# vlm

A vision-language model that processes image and text inputs to generate text outputs.

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

## Building Pinterest's VLM Serving Stack on NVIDIA Dynamo

DevFeed: [Building Pinterest's VLM Serving Stack on NVIDIA Dynamo](<https://devfeed.tech/articles/building-pinterest-s-vlm-serving-stack-on-nvidia-dynamo-1229.md>)

Original publisher: [Read original article](<https://medium.com/pinterest-engineering/building-pinterests-vlm-serving-stack-on-nvidia-dynamo-0dce6e93d0f3?source=rss----4c5a5f6279b6---4>)

Author: Pinterest Engineering

Published: 2026-09-10T23:08:16Z

Content type: article

Language: en

Sources: [Pinterest Engineering Blog - Medium](<https://devfeed.tech/sources/pinterest-engineering-blog-medium.md>)

Topics: [vlm](<https://devfeed.tech/topics/vlm.md>), [Inference](<https://devfeed.tech/topics/inference.md>), [model-deployment](<https://devfeed.tech/topics/model-deployment.md>), [Orchestration](<https://devfeed.tech/topics/orchestration.md>), [Latency](<https://devfeed.tech/topics/latency.md>), [Caching](<https://devfeed.tech/topics/caching.md>), [Open Source Models & Datasets](<https://devfeed.tech/topics/open-source-models-datasets.md>)

Tags: [blackwell](<https://devfeed.tech/tags/blackwell.md>), [cache](<https://devfeed.tech/tags/cache.md>), [dynamo](<https://devfeed.tech/tags/dynamo.md>), [embeddings](<https://devfeed.tech/tags/embeddings.md>), [engineering](<https://devfeed.tech/tags/engineering.md>), [inference](<https://devfeed.tech/tags/inference.md>), [latency](<https://devfeed.tech/tags/latency.md>), [llm](<https://devfeed.tech/tags/llm.md>), [multimodal](<https://devfeed.tech/tags/multimodal.md>), [multimodal-ai](<https://devfeed.tech/tags/multimodal-ai.md>), [nvidia](<https://devfeed.tech/tags/nvidia.md>), [nvidia-blackwell](<https://devfeed.tech/tags/nvidia-blackwell.md>), [open-source](<https://devfeed.tech/tags/open-source.md>), [orchestration](<https://devfeed.tech/tags/orchestration.md>), [performance](<https://devfeed.tech/tags/performance.md>), [pinterest](<https://devfeed.tech/tags/pinterest.md>), [vllm](<https://devfeed.tech/tags/vllm.md>), [vlm](<https://devfeed.tech/tags/vlm.md>), [vlm-serving](<https://devfeed.tech/tags/vlm-serving.md>)

### AI overview

Pinterest describes its VLM serving stack built on NVIDIA Blackwell GPUs and NVIDIA Dynamo. The stack addresses multimodal inference demands such as image processing, variable prefill costs, KV-cache pressure, routing, and cache offloading.

### Source excerpt

Lei Pan | Senior Software Engineer; Salina Wu | Senior Software Engineer; Cristian Lopez | Software Engineer I; Guangtong Bai | Staff Software Engineer; Soam Acharya | Principal Engineer; Saurabh Vishwas Joshi | Principal Engineer; Chia-Wei Chen | Staff Software Engineer; Ambud Sharma | Principal Engineer Why VLM Serving Matters at Pinterest Pinterest is a visual search and discovery platform, so its AI systems must reason over both language and visual content. Vision-language models (VLMs), which can interpret images, compare visual candidates, and respond naturally to user intent, are becoming the foundation for the next generation of Pinterest experiences: Pinterest Assistant, hybrid search, multimodal reranking, content understanding, signal generation, content safety, and more. This direction also reflects Pinterest's broader strategy to customize open-source models to meet its product & scale needs. Pinterest Assistant is a standout example. This multi-turn conversational experience covers both user language and visual content. Serving it requires low-latency VLM inference over rich multimodal context as well as reworking Qwen3-VL with proprietary multimodal embeddings to cut runtime cost while improving performance. Serving VLMs, however, introduces more challenges compared to text-only LLM workloads. Requests may carry multiple images, require extra vision encoder computation, incur larger and more variable prefill cost, and create higher KV cache pressure. To support this new class of models & product experiences, we built Pinterest's VLM serving stack on top of NVIDIA Blackwell GPUs and NVIDIA Dynamo. Blackwell GPUs incorporate many architectural innovations that are uniquely positioned for today's most demanding AI workloads -- including higher BF16/FP8 compute throughput, increased memory bandwidth, and larger HBM memory capacity -- that enable dramatically higher performance for inference. Dynamo provides a distributed inference orchestration layer that g

## Simplify and support your TorchServe workloads using Ray Serve Deep Learning Containers

DevFeed: [Simplify and support your TorchServe workloads using Ray Serve Deep Learning Containers](<https://devfeed.tech/articles/simplify-and-support-your-torchserve-workloads-using-ray-serve-deep-learning-containers-4741.md>)

Original publisher: [Read original article](<https://aws.amazon.com/blogs/machine-learning/simplify-and-support-your-torchserve-workloads-using-ray-serve-deep-learning-containers/>)

Author: Ananth Raghavendra

Published: 2026-09-09T15:51:29Z

Content type: tutorial

Language: en

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

Topics: [Inference](<https://devfeed.tech/topics/inference.md>), [model-deployment](<https://devfeed.tech/topics/model-deployment.md>), [Amazon Elastic Kubernetes Service](<https://devfeed.tech/topics/amazon-elastic-kubernetes-service.md>), [Containers](<https://devfeed.tech/topics/containers.md>), [vlm](<https://devfeed.tech/topics/vlm.md>), [GPU](<https://devfeed.tech/topics/gpu.md>), [PyTorch](<https://devfeed.tech/topics/pytorch.md>)

Tags: [amazon-eks](<https://devfeed.tech/tags/amazon-eks.md>), [containers](<https://devfeed.tech/tags/containers.md>), [gpu](<https://devfeed.tech/tags/gpu.md>), [inference](<https://devfeed.tech/tags/inference.md>), [intermediate-200](<https://devfeed.tech/tags/intermediate-200.md>), [pytorch](<https://devfeed.tech/tags/pytorch.md>), [technical-how-to](<https://devfeed.tech/tags/technical-how-to.md>), [vulnerabilities](<https://devfeed.tech/tags/vulnerabilities.md>)

### AI overview

The article introduces AWS Ray Serve Deep Learning Containers as a maintained, pre-tested inference option for teams moving from unmaintained TorchServe workloads. It demonstrates deploying a vision-language model on Amazon EKS using a single GPU node.

### Source excerpt

TorchServe is no longer maintained, leaving teams to own the entire GPU inference stack. The AWS Ray Serve Deep Learning Container is a supported, pre-tested container with the framework, GPU drivers, and serving layer already assembled. This post walks through deploying a vision-language model on Amazon EKS using the Ray Serve DLC on a single GPU node.

## NeoMME: an efficient Multimodal-native and Multilingual Encoder

DevFeed: [NeoMME: an efficient Multimodal-native and Multilingual Encoder](<https://devfeed.tech/articles/neomme-an-efficient-multimodal-native-and-multilingual-encoder-7011.md>)

Original publisher: [Read original article](<https://huggingface.co/blog/Hcompany/neomme>)

Author: Tony Wu; Aurélien Lac

Published: 2026-09-03T13:13:48Z

Content type: article

Language: en

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

Topics: [vlm](<https://devfeed.tech/topics/vlm.md>), [Fine-tuning](<https://devfeed.tech/topics/fine-tuning.md>), [Large Language Model](<https://devfeed.tech/topics/llm.md>), [GPU](<https://devfeed.tech/topics/gpu.md>)

Tags: [apache](<https://devfeed.tech/tags/apache.md>), [architecture](<https://devfeed.tech/tags/architecture.md>), [diffusion](<https://devfeed.tech/tags/diffusion.md>), [embeddings](<https://devfeed.tech/tags/embeddings.md>), [fine-tuning](<https://devfeed.tech/tags/fine-tuning.md>), [gpu](<https://devfeed.tech/tags/gpu.md>), [hugging-face](<https://devfeed.tech/tags/hugging-face.md>), [multimodal](<https://devfeed.tech/tags/multimodal.md>), [quantization](<https://devfeed.tech/tags/quantization.md>), [retrieval](<https://devfeed.tech/tags/retrieval.md>), [training](<https://devfeed.tech/tags/training.md>), [transformers](<https://devfeed.tech/tags/transformers.md>), [vector](<https://devfeed.tech/tags/vector.md>), [vision](<https://devfeed.tech/tags/vision.md>), [vlm](<https://devfeed.tech/tags/vlm.md>)

### AI overview

NeoMME is a family of multilingual multimodal encoders trained from scratch with a masked discrete-diffusion objective. It uses one bidirectional Transformer for text tokens and image patches, and is fine-tuned for visual document retrieval with dense and late-interaction embeddings.

### Source excerpt

We introduce NeoMME, a family of 260M and 800M multilingual multimodal encoders. Unlike many generative visual language models, NeoMME does not use a separate pretrained vision tower or a causal language model. A single bidirectional Transformer processes both text tokens and raw image patches, and we train the entire model from scratch with a masked discrete-diffusion objective. We fine-tuned NeoMME for visual document retrieval using ColPali's page-image approach.

## Training Yandex's Alice Omnimodel to Integrate Text and Images

DevFeed: [Training Yandex's Alice Omnimodel to Integrate Text and Images](<https://devfeed.tech/articles/ai-vlm-llm-24891.md>)

Original publisher: [Read original article](<https://habr.com/ru/companies/yandex/articles/1077274/>)

Author: formica\_rufa (Яндекс)

Published: 2026-09-03T07:03:43Z

Content type: tutorial

Language: ru

Sources: [Яндекс - Как мы делаем Яндекс / Статьи](<https://devfeed.tech/sources/source.md>)

Topics: [Large Language Model](<https://devfeed.tech/topics/llm.md>), [vlm](<https://devfeed.tech/topics/vlm.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [Mixture of Experts (MoE)](<https://devfeed.tech/topics/mixture-of-experts-moe.md>), [qwen](<https://devfeed.tech/topics/qwen.md>), [Mercury](<https://devfeed.tech/topics/mercury-lang.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [llm](<https://devfeed.tech/tags/llm.md>), [ml](<https://devfeed.tech/tags/ml.md>), [moe](<https://devfeed.tech/tags/moe.md>), [qwen](<https://devfeed.tech/tags/qwen.md>), [tag-055aee430837](<https://devfeed.tech/tags/tag-055aee430837.md>), [tag-61cd5a476b1d](<https://devfeed.tech/tags/tag-61cd5a476b1d.md>), [tag-831b63de9433](<https://devfeed.tech/tags/tag-831b63de9433.md>), [tag-86b843454893](<https://devfeed.tech/tags/tag-86b843454893.md>), [tag-95a2c958e46b](<https://devfeed.tech/tags/tag-95a2c958e46b.md>), [tag-ef0b1bf200df](<https://devfeed.tech/tags/tag-ef0b1bf200df.md>), [vlm](<https://devfeed.tech/tags/vlm.md>)

### AI overview

Yandex describes its work on an Alice omnimodel that combines a text LLM and a visual VLM into one model for text and image interactions. The article focuses on lessons from training and alignment, including the role of MoE architecture and reinforcement learning.

### Source excerpt

Ещё недавно Алиса отвечала на текст и на картинку будто двумя разными голосами. Под капотом и правда жили две генеративные модели: текстовая LLM и визуальная VLM, а между ними -- стена из непрозрачного роутинга, разных форматов ответов и разной вёрстки. Почти год мы сводили их в одну омнимодель -- такую, которая воспринимает текст и изображения как единое целое, без переключений за кадром. Получилось не всё и не сразу, но путь вышел поучительным, и в этой статье я хочу поделиться тем, что мы поняли про обучение таких моделей. Попутно -- несколько неочевидных поворотов: почему за два года до этого та же затея разваливалась, что изменила MoE-архитектура, почему омнипретрейн пришлось собирать с конца и почему один вид RL переезжает на большую модель легко, а другой рассыпается прямо на глазах. Меня зовут Алексей Григорьев, я представляю большую команду разработки омнимодели Яндекса. Вместе с моим коллегой Данилой Кашиным я расскажу про все технические грабли не со стороны наблюдателя, а как их непосредственный собиратель. Но рассказывать я буду с акцентом не на красивом замысле, а на самой болезненной части -- алайнменте. Читать далее

## Building Federated Multimodal AI Workflows with NVIDIA FLARE

DevFeed: [Building Federated Multimodal AI Workflows with NVIDIA FLARE](<https://devfeed.tech/articles/building-federated-multimodal-ai-workflows-with-nvidia-flare-6776.md>)

Original publisher: [Read original article](<https://developer.nvidia.com/blog/building-federated-multimodal-ai-workflows-with-nvidia-flare/>)

Author: Tanya Lenz

Published: 2026-08-19T17:50:47Z

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: [vlm](<https://devfeed.tech/topics/vlm.md>), [SDKs](<https://devfeed.tech/topics/sdks.md>)

Tags: [agentic-ai-generative-ai](<https://devfeed.tech/tags/agentic-ai-generative-ai.md>), [ai](<https://devfeed.tech/tags/ai.md>), [data-science](<https://devfeed.tech/tags/data-science.md>), [edge-computing](<https://devfeed.tech/tags/edge-computing.md>), [featured](<https://devfeed.tech/tags/featured.md>), [federated-learning](<https://devfeed.tech/tags/federated-learning.md>), [multimodal](<https://devfeed.tech/tags/multimodal.md>), [multimodal-ai](<https://devfeed.tech/tags/multimodal-ai.md>), [nvidia](<https://devfeed.tech/tags/nvidia.md>), [python](<https://devfeed.tech/tags/python.md>), [streaming](<https://devfeed.tech/tags/streaming.md>), [training](<https://devfeed.tech/tags/training.md>), [training-ai-models](<https://devfeed.tech/tags/training-ai-models.md>), [updates](<https://devfeed.tech/tags/updates.md>), [vlms](<https://devfeed.tech/tags/vlms.md>), [workflows](<https://devfeed.tech/tags/workflows.md>)

### AI overview

The article explains how NVIDIA FLARE supports federated training for multimodal and vision-language models when data remains distributed across sites. It focuses on deciding which model state to exchange and on efficiently transferring and aggregating large updates through externalization, tensor streaming, and disk-backed aggregation.

### Source excerpt

Modern vision-language models (VLMs) can support tasks such as visual question answering, captioning, and image-text reasoning. In practice, however, the data...

## Introducing CARE-X: Towards Clinically Useful Radiology VLMs with Auxiliary Supervision, Reward-Aligned Learning, and Tool-Augmented Measurement

DevFeed: [Introducing CARE-X: Towards Clinically Useful Radiology VLMs with Auxiliary Supervision, Reward-Aligned Learning, and Tool-Augmented Measurement](<https://devfeed.tech/articles/introducing-care-x-towards-clinically-useful-radiology-vlms-with-auxiliary-supervision-reward-aligned-learning-and-tool-augmented-measurement-6800.md>)

Original publisher: [Read original article](<https://www.microsoft.com/en-us/research/blog/introducing-care-x-towards-clinically-useful-radiology-vlms-with-auxiliary-supervision-reward-aligned-learning-and-tool-augmented-measurement/>)

Author: Mercy Ranjit, Nikhilesh E, Dr. Abhyuday Kumara Swamy, Tanuja Ganu

Published: 2026-08-11T16:00:00Z

Content type: article

Language: en

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

Topics: [vlm](<https://devfeed.tech/topics/vlm.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [Reinforcement learning](<https://devfeed.tech/topics/reinforcement-learning.md>), [data](<https://devfeed.tech/topics/data.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [data](<https://devfeed.tech/tags/data.md>), [generation](<https://devfeed.tech/tags/generation.md>), [reasoning](<https://devfeed.tech/tags/reasoning.md>), [reinforcement-learning](<https://devfeed.tech/tags/reinforcement-learning.md>), [research](<https://devfeed.tech/tags/research.md>), [research-blog](<https://devfeed.tech/tags/research-blog.md>), [tools](<https://devfeed.tech/tags/tools.md>), [vlms](<https://devfeed.tech/tags/vlms.md>)

### AI overview

CARE-X is a research chest X-ray vision-language model that combines free-text report generation, structured diagnostic prediction, and reinforcement learning for multi-task clinical interpretation. The article also describes a separate experiment using deterministic measurement tools with Qwen3-VL-4B-Instruct and reports validation on real-world Indian clinical data, while emphasizing that CARE-X is not approved for clinical use.

### Source excerpt

Radiology AI is evolving beyond report generation. CARE-X explores a unified approach that combines flexible reasoning, calibrated predictions, and measurement-based tools for chest X-ray interpretation. The post Introducing CARE-X: Towards Clinically Useful Radiology VLMs with Auxiliary Supervision, Reward-Aligned Learning, and Tool-Augmented Measurement appeared first on Microsoft Research.

## How Yandex combined image and document text signals for image-search ranking

DevFeed: [How Yandex combined image and document text signals for image-search ranking](<https://devfeed.tech/articles/article-24877.md>)

Original publisher: [Read original article](<https://habr.com/ru/companies/yandex/articles/1066946/>)

Author: nikolaevkona (Яндекс)

Published: 2026-08-10T08:00:19Z

Content type: tutorial

Language: ru

Sources: [Яндекс - Как мы делаем Яндекс / Статьи](<https://devfeed.tech/sources/source.md>)

Topics: [яндекс](<https://devfeed.tech/topics/tag-4004cf5948d3.md>), [vlm](<https://devfeed.tech/topics/vlm.md>), [Image](<https://devfeed.tech/topics/image.md>), [realtime](<https://devfeed.tech/topics/realtime.md>)

Tags: [image](<https://devfeed.tech/tags/image.md>), [machine-learning](<https://devfeed.tech/tags/machine-learning.md>), [ml](<https://devfeed.tech/tags/ml.md>), [realtime](<https://devfeed.tech/tags/realtime.md>), [tag-4004cf5948d3](<https://devfeed.tech/tags/tag-4004cf5948d3.md>), [tag-8be2dbf54d97](<https://devfeed.tech/tags/tag-8be2dbf54d97.md>), [vlm](<https://devfeed.tech/tags/vlm.md>), [yandex-e983188bc433](<https://devfeed.tech/tags/yandex-e983188bc433.md>)

### AI overview

Yandex describes using multimodal vision-language models to jointly assess an image and its associated document text for image-search ranking. The team distilled a larger model into lighter models for different pipeline stages and reports deployment in real-time search.

### Source excerpt

Исторически в Яндекс Картинках релевантность документа оценивалась по двум сигналам: насколько запросу подходит само изображение и насколько -- текст, связанный с этим изображением. Такой подход позволяет учесть контент картинки и не провалиться на визуально трудноотличимых объектах, однако он же порождает проблему: в "серой зоне", когда текстовая релевантность не сонаправлена с картиночной, становится неочевидно, как именно агрегировать сигналы в финальный скор релевантности. Привет! Я Константин Николаев, занимаюсь внедрением нейротехнологий в Поиске по картинкам. В этой статье я расскажу, как наша команда научила модели смотреть на картинку и читать текст документа одновременно: начали с тяжёлой мультимодальной VLM ради максимального качества, а затем дистиллировали её в набор лёгких моделей -- по одной под каждую стадию пайплайна. Что из этого удалось довести до realtime-поиска с десятками тысяч запросов в секунду и как совместный анализ двух модальностей добавил 5% релевантных картинок в топ выдачи -- под катом. Читать далее

## Meta is back with Muse Glimmer: local, agentic, multimodal, and open source

DevFeed: [Meta is back with Muse Glimmer: local, agentic, multimodal, and open source](<https://devfeed.tech/articles/meta-is-back-with-muse-glimmer-local-agentic-multimodal-and-open-source-7362.md>)

Original publisher: [Read original article](<https://huggingface.co/blog/muse-glimmer>)

Author: Pedro Cuenca; merve; ben burtenshaw; Aritra Roy Gosthipaty

Published: 2026-08-10T00:00:00Z

Content type: article

Language: en

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

Topics: [vlm](<https://devfeed.tech/topics/vlm.md>), [multimodal](<https://devfeed.tech/topics/multimodal.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [hugging face](<https://devfeed.tech/topics/hugging-face.md>), [Benchmark](<https://devfeed.tech/topics/benchmark.md>), [coding](<https://devfeed.tech/topics/coding.md>)

Tags: [agentic](<https://devfeed.tech/tags/agentic.md>), [artificial-intelligence](<https://devfeed.tech/tags/artificial-intelligence.md>), [benchmark](<https://devfeed.tech/tags/benchmark.md>), [hub](<https://devfeed.tech/tags/hub.md>), [hugging-face](<https://devfeed.tech/tags/hugging-face.md>), [images](<https://devfeed.tech/tags/images.md>), [llama-cpp](<https://devfeed.tech/tags/llama-cpp.md>), [llms](<https://devfeed.tech/tags/llms.md>), [local](<https://devfeed.tech/tags/local.md>), [meta](<https://devfeed.tech/tags/meta.md>), [model](<https://devfeed.tech/tags/model.md>), [multimodal](<https://devfeed.tech/tags/multimodal.md>), [muse](<https://devfeed.tech/tags/muse.md>), [open-source](<https://devfeed.tech/tags/open-source.md>), [videos](<https://devfeed.tech/tags/videos.md>), [vllm](<https://devfeed.tech/tags/vllm.md>), [vlm](<https://devfeed.tech/tags/vlm.md>), [vlms](<https://devfeed.tech/tags/vlms.md>)

### AI overview

Hugging Face presents Muse Glimmer, a local, agentic, multimodal, open-source 30B-parameter vision-language model developed with Meta. The article outlines its vision and language architecture, benchmark context, optional speculative decoding for faster generation, and support for both images and videos.

### Source excerpt

We're on a journey to advance and democratize artificial intelligence through open source and open science.

## Gemini Robotics 2 brings whole body intelligence to robots

DevFeed: [Gemini Robotics 2 brings whole body intelligence to robots](<https://devfeed.tech/articles/gemini-robotics-2-brings-whole-body-intelligence-to-robots-6170.md>)

Original publisher: [Read original article](<https://deepmind.google/blog/gemini-robotics-2-brings-whole-body-intelligence-to-robots/>)

Author: Carolina Parada

Published: 2026-07-28T13:21:37Z

Content type: article

Language: en

Sources: [Google DeepMind News](<https://devfeed.tech/sources/google-deepmind-news.md>)

Topics: [Robotics](<https://devfeed.tech/topics/robotics.md>), [AI Models](<https://devfeed.tech/topics/ai-models.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [vlm](<https://devfeed.tech/topics/vlm.md>), [multimodal](<https://devfeed.tech/topics/multimodal.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-models](<https://devfeed.tech/tags/ai-models.md>), [collaboration](<https://devfeed.tech/tags/collaboration.md>), [gemini](<https://devfeed.tech/tags/gemini.md>), [models](<https://devfeed.tech/tags/models.md>), [multimodal](<https://devfeed.tech/tags/multimodal.md>), [on-device](<https://devfeed.tech/tags/on-device.md>), [robotics](<https://devfeed.tech/tags/robotics.md>), [robots](<https://devfeed.tech/tags/robots.md>), [teamwork](<https://devfeed.tech/tags/teamwork.md>), [vision](<https://devfeed.tech/tags/vision.md>)

### AI overview

Gemini Robotics 2 is presented as an intelligence layer for adaptable robots, enabling whole-body control, dexterous manipulation, multi-robot teamwork, and adaptation to new robotic bodies. The article describes three models: a vision-language-action model for motor control, an embodied reasoning vision-language model for communication and multi-step planning, and an on-device model optimized for local operation.

### Source excerpt

From feet to fingertips -- we are teaching robots intelligent whole-body control, fine dexterity, and teamwork to complete a broad range of complex tasks.

## NVIDIA Ising Enables Fully Automated Quantum Computer Calibration with Enhanced In-Context Learning

DevFeed: [NVIDIA Ising Enables Fully Automated Quantum Computer Calibration with Enhanced In-Context Learning](<https://devfeed.tech/articles/nvidia-ising-enables-fully-automated-quantum-computer-calibration-with-enhanced-in-context-learning-6895.md>)

Original publisher: [Read original article](<https://developer.nvidia.com/blog/nvidia-ising-enables-fully-automated-quantum-computer-calibration-with-enhanced-in-context-learning/>)

Author: Tanya Lenz

Published: 2026-07-27T16:00:00Z

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: [Ising](<https://devfeed.tech/topics/ising.md>), [Quantum Computing](<https://devfeed.tech/topics/quantum-computing.md>), [vlm](<https://devfeed.tech/topics/vlm.md>), [Nvidia](<https://devfeed.tech/topics/nvidia.md>), [Open Source](<https://devfeed.tech/topics/open-source.md>), [Benchmark](<https://devfeed.tech/topics/benchmark.md>), [benchmarking](<https://devfeed.tech/topics/benchmarking.md>), [NVFP4](<https://devfeed.tech/topics/nvfp4.md>), [DGX Spark](<https://devfeed.tech/topics/dgx-spark.md>)

Tags: [agentic-ai-generative-ai](<https://devfeed.tech/tags/agentic-ai-generative-ai.md>), [ai-agent](<https://devfeed.tech/tags/ai-agent.md>), [benchmark](<https://devfeed.tech/tags/benchmark.md>), [benchmarking](<https://devfeed.tech/tags/benchmarking.md>), [data-science](<https://devfeed.tech/tags/data-science.md>), [dgx-spark](<https://devfeed.tech/tags/dgx-spark.md>), [featured](<https://devfeed.tech/tags/featured.md>), [ising](<https://devfeed.tech/tags/ising.md>), [nvfp4](<https://devfeed.tech/tags/nvfp4.md>), [nvidia](<https://devfeed.tech/tags/nvidia.md>), [open-source](<https://devfeed.tech/tags/open-source.md>), [quantum](<https://devfeed.tech/tags/quantum.md>), [quantum-computing](<https://devfeed.tech/tags/quantum-computing.md>), [simulation-modeling-design](<https://devfeed.tech/tags/simulation-modeling-design.md>), [training-ai-models](<https://devfeed.tech/tags/training-ai-models.md>), [vlm](<https://devfeed.tech/tags/vlm.md>), [vlms](<https://devfeed.tech/tags/vlms.md>)

### AI overview

NVIDIA Ising Calibration 1.5 is an open-source vision-language model for interpreting quantum-processor diagnostics and recommending calibration actions. The article highlights zero-shot and in-context learning evaluation on QCalEval, plus an NVFP4-quantized version for local deployment.

### Source excerpt

NVIDIA Ising Calibration is an open source vision language model (VLM) designed to interpret diagnostic outputs from quantum processors and determine how they...

## A better way to turn 2D designs into 3D models for rapid prototyping

DevFeed: [A better way to turn 2D designs into 3D models for rapid prototyping](<https://devfeed.tech/articles/a-better-way-to-turn-2d-designs-into-3d-models-for-rapid-prototyping-37984.md>)

Original publisher: [Read original article](<https://news.mit.edu/2026/turning-2d-designs-into-3d-models-for-rapid-prototyping-0716>)

Author: Adam Zewe | MIT News

Published: 2026-07-16T04:00:00Z

Content type: news

Language: en

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

Topics: [3D](<https://devfeed.tech/topics/3d.md>), [vlm](<https://devfeed.tech/topics/vlm.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [AI Development](<https://devfeed.tech/topics/ai-development.md>), [Computing](<https://devfeed.tech/topics/computing.md>), [coding](<https://devfeed.tech/topics/coding.md>)

Tags: [3d](<https://devfeed.tech/tags/3d.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-models](<https://devfeed.tech/tags/ai-models.md>), [algorithms](<https://devfeed.tech/tags/algorithms.md>), [artificial-intelligence](<https://devfeed.tech/tags/artificial-intelligence.md>), [automated](<https://devfeed.tech/tags/automated.md>), [computer-aided-design-cad](<https://devfeed.tech/tags/computer-aided-design-cad.md>), [computer-modeling](<https://devfeed.tech/tags/computer-modeling.md>), [computer-science-and-technology](<https://devfeed.tech/tags/computer-science-and-technology.md>), [computing](<https://devfeed.tech/tags/computing.md>), [design](<https://devfeed.tech/tags/design.md>), [efficiently](<https://devfeed.tech/tags/efficiently.md>), [faez-ahmed](<https://devfeed.tech/tags/faez-ahmed.md>), [generation](<https://devfeed.tech/tags/generation.md>), [generative-ai](<https://devfeed.tech/tags/generative-ai.md>), [geometric-inference-feedback-tuning-gift](<https://devfeed.tech/tags/geometric-inference-feedback-tuning-gift.md>), [giorgio-giannone](<https://devfeed.tech/tags/giorgio-giannone.md>), [machine-learning](<https://devfeed.tech/tags/machine-learning.md>), [mechanical-engineering](<https://devfeed.tech/tags/mechanical-engineering.md>), [mit-ibm-computing-research-lab](<https://devfeed.tech/tags/mit-ibm-computing-research-lab.md>), [mit-schwarzman-college-of-computing](<https://devfeed.tech/tags/mit-schwarzman-college-of-computing.md>), [performance](<https://devfeed.tech/tags/performance.md>), [rapid-prototyping](<https://devfeed.tech/tags/rapid-prototyping.md>), [research](<https://devfeed.tech/tags/research.md>), [school-of-engineering](<https://devfeed.tech/tags/school-of-engineering.md>), [systems-design](<https://devfeed.tech/tags/systems-design.md>), [vision-language-models-vlms](<https://devfeed.tech/tags/vision-language-models-vlms.md>)

### AI overview

Researchers developed an automated framework that teaches vision-language models to convert 2D designs into more accurate and functional CAD programs while using less computation. The system turns model failures into training data to improve CAD generation and support rapid prototyping.

### Source excerpt

Researchers developed an automated framework that helps AI models generate CAD programs more accurately and efficiently.

## SceneSmith uses collaborative AI agents to create 3D environments for robot training

DevFeed: [SceneSmith uses collaborative AI agents to create 3D environments for robot training](<https://devfeed.tech/articles/ai-agents-create-virtual-playgrounds-to-help-robots-get-crucial-training-data-37940.md>)

Original publisher: [Read original article](<https://news.mit.edu/2026/ai-agents-create-virtual-playgrounds-to-help-robots-get-crucial-training-data-0713>)

Author: Alex Shipps | MIT CSAIL

Published: 2026-07-13T18:50:00Z

Content type: news

Language: en

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

Topics: [AI research agents](<https://devfeed.tech/topics/ai-research-agents.md>), [robot grasping simulation](<https://devfeed.tech/topics/robot-grasping-simulation.md>), [Simulation](<https://devfeed.tech/topics/simulation.md>), [vlm](<https://devfeed.tech/topics/vlm.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [Computer Science and Artificial Intelligence Laboratory (CSAIL)](<https://devfeed.tech/topics/computer-science-and-artificial-intelligence-laboratory-csail.md>)

Tags: [3-d](<https://devfeed.tech/tags/3-d.md>), [3d](<https://devfeed.tech/tags/3d.md>), [adversarial-machine-learning](<https://devfeed.tech/tags/adversarial-machine-learning.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [artificial-intelligence](<https://devfeed.tech/tags/artificial-intelligence.md>), [computer-science-and-artificial-intelligence-laboratory-csail](<https://devfeed.tech/tags/computer-science-and-artificial-intelligence-laboratory-csail.md>), [computer-science-and-technology](<https://devfeed.tech/tags/computer-science-and-technology.md>), [electrical-engineering-and-computer-science-eecs](<https://devfeed.tech/tags/electrical-engineering-and-computer-science-eecs.md>), [foundation-models](<https://devfeed.tech/tags/foundation-models.md>), [general-purpose-robotics](<https://devfeed.tech/tags/general-purpose-robotics.md>), [gpt-5-2](<https://devfeed.tech/tags/gpt-5-2.md>), [machine-learning](<https://devfeed.tech/tags/machine-learning.md>), [mit-csail](<https://devfeed.tech/tags/mit-csail.md>), [mit-eecs](<https://devfeed.tech/tags/mit-eecs.md>), [mit-schwarzman-college-of-computing](<https://devfeed.tech/tags/mit-schwarzman-college-of-computing.md>), [national-science-foundation-nsf](<https://devfeed.tech/tags/national-science-foundation-nsf.md>), [nicholas-pfaff](<https://devfeed.tech/tags/nicholas-pfaff.md>), [research](<https://devfeed.tech/tags/research.md>), [robot-simulations](<https://devfeed.tech/tags/robot-simulations.md>), [robotics](<https://devfeed.tech/tags/robotics.md>), [robots](<https://devfeed.tech/tags/robots.md>), [russ-tedrake](<https://devfeed.tech/tags/russ-tedrake.md>), [scene-generation](<https://devfeed.tech/tags/scene-generation.md>), [scenesmith](<https://devfeed.tech/tags/scenesmith.md>), [school-of-engineering](<https://devfeed.tech/tags/school-of-engineering.md>), [simulation](<https://devfeed.tech/tags/simulation.md>), [simulation-ready-indoor-scenes](<https://devfeed.tech/tags/simulation-ready-indoor-scenes.md>), [virtual-playgrounds](<https://devfeed.tech/tags/virtual-playgrounds.md>), [vision-language-models-vlms](<https://devfeed.tech/tags/vision-language-models-vlms.md>), [zero-shot-policy](<https://devfeed.tech/tags/zero-shot-policy.md>)

### AI overview

MIT CSAIL and Toyota Research Institute researchers developed SceneSmith, a system that uses three collaborative AI agents to create realistic 3D environments for robot training. The scenes can be loaded into physics simulation software, allowing robots to practice tasks before real-world testing.

### Source excerpt

"SceneSmith" system uses collaborative AI agents to create realistic 3D environments of places like kitchens, hotels, and living rooms, where robots can simulate everyday chores.

## LeRobot v0.6.0: Imagine, Evaluate, Improve

DevFeed: [LeRobot v0.6.0: Imagine, Evaluate, Improve](<https://devfeed.tech/articles/lerobot-v0-6-0-imagine-evaluate-improve-7329.md>)

Original publisher: [Read original article](<https://huggingface.co/blog/lerobot-release-v060>)

Author: Steven Palma; Pepijn Kooijmans; Caroline Pascal; Khalil Meftah; Maxime Ellerbach; Martino Russi; Nikodem Bartnik; Nicolas Rabault; Thomas Wolf

Published: 2026-07-07T00:00:00Z

Content type: article

Language: en

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

Topics: [lerobot](<https://devfeed.tech/topics/lerobot.md>), [World models](<https://devfeed.tech/topics/world-models.md>), [Robotics](<https://devfeed.tech/topics/robotics.md>), [vlm](<https://devfeed.tech/topics/vlm.md>), [Cosmos](<https://devfeed.tech/topics/cosmos.md>), [foundation-models](<https://devfeed.tech/topics/foundation-models.md>), [datasets](<https://devfeed.tech/topics/datasets.md>), [Open Source](<https://devfeed.tech/topics/open-source.md>)

Tags: [artificial-intelligence](<https://devfeed.tech/tags/artificial-intelligence.md>), [cli](<https://devfeed.tech/tags/cli.md>), [cosmos](<https://devfeed.tech/tags/cosmos.md>), [datasets](<https://devfeed.tech/tags/datasets.md>), [gpu](<https://devfeed.tech/tags/gpu.md>), [lerobot](<https://devfeed.tech/tags/lerobot.md>), [models](<https://devfeed.tech/tags/models.md>), [open-source](<https://devfeed.tech/tags/open-source.md>), [robotics](<https://devfeed.tech/tags/robotics.md>), [science](<https://devfeed.tech/tags/science.md>), [training](<https://devfeed.tech/tags/training.md>), [vlm](<https://devfeed.tech/tags/vlm.md>), [world-model](<https://devfeed.tech/tags/world-model.md>)

### AI overview

LeRobot v0.6.0 adds world-model policies, new vision-language-action models, reward-model APIs, simulation benchmarks, human-in-the-loop CLI corrections, FSDP and cloud training. It also expands dataset capabilities with depth support, automated language annotation, custom video encoding, and faster data loading.

### Source excerpt

We're on a journey to advance and democratize artificial intelligence through open source and open science.

## PRX Part 4: Our Data Strategy

DevFeed: [PRX Part 4: Our Data Strategy](<https://devfeed.tech/articles/prx-part-4-our-data-strategy-7039.md>)

Original publisher: [Read original article](<https://huggingface.co/blog/Photoroom/prx-part4-data>)

Author: Roman Frigg; David Bertoin; Jon Almazán

Published: 2026-07-06T15:30:55Z

Content type: article

Language: en

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

Topics: [Training AI Models](<https://devfeed.tech/topics/training-ai-models.md>), [vlm](<https://devfeed.tech/topics/vlm.md>)

Tags: [data](<https://devfeed.tech/tags/data.md>), [datasets](<https://devfeed.tech/tags/datasets.md>), [diversity](<https://devfeed.tech/tags/diversity.md>), [fine-tuning](<https://devfeed.tech/tags/fine-tuning.md>), [images](<https://devfeed.tech/tags/images.md>), [tooling](<https://devfeed.tech/tags/tooling.md>), [training](<https://devfeed.tech/tags/training.md>), [vlm](<https://devfeed.tech/tags/vlm.md>)

### AI overview

The article describes assembling a diverse pre-training corpus for PRX from public and internal datasets, recaptioning images with a vision-language model, and prioritizing broad, faithful long-caption coverage over aesthetic filtering.

### Source excerpt

In one sentence: we assemble training data from a mix of public and internal datasets, re-caption the images with a VLM, and turn the result into the streamable corpus we trained PRX on. At a high level, the data pipeline looks like this: In the following we will dive into it in detail. The goal was to assemble a large, diverse dataset for pre-training.

## Direct Preference Optimization Beyond Chatbots

DevFeed: [Direct Preference Optimization Beyond Chatbots](<https://devfeed.tech/articles/direct-preference-optimization-beyond-chatbots-6992.md>)

Original publisher: [Read original article](<https://huggingface.co/blog/Dharma-AI/direct-preference-optimization-beyond-chatbots>)

Author: Erick Lachmann; Gabriel Pimenta de Freitas Cardoso; Francisco de Almeida Rocha Alves

Published: 2026-06-03T12:55:11Z

Content type: article

Language: en

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

Topics: [dpo](<https://devfeed.tech/topics/dpo.md>), [vlm](<https://devfeed.tech/topics/vlm.md>), [Benchmark](<https://devfeed.tech/topics/benchmark.md>), [Fine-tuning](<https://devfeed.tech/topics/fine-tuning.md>), [hugging face](<https://devfeed.tech/topics/hugging-face.md>), [Open Source](<https://devfeed.tech/topics/open-source.md>)

Tags: [benchmark](<https://devfeed.tech/tags/benchmark.md>), [cost](<https://devfeed.tech/tags/cost.md>), [dpo](<https://devfeed.tech/tags/dpo.md>), [efficiency](<https://devfeed.tech/tags/efficiency.md>), [fine-tuning](<https://devfeed.tech/tags/fine-tuning.md>), [hugging-face](<https://devfeed.tech/tags/hugging-face.md>), [model](<https://devfeed.tech/tags/model.md>), [ocr](<https://devfeed.tech/tags/ocr.md>), [open-source](<https://devfeed.tech/tags/open-source.md>), [vision](<https://devfeed.tech/tags/vision.md>)

### AI overview

The article presents Direct Preference Optimization (DPO) as a second training stage for reducing text degeneration in DharmaOCR, a structured OCR model. Applied after supervised fine-tuning, DPO reduced degeneration across every tested model family, with an average reduction of 59.4% and a best-case reduction of 87.6%.

### Source excerpt

In April, we released DharmaOCR, our specialized structured OCR model (available on Hugging Face) along with a paper detailing the methodology behind it and a benchmark demonstrating its superior quality and cost efficiency. The paper benchmarked leading vision-language model families - both open-source and commercial - on a structured document extraction task: OCR on Brazilian Portuguese text.

## Multimodal Embedding & Reranker Models with Sentence Transformers

DevFeed: [Multimodal Embedding & Reranker Models with Sentence Transformers](<https://devfeed.tech/articles/multimodal-embedding-reranker-models-with-sentence-transformers-7361.md>)

Original publisher: [Read original article](<https://huggingface.co/blog/multimodal-sentence-transformers>)

Author: Tom Aarsen

Published: 2026-04-09T00:00:00Z

Content type: article

Language: en

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

Topics: [sentence-transformers](<https://devfeed.tech/topics/sentence-transformers.md>), [Embeddings](<https://devfeed.tech/topics/embeddings.md>), [multimodal](<https://devfeed.tech/topics/multimodal.md>), [Retrieval Augmented Generation (RAG)](<https://devfeed.tech/topics/retrieval-augmented-generation-rag.md>), [vlm](<https://devfeed.tech/topics/vlm.md>), [GPU](<https://devfeed.tech/topics/gpu.md>), [Cloud](<https://devfeed.tech/topics/cloud.md>)

Tags: [cloud](<https://devfeed.tech/tags/cloud.md>), [community](<https://devfeed.tech/tags/community.md>), [embedding](<https://devfeed.tech/tags/embedding.md>), [gpu](<https://devfeed.tech/tags/gpu.md>), [multimodal](<https://devfeed.tech/tags/multimodal.md>), [nlp](<https://devfeed.tech/tags/nlp.md>), [open-source](<https://devfeed.tech/tags/open-source.md>), [rag](<https://devfeed.tech/tags/rag.md>), [retrieval](<https://devfeed.tech/tags/retrieval.md>), [search](<https://devfeed.tech/tags/search.md>), [sentence-transformers](<https://devfeed.tech/tags/sentence-transformers.md>), [transformers](<https://devfeed.tech/tags/transformers.md>), [vision](<https://devfeed.tech/tags/vision.md>)

### AI overview

This article explains how multimodal embedding and reranker models in Sentence Transformers map text, images, audio, and video into shared spaces or score cross-modal pairs. It covers visual document retrieval, cross-modal search, multimodal RAG, hardware requirements, model loading, and similarity computation.

### Source excerpt

We're on a journey to advance and democratize artificial intelligence through open source and open science.

## NVIDIA Cosmos Reason 2 Brings Advanced Reasoning To Physical AI

DevFeed: [NVIDIA Cosmos Reason 2 Brings Advanced Reasoning To Physical AI](<https://devfeed.tech/articles/nvidia-cosmos-reason-2-brings-advanced-reasoning-to-physical-ai-7400.md>)

Original publisher: [Read original article](<https://huggingface.co/blog/nvidia/nvidia-cosmos-reason-2-brings-advanced-reasoning>)

Author: Tsung-Yi Lin; Debraj Sinha

Published: 2026-01-05T22:56:51Z

Content type: release

Language: en

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

Topics: [Cosmos](<https://devfeed.tech/topics/cosmos.md>), [Physical AI](<https://devfeed.tech/topics/physical-ai.md>), [vlm](<https://devfeed.tech/topics/vlm.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [Video Analytics](<https://devfeed.tech/topics/video-analytics.md>), [long-context](<https://devfeed.tech/topics/long-context.md>), [Deployment](<https://devfeed.tech/topics/deployment.md>), [data](<https://devfeed.tech/topics/data.md>), [datasets](<https://devfeed.tech/topics/datasets.md>), [Cloud](<https://devfeed.tech/topics/cloud.md>)

Tags: [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [analytics](<https://devfeed.tech/tags/analytics.md>), [cloud](<https://devfeed.tech/tags/cloud.md>), [cosmos](<https://devfeed.tech/tags/cosmos.md>), [data](<https://devfeed.tech/tags/data.md>), [datasets](<https://devfeed.tech/tags/datasets.md>), [deployment](<https://devfeed.tech/tags/deployment.md>), [language-models](<https://devfeed.tech/tags/language-models.md>), [long-context](<https://devfeed.tech/tags/long-context.md>), [models](<https://devfeed.tech/tags/models.md>), [nvidia](<https://devfeed.tech/tags/nvidia.md>), [ocr](<https://devfeed.tech/tags/ocr.md>), [open](<https://devfeed.tech/tags/open.md>), [performance](<https://devfeed.tech/tags/performance.md>), [physical-ai](<https://devfeed.tech/tags/physical-ai.md>), [physics](<https://devfeed.tech/tags/physics.md>), [reasoning](<https://devfeed.tech/tags/reasoning.md>), [vision](<https://devfeed.tech/tags/vision.md>)

### AI overview

NVIDIA released Cosmos Reason 2, an open reasoning vision-language model for physical AI. The model is designed to help robots and AI agents understand, plan, and act in the physical world, with improved spatio-temporal reasoning, visual perception, OCR, long-context input, and deployment from edge to cloud.

### Source excerpt

NVIDIA today released Cosmos Reason 2, the latest advancement in open, reasoning vision language models for physical AI. Cosmos Reason 2 surpasses its previous version in accuracy and tops the Physical AI Bench and Physical Reasoning leaderboards as the #1 open model for visual understanding. Since their introduction, vision-language models have rapidly improved at tasks like object and pattern recognition in images.

## Get your VLM running in 3 simple steps on Intel CPUs

DevFeed: [Get your VLM running in 3 simple steps on Intel CPUs](<https://devfeed.tech/articles/get-your-vlm-running-in-3-simple-steps-on-intel-cpus-7431.md>)

Original publisher: [Read original article](<https://huggingface.co/blog/openvino-vlm>)

Author: Ezequiel Lanza; Helena; Nikita; Ella Charlaix; Ilyas Moutawwakil

Published: 2025-10-15T00:00:00Z

Content type: tutorial

Language: en

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

Topics: [vlm](<https://devfeed.tech/topics/vlm.md>), [smolvlm](<https://devfeed.tech/topics/smolvlm.md>), [optimum](<https://devfeed.tech/topics/optimum.md>), [quantization](<https://devfeed.tech/topics/quantization.md>), [Inference](<https://devfeed.tech/topics/inference.md>), [intel](<https://devfeed.tech/topics/intel.md>)

Tags: [inference](<https://devfeed.tech/tags/inference.md>), [intel](<https://devfeed.tech/tags/intel.md>), [optimum](<https://devfeed.tech/tags/optimum.md>), [quantization](<https://devfeed.tech/tags/quantization.md>), [smolvlm](<https://devfeed.tech/tags/smolvlm.md>), [vlm](<https://devfeed.tech/tags/vlm.md>)

### AI overview

A tutorial explains how to run SmolVLM locally with Optimum Intel and OpenVINO, then optimize it for lower memory use and faster inference through quantization.

### Source excerpt

We're on a journey to advance and democratize artificial intelligence through open source and open science.

## Smol2Operator: Post-Training GUI Agents for Computer Use

DevFeed: [Smol2Operator: Post-Training GUI Agents for Computer Use](<https://devfeed.tech/articles/smol2operator-post-training-gui-agents-for-computer-use-7476.md>)

Original publisher: [Read original article](<https://huggingface.co/blog/smol2operator>)

Author: Amir Mahla; merve; Sergio Paniego; Vaibhav Srivastav; Lewis Tunstall

Published: 2025-09-23T00:00:00Z

Content type: article

Language: en

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

Topics: [gui-agents](<https://devfeed.tech/topics/gui-agents.md>), [computer-use](<https://devfeed.tech/topics/computer-use.md>), [post-training](<https://devfeed.tech/topics/post-training.md>), [vlm](<https://devfeed.tech/topics/vlm.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [Open Source](<https://devfeed.tech/topics/open-source.md>), [Benchmark](<https://devfeed.tech/topics/benchmark.md>), [datasets](<https://devfeed.tech/topics/datasets.md>), [Fine-tuning](<https://devfeed.tech/topics/fine-tuning.md>)

Tags: [agentic](<https://devfeed.tech/tags/agentic.md>), [agents](<https://devfeed.tech/tags/agents.md>), [artificial-intelligence](<https://devfeed.tech/tags/artificial-intelligence.md>), [benchmark](<https://devfeed.tech/tags/benchmark.md>), [blog](<https://devfeed.tech/tags/blog.md>), [community](<https://devfeed.tech/tags/community.md>), [computer-use](<https://devfeed.tech/tags/computer-use.md>), [datasets](<https://devfeed.tech/tags/datasets.md>), [fine-tuning](<https://devfeed.tech/tags/fine-tuning.md>), [gui](<https://devfeed.tech/tags/gui.md>), [gui-agents](<https://devfeed.tech/tags/gui-agents.md>), [language-models](<https://devfeed.tech/tags/language-models.md>), [open-source](<https://devfeed.tech/tags/open-source.md>), [post-training](<https://devfeed.tech/tags/post-training.md>), [science](<https://devfeed.tech/tags/science.md>), [training](<https://devfeed.tech/tags/training.md>), [vision](<https://devfeed.tech/tags/vision.md>), [vlm](<https://devfeed.tech/tags/vlm.md>)

### AI overview

This article presents a multi-phase method for post-training vision-language models to perform GUI automation and computer-use tasks. It covers data processing, action standardization, grounding, supervised fine-tuning, agentic reasoning, and evaluation with the ScreenSpot-v2 benchmark, using SmolVLM2-2.2B-Instruct as the baseline model.

### Source excerpt

We're on a journey to advance and democratize artificial intelligence through open source and open science.

## Vision Language Model Alignment in TRL ⚡

DevFeed: [Vision Language Model Alignment in TRL ⚡](<https://devfeed.tech/articles/vision-language-model-alignment-in-trl-7542.md>)

Original publisher: [Read original article](<https://huggingface.co/blog/trl-vlm-alignment>)

Author: Sergio Paniego; merve; Quentin Gallouédec; Kashif Rasul; Aritra Roy Gosthipaty

Published: 2025-08-07T00:00:00Z

Content type: article

Language: en

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

Topics: [trl](<https://devfeed.tech/topics/trl.md>), [vlm](<https://devfeed.tech/topics/vlm.md>), [multimodal](<https://devfeed.tech/topics/multimodal.md>), [Fine-tuning](<https://devfeed.tech/topics/fine-tuning.md>)

Tags: [artificial-intelligence](<https://devfeed.tech/tags/artificial-intelligence.md>), [dpo](<https://devfeed.tech/tags/dpo.md>), [fine-tuning](<https://devfeed.tech/tags/fine-tuning.md>), [grpo](<https://devfeed.tech/tags/grpo.md>), [model](<https://devfeed.tech/tags/model.md>), [multimodal](<https://devfeed.tech/tags/multimodal.md>), [trl](<https://devfeed.tech/tags/trl.md>), [vision](<https://devfeed.tech/tags/vision.md>), [vlm](<https://devfeed.tech/tags/vlm.md>)

### AI overview

This article presents new and extended methods in TRL for aligning Vision Language Models with human preferences. It covers Mixed Preference Optimization, Group Relative Policy Optimization, Group Sequence Policy Optimization, Reinforce Leave One Out, and Online Direct Preference Optimization, along with native supervised fine-tuning support, training scripts, and demo notebooks.

### Source excerpt

We're on a journey to advance and democratize artificial intelligence through open source and open science.

## TimeScope: How Long Can Your Video Large Multimodal Model Go?

DevFeed: [TimeScope: How Long Can Your Video Large Multimodal Model Go?](<https://devfeed.tech/articles/timescope-how-long-can-your-video-large-multimodal-model-go-7512.md>)

Original publisher: [Read original article](<https://huggingface.co/blog/timescope-video-lmm-benchmark>)

Author: Orr Zohar; Rui Li; Andres Marafioti; Xiaohan Wang

Published: 2025-07-23T00:00:00Z

Content type: article

Language: en

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

Topics: [Benchmark](<https://devfeed.tech/topics/benchmark.md>), [vlm](<https://devfeed.tech/topics/vlm.md>), [long-context](<https://devfeed.tech/topics/long-context.md>), [multimodal-ai](<https://devfeed.tech/topics/multimodal-ai.md>), [hugging face](<https://devfeed.tech/topics/hugging-face.md>)

Tags: [artificial-intelligence](<https://devfeed.tech/tags/artificial-intelligence.md>), [benchmark](<https://devfeed.tech/tags/benchmark.md>), [datasets](<https://devfeed.tech/tags/datasets.md>), [hugging-face](<https://devfeed.tech/tags/hugging-face.md>), [language-models](<https://devfeed.tech/tags/language-models.md>), [long-context](<https://devfeed.tech/tags/long-context.md>), [measurement](<https://devfeed.tech/tags/measurement.md>), [multimodal](<https://devfeed.tech/tags/multimodal.md>), [multimodal-ai](<https://devfeed.tech/tags/multimodal-ai.md>), [open-source](<https://devfeed.tech/tags/open-source.md>), [reasoning](<https://devfeed.tech/tags/reasoning.md>), [retrieval](<https://devfeed.tech/tags/retrieval.md>), [video](<https://devfeed.tech/tags/video.md>)

### AI overview

TimeScope is an open-source benchmark for evaluating how vision-language models understand long videos. It inserts short video clips into videos ranging from one minute to eight hours and measures localized retrieval, information synthesis, and fine-grained temporal perception.

### Source excerpt

We're on a journey to advance and democratize artificial intelligence through open source and open science.

## ScreenEnv: Deploy your full stack Desktop Agent

DevFeed: [ScreenEnv: Deploy your full stack Desktop Agent](<https://devfeed.tech/articles/screenenv-deploy-your-full-stack-desktop-agent-7467.md>)

Original publisher: [Read original article](<https://huggingface.co/blog/screenenv>)

Author: Amir Mahla; Aymeric Roucher

Published: 2025-07-10T00:00:00Z

Content type: article

Language: en

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

Topics: [AI Agent](<https://devfeed.tech/topics/ai-agent.md>), [Docker Container](<https://devfeed.tech/topics/docker-container.md>), [Model Context Protocol](<https://devfeed.tech/topics/model-context-protocol.md>), [computer-use](<https://devfeed.tech/topics/computer-use.md>), [vlm](<https://devfeed.tech/topics/vlm.md>), [GUI](<https://devfeed.tech/topics/gui.md>), [cross-platform](<https://devfeed.tech/topics/cross-platform.md>), [GitHub](<https://devfeed.tech/topics/github.md>), [Linux](<https://devfeed.tech/topics/linux.md>), [Windows](<https://devfeed.tech/topics/windows.md>), [Android](<https://devfeed.tech/topics/android.md>), [macOS](<https://devfeed.tech/topics/macos.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai-agent](<https://devfeed.tech/tags/ai-agent.md>), [community](<https://devfeed.tech/tags/community.md>), [cross-platform](<https://devfeed.tech/tags/cross-platform.md>), [docker](<https://devfeed.tech/tags/docker.md>), [docker-container](<https://devfeed.tech/tags/docker-container.md>), [github](<https://devfeed.tech/tags/github.md>), [gui](<https://devfeed.tech/tags/gui.md>), [mcp](<https://devfeed.tech/tags/mcp.md>), [model-context-protocol](<https://devfeed.tech/tags/model-context-protocol.md>), [open-source](<https://devfeed.tech/tags/open-source.md>), [vlm](<https://devfeed.tech/tags/vlm.md>)

### AI overview

ScreenEnv is a Docker-based sandboxed desktop environment for automating GUI applications and building AI agents that can control a complete desktop session. It supports mouse and keyboard input, window and file management, application launching, terminal commands, and session recording, with integrations through both the Model Context Protocol and a direct Sandbox API. The article also describes building custom desktop agents and plans for Android, macOS, and Windows support.

### Source excerpt

We're on a journey to advance and democratize artificial intelligence through open source and open science.

## Welcome the NVIDIA Llama Nemotron Nano VLM to Hugging Face Hub

DevFeed: [Welcome the NVIDIA Llama Nemotron Nano VLM to Hugging Face Hub](<https://devfeed.tech/articles/welcome-the-nvidia-llama-nemotron-nano-vlm-to-hugging-face-hub-7384.md>)

Original publisher: [Read original article](<https://huggingface.co/blog/nvidia/llama-nemotron-nano-vl>)

Author: Amanda Saunders; Amala Sanjay Deshmukh; Kateryna Chumachenko; Annie Surla; Karan; Tuomas Rintamaki; Matthieu Le; Yu Yao; Chen Cui; Timo Roman; Zhiding Yu; Mike Ranzinger

Published: 2025-06-27T21:09:27Z

Content type: release

Language: en

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

Topics: [vlm](<https://devfeed.tech/topics/vlm.md>), [llama](<https://devfeed.tech/topics/llama.md>), [Nemotron](<https://devfeed.tech/topics/nemotron.md>), [Nvidia](<https://devfeed.tech/topics/nvidia.md>), [hugging face](<https://devfeed.tech/topics/hugging-face.md>), [multimodal](<https://devfeed.tech/topics/multimodal.md>), [Benchmark](<https://devfeed.tech/topics/benchmark.md>), [NeMo](<https://devfeed.tech/topics/nemo.md>), [datasets](<https://devfeed.tech/topics/datasets.md>)

Tags: [benchmark](<https://devfeed.tech/tags/benchmark.md>), [data](<https://devfeed.tech/tags/data.md>), [datasets](<https://devfeed.tech/tags/datasets.md>), [hugging-face](<https://devfeed.tech/tags/hugging-face.md>), [idp](<https://devfeed.tech/tags/idp.md>), [llama](<https://devfeed.tech/tags/llama.md>), [multimodal](<https://devfeed.tech/tags/multimodal.md>), [nemo](<https://devfeed.tech/tags/nemo.md>), [nemotron](<https://devfeed.tech/tags/nemotron.md>), [nvidia](<https://devfeed.tech/tags/nvidia.md>), [ocr](<https://devfeed.tech/tags/ocr.md>), [performance](<https://devfeed.tech/tags/performance.md>), [recognition](<https://devfeed.tech/tags/recognition.md>), [train](<https://devfeed.tech/tags/train.md>), [use-cases](<https://devfeed.tech/tags/use-cases.md>), [vision](<https://devfeed.tech/tags/vision.md>), [vlm](<https://devfeed.tech/tags/vlm.md>), [workflows](<https://devfeed.tech/tags/workflows.md>)

### AI overview

NVIDIA Llama Nemotron Nano VL is an 8B vision-language model for intelligent document processing. Available on Hugging Face, it extracts and interprets text, tables, charts, diagrams, and other information from complex documents.

### Source excerpt

NVIDIA Llama Nemotron Nano VL is a state-of-the-art 8B Vision Language Model (VLM) designed for intelligent document processing, offering high accuracy and multimodal understanding. Available on Hugging Face, it excels in extracting and understanding information from complex documents like invoices, receipts, contracts, and more.

## nanoVLM: The simplest repository to train your VLM in pure PyTorch

DevFeed: [nanoVLM: The simplest repository to train your VLM in pure PyTorch](<https://devfeed.tech/articles/nanovlm-the-simplest-repository-to-train-your-vlm-in-pure-pytorch-7363.md>)

Original publisher: [Read original article](<https://huggingface.co/blog/nanovlm>)

Author: Aritra Roy Gosthipaty; Luis; Andres Marafioti; Sergio Paniego; merve; Pedro Cuenca; Vaibhav Srivastav

Published: 2025-05-21T00:00:00Z

Content type: article

Language: en

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

Topics: [vlm](<https://devfeed.tech/topics/vlm.md>), [PyTorch](<https://devfeed.tech/topics/pytorch.md>), [Language models](<https://devfeed.tech/topics/language-models.md>), [llama](<https://devfeed.tech/topics/llama.md>), [Transformer](<https://devfeed.tech/topics/transformer.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>)

Tags: [community](<https://devfeed.tech/tags/community.md>), [llama](<https://devfeed.tech/tags/llama.md>), [llm](<https://devfeed.tech/tags/llm.md>), [nanovlm](<https://devfeed.tech/tags/nanovlm.md>), [object-detection](<https://devfeed.tech/tags/object-detection.md>), [open](<https://devfeed.tech/tags/open.md>), [pytorch](<https://devfeed.tech/tags/pytorch.md>), [research](<https://devfeed.tech/tags/research.md>), [train](<https://devfeed.tech/tags/train.md>), [training](<https://devfeed.tech/tags/training.md>), [vision](<https://devfeed.tech/tags/vision.md>), [vlm](<https://devfeed.tech/tags/vlm.md>)

### AI overview

nanoVLM is a minimal, readable pure-PyTorch toolkit for building and training vision-language models. It processes images and text to generate text, focuses on visual question answering, and is designed to help beginners explore VLMs through a compact codebase and guided training workflow.

### Source excerpt

We're on a journey to advance and democratize artificial intelligence through open source and open science.

[Next page](<https://devfeed.tech/topics/vlm.md?cursor=WyIyMDI1LTA1LTIxVDAwOjAwOjAwKzAwOjAwIiwgIjYzMjkzYjIyLWUyMjMtNDgxMi04NmY0LTNkNmJjYWUwYjFjZSJd>)