision](<https://devfeed.tech/tags/precision.md>), [process](<https://devfeed.tech/tags/process.md>), [rf](<https://devfeed.tech/tags/rf.md>), [spatial](<https://devfeed.tech/tags/spatial.md>), [synthetic](<https://devfeed.tech/tags/synthetic.md>), [temporal](<https://devfeed.tech/tags/temporal.md>), [validation](<https://devfeed.tech/tags/validation.md>)

### AI overview

The study uses a Pair Hidden Markov Model (PHMM) to match space-based RF vessel detections to AIS trajectories using spatial and temporal information while accounting for noise and timing differences. On NOAA AIS data with synthetic RF detections, a length-corrected Forward score achieved 0.7776 top-1 precision and 0.637 AUC for dark-vessel detection after prefiltering. A log-odds score improved these to 0.8580 and 0.852. Its length-corrected form reduced some trajectory biases but still favored candidates farther from the RF detection. A time-weighted nearest-neighbor baseline performed better, with 0.9013 precision and 0.904 AUC; the tested single-detection PHMM formulation approached but did not surpass it.

### Source excerpt

arXiv:2611.18563v1 Announce Type: new Abstract: Monitoring maritime activities is important for safety and security, particularly for detecting illegal activities, but remains challenging due to the size and complexity of the maritime domain. The Automatic Identification System (AIS) is commonly used for this purpose, despite its known vulnerabilities. In contrast, space-based radio frequency (RF) observations provide an independent source of vessel activity but lack ship identification and therefore cannot identify vessels on their own. Following the CRISP-DM process, this study applies a Pair Hidden Markov Model (PHMM) to align individual RF detections with AIS trajectories, using temporal and spatial information while modeling noise and timing discrepancies. We evaluate it on NOAA AIS data with synthetic RF detections against nearest-neighbor baselines and analyze its errors with bias tests on trajectory length, sampling density, stationarity and AIS--RF distance. The length-corrected Forward score reaches a top-1 precision of $0.7776$ on the validation split of multi-candidate detections, where errors are possible, and an AUC of $0.637$ for detecting dark vessels among the detections that pass the prefilter. With a single RF detection, the score mostly reflects the AIS trajectory itself, and its errors favor longer and more stationary trajectories. A log-odds score, which compares the full model with a null model without match transitions, raises precision to $0.8580$ and AUC to $0.852$. Its length-corrected variant no longer shows a significant bias towards stationary trajectories and short inter-message distances, but still favors candidates farther from the RF detection. A time-weighted nearest-neighbor baseline without fitting remains ahead (precision $0.9013$, AUC $0.904$), so this single-detection, hand-designed PHMM formulation approaches but does not beat it.

## Introducing Reflection Beam: an open-weight model for agentic coding on AWS

DevFeed: [Introducing Reflection Beam: an open-weight model for agentic coding on AWS](<https://devfeed.tech/articles/introducing-reflection-beam-an-open-weight-model-for-agentic-coding-on-aws-88891.md>)

Original publisher: [Read original article](<https://aws.amazon.com/blogs/machine-learning/introducing-reflection-beam-an-open-weight-model-for-agentic-coding-on-aws/>)

Author: Clement Perrot

Published: 2026-10-16T15:23:10Z

Content type: tutorial

Language: en

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

Topics: [Amazon Web Services](<https://devfeed.tech/topics/aws.md>), [lunar foundation model](<https://devfeed.tech/topics/lunar-foundation-model.md>), [Amazon SageMaker](<https://devfeed.tech/topics/amazon-sagemaker.md>), [Amazon SageMaker HyperPod](<https://devfeed.tech/topics/amazon-sagemaker-hyperpod.md>), [Amazon Elastic Kubernetes Service](<https://devfeed.tech/topics/amazon-elastic-kubernetes-service.md>), [flux](<https://devfeed.tech/topics/flux.md>), [vllm](<https://devfeed.tech/topics/vllm.md>), [AWS Trainium](<https://devfeed.tech/topics/aws-trainium.md>), [Apache Cassandra](<https://devfeed.tech/topics/cassandra.md>)

Tags: [advanced-300](<https://devfeed.tech/tags/advanced-300.md>), [agentic-coding](<https://devfeed.tech/tags/agentic-coding.md>), [ai](<https://devfeed.tech/tags/ai.md>), [amazon-sagemaker-ai](<https://devfeed.tech/tags/amazon-sagemaker-ai.md>), [amazon-sagemaker-hyperpod](<https://devfeed.tech/tags/amazon-sagemaker-hyperpod.md>), [amazon-sagemaker-jumpstart](<https://devfeed.tech/tags/amazon-sagemaker-jumpstart.md>), [api](<https://devfeed.tech/tags/api.md>), [authentication](<https://devfeed.tech/tags/authentication.md>), [autoscaling](<https://devfeed.tech/tags/autoscaling.md>), [aws](<https://devfeed.tech/tags/aws.md>), [aws-cli](<https://devfeed.tech/tags/aws-cli.md>), [aws-command-line-interface-aws-cli](<https://devfeed.tech/tags/aws-command-line-interface-aws-cli.md>), [aws-identity-and-access-management-iam](<https://devfeed.tech/tags/aws-identity-and-access-management-iam.md>), [batch](<https://devfeed.tech/tags/batch.md>), [batching](<https://devfeed.tech/tags/batching.md>), [distributed](<https://devfeed.tech/tags/distributed.md>), [gpu](<https://devfeed.tech/tags/gpu.md>), [gpu-infrastructure](<https://devfeed.tech/tags/gpu-infrastructure.md>), [inference](<https://devfeed.tech/tags/inference.md>), [infrastructure](<https://devfeed.tech/tags/infrastructure.md>), [kubernetes](<https://devfeed.tech/tags/kubernetes.md>), [over](<https://devfeed.tech/tags/over.md>), [sglang](<https://devfeed.tech/tags/sglang.md>), [technical-how-to](<https://devfeed.tech/tags/technical-how-to.md>), [vllm](<https://devfeed.tech/tags/vllm.md>)

### AI overview

Reflection AI's Beam is an open-weight model for agentic coding and long-horizon software tasks. The tutorial explains deployment options on AWS, from a managed SageMaker JumpStart endpoint to Kubernetes-based SageMaker HyperPod Inference using JumpStart, SGLang, or vLLM. It covers GPU capacity planning, deployment setup, performance measurement, tuning, and cleanup.

### Source excerpt

Reflection AI's Beam is an open-weight model for agentic coding and long-horizon tasks. This post shows how to deploy Beam on AWS: start with an Amazon SageMaker JumpStart real-time endpoint, or use Amazon SageMaker HyperPod Inference with JumpStart, SGLang, or vLLM for Kubernetes-native control over distributed GPU infrastructure.

## Meta launches an open-weight AI model that runs on Macs

DevFeed: [Meta launches an open-weight AI model that runs on Macs](<https://devfeed.tech/articles/meta-launches-an-open-weight-ai-model-that-runs-on-macs-88311.md>)

Original publisher: [Read original article](<https://techcrunch.com/2026/10/15/meta-launches-an-open-weight-model-that-runs-on-macs/>)

Author: Lucas Ropek

Published: 2026-10-15T20:04:53Z

Content type: news

Language: en

Sources: [TechCrunch | AI News & Artificial Intelligence](<https://devfeed.tech/sources/techcrunch-ai-news-artificial-intelligence.md>)

Topics: [gpt-oss](<https://devfeed.tech/topics/gpt-oss.md>), [Local AI](<https://devfeed.tech/topics/local-ai.md>), [lunar foundation model](<https://devfeed.tech/topics/lunar-foundation-model.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [ai-model](<https://devfeed.tech/tags/ai-model.md>), [apple](<https://devfeed.tech/tags/apple.md>), [cost](<https://devfeed.tech/tags/cost.md>), [evaluation](<https://devfeed.tech/tags/evaluation.md>), [m5-ultra](<https://devfeed.tech/tags/m5-ultra.md>), [mac](<https://devfeed.tech/tags/mac.md>), [mac-studio](<https://devfeed.tech/tags/mac-studio.md>), [memory](<https://devfeed.tech/tags/memory.md>), [meta](<https://devfeed.tech/tags/meta.md>), [multimodal](<https://devfeed.tech/tags/multimodal.md>), [muse](<https://devfeed.tech/tags/muse.md>), [muse-code](<https://devfeed.tech/tags/muse-code.md>), [open-weight-ai](<https://devfeed.tech/tags/open-weight-ai.md>), [performance](<https://devfeed.tech/tags/performance.md>), [ram](<https://devfeed.tech/tags/ram.md>)

### AI overview

Meta launched Muse Spark Open, an open-weight multimodal model designed to run locally on Macs. It has 816 billion parameters and a one-million-token context window, and Meta says it is built for complex coding tasks and agentic workflows. Running it locally requires at least 1 terabyte of RAM; Meta also says it is available through several API platforms.

### Source excerpt

Meta and Apple have teamed up for the launch of the social media giant's newest model, Muse Spark Open, which will run locally on Apple silicon.

## How Molmo 2's open release helped an MIT researcher rethink fish tracking

DevFeed: [How Molmo 2's open release helped an MIT researcher rethink fish tracking](<https://devfeed.tech/articles/how-molmo-2-s-open-release-helped-an-mit-researcher-rethink-fish-tracking-86240.md>)

Original publisher: [Read original article](<https://allenai.org/blog/molmo2fish>)

Published: 2026-10-13T08:00:00Z

Content type: news

Language: en

Sources: [Ai2 Blog](<https://devfeed.tech/sources/ai2-blog.md>)

Topics: [lunar foundation model](<https://devfeed.tech/topics/lunar-foundation-model.md>), [Open Source](<https://devfeed.tech/topics/open-source.md>), [canary release](<https://devfeed.tech/topics/canary-release.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [computer-vision](<https://devfeed.tech/tags/computer-vision.md>), [model](<https://devfeed.tech/tags/model.md>)

### AI overview

Kai Van Brunt adapted the open Molmo 2 vision-language model into Molmo2Fish, which tracks salmon in sonar video and can correct some errors when given clear language instructions. It performed roughly as well as a specialized fish-tracking system before corrections, with results varying across rivers. The project remains research and has not been deployed.

### Source excerpt

Molmo 2's open release helped MIT researcher Kai Van Brunt develop Molmo2Fish, an experimental model that tracks salmon in sonar footage and corrects some tracking errors using everyday language.

## Open-Source Voice AI runs entirely on ESP32-S3

DevFeed: [Open-Source Voice AI runs entirely on ESP32-S3](<https://devfeed.tech/articles/open-source-voice-ai-runs-entirely-on-esp32-s3-85404.md>)

Original publisher: [Read original article](<https://blog.adafruit.com/2026/10/12/open-source-voice-ai-runs-entirely-on-esp32-s3/>)

Author: Anne Barela

Published: 2026-10-12T18:44:04Z

Content type: news

Language: en

Sources: [Adafruit Industries](<https://devfeed.tech/sources/adafruit-industries-makers-hackers-artists-designers-and-engineers.md>)

Topics: [Toit](<https://devfeed.tech/topics/toit.md>), [speech-to-speech](<https://devfeed.tech/topics/speech-to-speech.md>), [lunar foundation model](<https://devfeed.tech/topics/lunar-foundation-model.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [dataset](<https://devfeed.tech/tags/dataset.md>), [esp32-s3](<https://devfeed.tech/tags/esp32-s3.md>), [espressif](<https://devfeed.tech/tags/espressif.md>), [firmware](<https://devfeed.tech/tags/firmware.md>), [gguf](<https://devfeed.tech/tags/gguf.md>), [inference](<https://devfeed.tech/tags/inference.md>), [model-inference](<https://devfeed.tech/tags/model-inference.md>), [speech](<https://devfeed.tech/tags/speech.md>), [speech-recognition](<https://devfeed.tech/tags/speech-recognition.md>), [speech-synthesis](<https://devfeed.tech/tags/speech-synthesis.md>)

### AI overview

Ivy AI is an open-source voice assistant that runs speech recognition, language model inference and speech synthesis locally on an ESP32-S3, using Wi-Fi only for time synchronization. The article describes its hardware, four-bit model quantization, performance, memory constraints and licensing considerations.

### Source excerpt

Ananthu Ashok, writing for Open Source For You, covers Ivy AI, a voice assistant from Anankush Pandit that runs speech recognition, language model inference and speech synthesis on an ESP32-S3. Firmware, model conversion tools, host-side tests and documentation are published under GPL-3.0-or-later. WiFi is used only for time sync, so the voice pipeline works without [...]

## Google Earth AI's Population Dynamics Foundation Model supports public health research

DevFeed: [Google Earth AI's Population Dynamics Foundation Model supports public health research](<https://devfeed.tech/articles/unlocking-earth-ai-s-planetary-geospatial-foundation-models-for-global-public-health-66369.md>)

Original publisher: [Read original article](<https://research.google/blog/earth-ais-planetary-geospatial-foundation-models-for-global-public-health/>)

Published: 2026-10-06T15:05:11Z

Content type: article

Language: en

Sources: [The latest research from Google](<https://devfeed.tech/sources/the-latest-research-from-google.md>)

Topics: [AI Foundation Models](<https://devfeed.tech/topics/ai-foundation-models.md>), [geospatial](<https://devfeed.tech/topics/geospatial.md>), [Earth AI](<https://devfeed.tech/topics/earth-ai.md>), [lunar foundation model](<https://devfeed.tech/topics/lunar-foundation-model.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [earth](<https://devfeed.tech/tags/earth.md>), [earth-ai](<https://devfeed.tech/tags/earth-ai.md>), [foundation-models](<https://devfeed.tech/tags/foundation-models.md>), [geospatial](<https://devfeed.tech/tags/geospatial.md>), [global](<https://devfeed.tech/tags/global.md>), [health](<https://devfeed.tech/tags/health.md>), [health-bioscience](<https://devfeed.tech/tags/health-bioscience.md>), [public-health](<https://devfeed.tech/tags/public-health.md>)

### AI overview

Google Research presents five partner-led case studies evaluating its Population Dynamics Foundation Model (PDFM), which turns privacy-preserving population and environmental signals into location embeddings for epidemiological workflows. Across studies involving measles vaccination, cardiovascular disease, dengue, postpartum depression and cholera, the embeddings supplemented existing data and models, with reported benefits varying by task and forecast horizon. The article also notes limitations including static snapshots and ongoing work on dynamic embeddings and geographic transfer.

### Source excerpt

Earth AI

## How a PyTorch World Model Reduces Data Sent Between a Drone and the Cloud

DevFeed: [How a PyTorch World Model Reduces Data Sent Between a Drone and the Cloud](<https://devfeed.tech/articles/how-to-make-a-cloud-read-a-drone-s-mind-and-cut-data-usage-by-94-65601.md>)

Original publisher: [Read original article](<https://towardsdatascience.com/how-to-make-a-cloud-read-a-drones-mind-and-cut-data-usage-by-94/>)

Author: Anubhab Banerjee

Published: 2026-10-06T12:30:00Z

Content type: tutorial

Language: en

Sources: [Towards Data Science](<https://devfeed.tech/sources/towards-data-science.md>)

Topics: [Machine learning](<https://devfeed.tech/topics/machine-learning.md>), [lunar foundation model](<https://devfeed.tech/topics/lunar-foundation-model.md>), [quantization](<https://devfeed.tech/topics/quantization.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [artificial-intelligence](<https://devfeed.tech/tags/artificial-intelligence.md>), [drone](<https://devfeed.tech/tags/drone.md>), [editor-s-picks](<https://devfeed.tech/tags/editor-s-picks.md>), [how-to](<https://devfeed.tech/tags/how-to.md>), [machine-learning](<https://devfeed.tech/tags/machine-learning.md>), [physical-ai](<https://devfeed.tech/tags/physical-ai.md>), [pytorch](<https://devfeed.tech/tags/pytorch.md>), [pytorch-tutorial](<https://devfeed.tech/tags/pytorch-tutorial.md>), [world-model](<https://devfeed.tech/tags/world-model.md>), [world-models](<https://devfeed.tech/tags/world-models.md>)

### AI overview

The tutorial describes a simulated approach to reducing communication between a remote machine and the cloud. Matching world-model copies on both sides predict the machine's state, while the remote side sends corrections when their estimates diverge beyond a threshold. In CartPole simulations, the method used 87% to 94.5% fewer bits than streaming the full state and 26.5% to 69% fewer than the stronger simple baseline. The author notes limits including perfect network conditions, identical arithmetic on both copies, and the use of a simulator rather than a real drone.

### Source excerpt

Two copies of one small AI model keep a remote machine in sync with the cloud, with no constant streaming. A beginner-friendly world model tutorial in PyTorch. The post How to Make a Cloud Read a Drone's Mind (and Cut Data Usage by 94%) appeared first on Towards Data Science.

## MIT Transit Lab to develop an AI platform for public transit agencies

DevFeed: [MIT Transit Lab to develop an AI platform for public transit agencies](<https://devfeed.tech/articles/mit-transit-lab-to-develop-an-ai-platform-for-public-transit-agencies-62785.md>)

Original publisher: [Read original article](<https://news.mit.edu/2026/mit-transit-lab-to-develop-ai-platform-public-transit-agencies-0930>)

Author: Denise Brehm | Department of Urban Studies and Planning

Published: 2026-09-30T15:15:00Z

Content type: news

Language: en

Sources: [MIT AI News](<https://devfeed.tech/sources/mit-ai-news.md>)

Topics: [Digital Public Good](<https://devfeed.tech/topics/digital-public-goods.md>), [NAT and SNAT](<https://devfeed.tech/topics/nat-and-snat.md>), [lunar foundation model](<https://devfeed.tech/topics/lunar-foundation-model.md>)

Tags: [academic](<https://devfeed.tech/tags/academic.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-platform](<https://devfeed.tech/tags/ai-platform.md>), [artificial-intelligence](<https://devfeed.tech/tags/artificial-intelligence.md>), [awad-abdelhalim](<https://devfeed.tech/tags/awad-abdelhalim.md>), [cities](<https://devfeed.tech/tags/cities.md>), [communications](<https://devfeed.tech/tags/communications.md>), [develop](<https://devfeed.tech/tags/develop.md>), [funding](<https://devfeed.tech/tags/funding.md>), [go](<https://devfeed.tech/tags/go.md>), [google-org](<https://devfeed.tech/tags/google-org.md>), [google-org-impact-challenge](<https://devfeed.tech/tags/google-org-impact-challenge.md>), [jinhua-zhao](<https://devfeed.tech/tags/jinhua-zhao.md>), [lab](<https://devfeed.tech/tags/lab.md>), [manager](<https://devfeed.tech/tags/manager.md>), [mit](<https://devfeed.tech/tags/mit.md>), [mit-transit-lab](<https://devfeed.tech/tags/mit-transit-lab.md>), [mobility](<https://devfeed.tech/tags/mobility.md>), [nasa](<https://devfeed.tech/tags/nasa.md>), [nasa-mission-control](<https://devfeed.tech/tags/nasa-mission-control.md>), [network](<https://devfeed.tech/tags/network.md>), [open-source](<https://devfeed.tech/tags/open-source.md>), [ptiq](<https://devfeed.tech/tags/ptiq.md>), [public](<https://devfeed.tech/tags/public.md>), [public-transit-intelligence-hub](<https://devfeed.tech/tags/public-transit-intelligence-hub.md>), [research](<https://devfeed.tech/tags/research.md>), [school-of-architecture-and-planning](<https://devfeed.tech/tags/school-of-architecture-and-planning.md>), [transportation](<https://devfeed.tech/tags/transportation.md>), [urban-studies-and-planning](<https://devfeed.tech/tags/urban-studies-and-planning.md>)

### AI overview

MIT Transit Lab received $2.1 million from Google.org to develop the open-source Public Transit Intelligence Hub. The AI-orchestrated platform is intended to combine transit agencies' monitoring, operations control, and passenger communication systems, helping staff make informed real-time decisions and provide riders with timely, accurate information.

### Source excerpt

With $2.1 million funding from Google.org, the open-source Public Transit Intelligence Hub will unify public transit monitoring, operations, and passenger communication.

## From Caliptra Foundation To Full Production Deployment

DevFeed: [From Caliptra Foundation To Full Production Deployment](<https://devfeed.tech/articles/from-caliptra-foundation-to-full-production-deployment-62559.md>)

Original publisher: [Read original article](<https://semiengineering.com/from-caliptra-foundation-to-full-production-deployment/>)

Author: Rambus

Published: 2026-09-30T07:04:24Z

Content type: article

Language: en

Sources: [Semiconductor Engineering](<https://devfeed.tech/sources/semiconductor-engineering.md>)

Topics: [Security](<https://devfeed.tech/topics/security.md>), [lunar foundation model](<https://devfeed.tech/topics/lunar-foundation-model.md>), [Deployment](<https://devfeed.tech/topics/deployment.md>)

Tags: [ai-infrastructure-security](<https://devfeed.tech/tags/ai-infrastructure-security.md>), [attestation](<https://devfeed.tech/tags/attestation.md>), [caliptra](<https://devfeed.tech/tags/caliptra.md>), [cryptomanager-root-of-trust](<https://devfeed.tech/tags/cryptomanager-root-of-trust.md>), [data-center-security](<https://devfeed.tech/tags/data-center-security.md>), [device-identity](<https://devfeed.tech/tags/device-identity.md>), [infrastructure](<https://devfeed.tech/tags/infrastructure.md>), [iot-and-security](<https://devfeed.tech/tags/iot-and-security.md>), [measured-boot](<https://devfeed.tech/tags/measured-boot.md>), [rambus](<https://devfeed.tech/tags/rambus.md>), [root-of-trust](<https://devfeed.tech/tags/root-of-trust.md>), [security](<https://devfeed.tech/tags/security.md>), [whitepapers](<https://devfeed.tech/tags/whitepapers.md>)

### AI overview

This white paper describes how the open-source Caliptra Root of Trust framework supports device identity, measured boot, and attestation across data center class systems. It discusses challenges in turning the open standard into a production deployment for data center and AI infrastructure.

### Source excerpt

Bridging the gap between open-source Root of Trust foundations and enterprise-grade security deployments. The post From Caliptra Foundation To Full Production Deployment appeared first on Semiconductor Engineering.

## NVIDIA Kumo Tabular Sets a New Accuracy-Efficiency Frontier for Tabular Prediction

DevFeed: [NVIDIA Kumo Tabular Sets a New Accuracy-Efficiency Frontier for Tabular Prediction](<https://devfeed.tech/articles/nvidia-kumo-tabular-sets-a-new-accuracy-efficiency-frontier-for-tabular-prediction-61938.md>)

Original publisher: [Read original article](<https://huggingface.co/blog/nvidia/kumo-tabular>)

Author: Jingang Qu; Valter Hudovernik; Martin Jurkovic; Cedric Lorenz; Akihiro Nitta; Dmitry Gordeev; Federico Lopez; Ramona Bendias; Gilberto Titericz Jr; Aleksandar S Sokolovski; Isabel Hulseman; Jure Lesko

Published: 2026-09-29T15:30:38Z

Content type: release

Language: en

Sources: [Hugging Face](<https://devfeed.tech/sources/hugging-face-blog.md>)

Topics: [Machine learning](<https://devfeed.tech/topics/machine-learning.md>), [Structured-data](<https://devfeed.tech/topics/structured-data.md>), [lunar foundation model](<https://devfeed.tech/topics/lunar-foundation-model.md>), [generalization in machine learning](<https://devfeed.tech/topics/generalization-in-machine-learning.md>)

Tags: [classification](<https://devfeed.tech/tags/classification.md>), [data](<https://devfeed.tech/tags/data.md>), [model](<https://devfeed.tech/tags/model.md>), [nvidia](<https://devfeed.tech/tags/nvidia.md>), [regression](<https://devfeed.tech/tags/regression.md>), [structured](<https://devfeed.tech/tags/structured.md>)

### AI overview

NVIDIA Kumo Tabular is an open foundation model for tabular classification and regression. It predicts labels for new rows from labeled table data in a single forward pass, without task-specific training, tuning, or feature engineering. The article describes its Transformer architecture and reports top rankings on four benchmarks.

### Source excerpt

NVIDIA Kumo Tabular, part of the NVIDIA Kumo Structured model collection, is an open foundation model for tabular data now available on Hugging Face. Given a table of labeled rows, it predicts the labels of new rows in a single forward pass, with no training, no tuning, and no feature engineering, for both classification and regression.

## This Week in Open Source for September 24, 2026

DevFeed: [This Week in Open Source for September 24, 2026](<https://devfeed.tech/articles/this-week-in-open-source-for-september-24-2026-59639.md>)

Original publisher: [Read original article](<http://opensource.googleblog.com/2026/09/this-week-in-open-source-for-september.html>)

Author: Google Open Source (noreply@blogger.com)

Published: 2026-09-24T18:30:00Z

Content type: article

Language: en

Sources: [Google Open Source Blog](<https://devfeed.tech/sources/google-open-source-blog.md>)

Topics: [Open Source](<https://devfeed.tech/topics/open-source.md>), [lunar foundation model](<https://devfeed.tech/topics/lunar-foundation-model.md>), [A2A protocol](<https://devfeed.tech/topics/a2a-protocol.md>), [Model Context Protocol](<https://devfeed.tech/topics/model-context-protocol.md>), [openssf](<https://devfeed.tech/topics/openssf.md>), [Digital Public Good](<https://devfeed.tech/topics/digital-public-goods.md>)

Tags: [2](<https://devfeed.tech/tags/2.md>), [2026](<https://devfeed.tech/tags/2026.md>), [a2a](<https://devfeed.tech/tags/a2a.md>), [a2a-protocol](<https://devfeed.tech/tags/a2a-protocol.md>), [adapting](<https://devfeed.tech/tags/adapting.md>), [agent](<https://devfeed.tech/tags/agent.md>), [agent2agent](<https://devfeed.tech/tags/agent2agent.md>), [agentic](<https://devfeed.tech/tags/agentic.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-engineering](<https://devfeed.tech/tags/ai-engineering.md>), [ai-security](<https://devfeed.tech/tags/ai-security.md>), [all](<https://devfeed.tech/tags/all.md>), [anniversary](<https://devfeed.tech/tags/anniversary.md>), [apache](<https://devfeed.tech/tags/apache.md>), [apache-software-foundation](<https://devfeed.tech/tags/apache-software-foundation.md>), [events](<https://devfeed.tech/tags/events.md>), [governance](<https://devfeed.tech/tags/governance.md>), [news](<https://devfeed.tech/tags/news.md>), [open](<https://devfeed.tech/tags/open.md>), [open-source](<https://devfeed.tech/tags/open-source.md>), [source](<https://devfeed.tech/tags/source.md>), [sustainability](<https://devfeed.tech/tags/sustainability.md>), [this](<https://devfeed.tech/tags/this.md>), [this-week-in-open-source](<https://devfeed.tech/tags/this-week-in-open-source.md>), [twios](<https://devfeed.tech/tags/twios.md>)

### AI overview

Open source's economic value is substantial, but sustaining its maintainers and governance calls for practical funding and evidence of benefits. The excerpt highlights a proposal for commercial package registries and mirror vendors to pay automatic royalties down dependency trees, and an LF Energy report finding 2-5x greater net value for regulated grid operators under an auditable benefit-cost framework. It also argues that examining autonomous AI security failures can inform stronger supply-chain defenses. In open science, IBM and NASA released a Lunar Foundation Model alongside a harmonized, machine-learning-ready lunar dataset combining more than 30 instrument layers. The newsletter also lists October and November open source events. These points reflect the supplied excerpt; it does not provide the full linked articles or reports.

### Source excerpt

by Daryl Ducharme, Open Source Programs Office This Week in Open Source for September 24, 2026 A look around the world of open source Open source underpins an $8.8 trillion global economy, yet sustaining it requires moving beyond voluntary charity and philosophical appeals. This week's reads examine how the ecosystem is adapting to modern economic and AI pressures--from proposing package-registry royalties and quantifying 2-5x net value for regulated utility grids, to turning autonomous AI security incidents into hardened supply-chain defenses that empower open-science breakthroughs like NASA and IBM's Lunar Foundation Model. Upcoming Events 🗓 October 2026 MCP Dev Summit Toronto (October 5-6, 2026) -- Toronto, Ontario, Canada. Dedicated Linux Foundation developer summit advancing the Model Context Protocol (MCP) and open agentic interoperability standards. Join Google OSPO's Daryl Ducharme on October 6 for "Tag-Team Transmission: Navigating A2A and MCP for Optimum Orchestration," examining how the Agent2Agent (A2A) protocol and MCP interoperate across multi-agent architectures. Open Source Summit Europe (October 7-9, 2026) -- Prague, Czechia. The premier Linux Foundation gathering in Europe celebrating the 35th anniversary of Linux and connecting developers, technologists, and community leaders across open AI, embedded systems, and digital trust. Community Over Code (October 11-14, 2026) -- Glasgow, Scotland. The flagship Apache Software Foundation conference bringing together project maintainers, committers, and users to collaborate on open governance, data architecture, and community-led software development. All Things Open 2026 (October 19-20, 2026) -- Raleigh, North Carolina, USA. One of the largest community-focused open source conferences on the U.S. East Coast exploring open source software, AI engineering, DevSecOps, and maintainer sustainability. GitHub Universe 2026 (October 28-29, 2026) -- San Francisco, California, USA & Virtual. Annual global developer gath

## NASA-IBM Lunar Foundation Model Goes Open Source With a 2M-Tile Dataset and 22% Lower Ice-Mapping Error

DevFeed: [NASA-IBM Lunar Foundation Model Goes Open Source With a 2M-Tile Dataset and 22% Lower Ice-Mapping Error](<https://devfeed.tech/articles/nasa-ibm-lunar-foundation-model-goes-open-source-with-a-2m-tile-dataset-and-22-lower-ice-mapping-error-17437.md>)

Original publisher: [Read original article](<https://www.storagereview.com/news/nasa-ibm-lunar-foundation-model-goes-open-source-with-a-2m-tile-dataset-and-22-lower-ice-mapping-error>)

Author: Harold Fritts

Published: 2026-09-14T16:43:16Z

Content type: news

Language: en

Sources: [StorageReview.com](<https://devfeed.tech/sources/storagereview-com.md>)

Topics: [lunar foundation model](<https://devfeed.tech/topics/lunar-foundation-model.md>), [AI Foundation Models](<https://devfeed.tech/topics/ai-foundation-models.md>), [ibm](<https://devfeed.tech/topics/ibm.md>), [Open Source](<https://devfeed.tech/topics/open-source.md>), [hugging face](<https://devfeed.tech/topics/hugging-face.md>), [dataset](<https://devfeed.tech/topics/dataset.md>), [multimodal-ai](<https://devfeed.tech/topics/multimodal-ai.md>), [Benchmark](<https://devfeed.tech/topics/benchmark.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [benchmark](<https://devfeed.tech/tags/benchmark.md>), [data](<https://devfeed.tech/tags/data.md>), [enterprise](<https://devfeed.tech/tags/enterprise.md>), [fine-tuning](<https://devfeed.tech/tags/fine-tuning.md>), [foundation-models](<https://devfeed.tech/tags/foundation-models.md>), [hugging-face](<https://devfeed.tech/tags/hugging-face.md>), [ibm](<https://devfeed.tech/tags/ibm.md>), [lunar-foundation-model](<https://devfeed.tech/tags/lunar-foundation-model.md>), [machine-learning](<https://devfeed.tech/tags/machine-learning.md>), [multimodal](<https://devfeed.tech/tags/multimodal.md>), [nasa](<https://devfeed.tech/tags/nasa.md>), [open-source](<https://devfeed.tech/tags/open-source.md>), [space](<https://devfeed.tech/tags/space.md>)

### AI overview

IBM and NASA have released the NASA-IBM Lunar Foundation Model as open source on Hugging Face, along with its weights, technical report, and training dataset. Built on TerraMind, the model uses multimodal lunar observations for tasks including ice-deposit mapping, volcanic-feature detection, and crater detection. Reported benchmarks show up to 22% lower ice-mapping error than SwinV2-B, while the accompanying dataset contains roughly 2 million image tiles from nine instruments across four lunar missions.

### Source excerpt

IBM and NASA have released the NASA-IBM Lunar Foundation Model as open source, one of the first publicly available foundation models built for scientific study of the Moon. The weights, a technical report, and the machine-learning-ready dataset it was trained on are up on Hugging Face under the Prithvi family, which already covers Earth observation, The post NASA-IBM Lunar Foundation Model Goes Open Source With a 2M-Tile Dataset and 22% Lower Ice-Mapping Error appeared first on StorageReview.com.

## Introducing IBM and NASA's new foundation model for the Moon

DevFeed: [Introducing IBM and NASA's new foundation model for the Moon](<https://devfeed.tech/articles/introducing-ibm-and-nasa-s-new-foundation-model-for-the-moon-17342.md>)

Original publisher: [Read original article](<https://research.ibm.com/blog/nasa-ibm-lunar-foundation-model>)

Author: Kim Martineau

Published: 2026-09-10T12:30:00Z

Content type: article

Language: en

Sources: [IBM Research](<https://devfeed.tech/sources/ibm-research.md>)

Topics: [lunar foundation model](<https://devfeed.tech/topics/lunar-foundation-model.md>), [ibm](<https://devfeed.tech/topics/ibm.md>), [AI Foundation Models](<https://devfeed.tech/topics/ai-foundation-models.md>), [data](<https://devfeed.tech/topics/data.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [AI Architecture](<https://devfeed.tech/topics/ai-architecture.md>)

Tags: [accelerated-discovery](<https://devfeed.tech/tags/accelerated-discovery.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-architecture](<https://devfeed.tech/tags/ai-architecture.md>), [ai-models](<https://devfeed.tech/tags/ai-models.md>), [algorithms](<https://devfeed.tech/tags/algorithms.md>), [ibm](<https://devfeed.tech/tags/ibm.md>), [lunar-foundation-model](<https://devfeed.tech/tags/lunar-foundation-model.md>), [mapping](<https://devfeed.tech/tags/mapping.md>), [model](<https://devfeed.tech/tags/model.md>), [nasa](<https://devfeed.tech/tags/nasa.md>), [release](<https://devfeed.tech/tags/release.md>), [science](<https://devfeed.tech/tags/science.md>), [space](<https://devfeed.tech/tags/space.md>), [us](<https://devfeed.tech/tags/us.md>)

### AI overview

IBM and NASA are open-sourcing the NASA-IBM Lunar Foundation Model, a multimodal AI model that integrates lunar observations from US and Japanese missions across viewing angles, spatial scales, and measurement types. The model is intended to support lunar mapping, volcanic-history research, and searches for polar ice.

### Source excerpt

The multi-modal model could help astronauts navigate craters, investigate ancient lava, and search for ice, as the US plans for a long-term lunar presence.

## Jina embeddings v3 now available on Gemini Enterprise Agent Platform Model Garden

DevFeed: [Jina embeddings v3 now available on Gemini Enterprise Agent Platform Model Garden](<https://devfeed.tech/articles/jina-embeddings-v3-now-available-on-gemini-enterprise-agent-platform-model-garden-78852.md>)

Original publisher: [Read original article](<https://www.elastic.co/search-labs/blog/jina-embeddings-v3-gemini-enterprise-model-garden>)

Author: Sa Zhang

Published: 2026-04-22T00:00:00Z

Content type: news

Language: en

Sources: [Elasticsearch Labs](<https://devfeed.tech/sources/elasticsearch-labs.md>)

Topics: [Embeddings](<https://devfeed.tech/topics/embeddings.md>), [Amazon SageMaker](<https://devfeed.tech/topics/amazon-sagemaker.md>), [GPU](<https://devfeed.tech/topics/gpu.md>), [lunar foundation model](<https://devfeed.tech/topics/lunar-foundation-model.md>), [quantization](<https://devfeed.tech/topics/quantization.md>)

Tags: [2026](<https://devfeed.tech/tags/2026.md>), [ai](<https://devfeed.tech/tags/ai.md>), [api](<https://devfeed.tech/tags/api.md>), [bigquery](<https://devfeed.tech/tags/bigquery.md>), [cloud-storage](<https://devfeed.tech/tags/cloud-storage.md>), [clustering](<https://devfeed.tech/tags/clustering.md>), [cost](<https://devfeed.tech/tags/cost.md>), [deployment](<https://devfeed.tech/tags/deployment.md>), [developers](<https://devfeed.tech/tags/developers.md>), [embeddings](<https://devfeed.tech/tags/embeddings.md>), [gpu](<https://devfeed.tech/tags/gpu.md>), [jina-ai](<https://devfeed.tech/tags/jina-ai.md>), [vpc](<https://devfeed.tech/tags/vpc.md>)

### AI overview

Jina embeddings v3 is now available for self-deployment through Gemini Enterprise Agent Platform Model Garden. The model runs on GPU instances in a customer's Google Cloud project and VPC, avoiding external API calls and per-token pricing. The article describes its use for search and retrieval, deployment requirements, and reported model capabilities.

### Source excerpt

Jina search foundation model, jina-embeddings-v3, is now self-deployable on Gemini Enterprise Agent Platform Model Garden, with more to follow. Run jina-embeddings-v3 on a single L4 GPU inside your own VPC.

## Stability AI and Arm Collaborate to Release Stable Audio Open Small, Enabling Real-World Deployment for On-Device Audio Generation

DevFeed: [Stability AI and Arm Collaborate to Release Stable Audio Open Small, Enabling Real-World Deployment for On-Device Audio Generation](<https://devfeed.tech/articles/stability-ai-and-arm-collaborate-to-release-stable-audio-open-small-enabling-real-world-deployment-for-on-device-audio-generation-82867.md>)

Original publisher: [Read original article](<https://stability.ai/news-updates/stability-ai-and-arm-release-stable-audio-open-small-enabling-real-world-deployment-for-on-device-audio-control>)

Author: Guest User

Published: 2025-05-14T14:58:02Z

Content type: release

Language: en

Sources: [News & Updates - Stability AI](<https://devfeed.tech/sources/news-updates-stability-ai.md>)

Topics: [lunar foundation model](<https://devfeed.tech/topics/lunar-foundation-model.md>), [Arm](<https://devfeed.tech/topics/arm.md>), [Cosmos](<https://devfeed.tech/topics/cosmos.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [arm](<https://devfeed.tech/tags/arm.md>), [audio](<https://devfeed.tech/tags/audio.md>), [free](<https://devfeed.tech/tags/free.md>), [hardware](<https://devfeed.tech/tags/hardware.md>), [inference](<https://devfeed.tech/tags/inference.md>), [on-device](<https://devfeed.tech/tags/on-device.md>), [open](<https://devfeed.tech/tags/open.md>)

### AI overview

Stability AI and Arm released Stable Audio Open Small, a 341-million-parameter text-to-audio model optimized to run on Arm CPUs. The release says it can generate up to 11 seconds of audio on a smartphone in under eight seconds, and provides model weights, code, and a deployment learning path.

### Source excerpt

We're open-sourcing Stable Audio Open Small in partnership with Arm, whose technology powers 99% of smartphones globally. Building on the industry-leading text-to-audio model Stable Audio Open, the new compact variant is smaller and faster, while preserving output quality and prompt adherence.