Introduce CoT-VLA – Visual Chain-of-Thought reasoning for Robot Foundation... Models! 🤖 By leveraging next-frame prediction as visual chain-of-thought reasoning, CoT-VLA uses future prediction to guide action generation and unlock large-scale video data for training. #CVPR2025show more

Introducing Alpamayo 1.5. Based on community feedback, we’ve updated... our 10B-parameter chain-of-thought reasoning VLA model to be a more interactive and steerable engine for autonomous vehicle development. Built on the Cosmos-Reason2 VLM backbone, this release adds support for navigation guidance and flexible camera configurations while providing new post-training scripts for model adaptation. 🤗 Learn more:show more

Zero-shot video reasoning (chain-of-frames) isn’t just for Veo3 —... open-source models can understand and edit too! 🕹️ ChronoEdit brings temporal reasoning to image editing. 🔗show more

I just published Trace, a new component for agent... activity. It's one abstraction for reasoning, tool calls, queues, chain of thought, subagents...etc Also in this release: Code Block and AI Elements.show more

Current Vision-Language-Action (VLA) paradigms in autonomous driving primarily rely... on Imitation Learning (IL), which introduces inherent challenges such as distribution shift and causal confusion. Online Reinforcement Learning offers a promising pathway to address these issues through trial-and-error learning. However, applying online reinforcement learning to VLA models in autonomous driving is hindered by inefficient exploration in continuous action spaces. MindDrive, a VLA framework comprising a large language model (LLM) with two distinct sets of LoRA parameters. The one LLM serves as a Decision Expert for scenario reasoning and driving decision-making, while the other acts as an Action Expert that dynamically maps linguistic decisions into feasible trajectories. Paper Title: MindDrive: A Vision-Language-Action Model for Autonomous Driving via Project: Link:show more

What is $REPPO? Reppo uses prediction markets to power... AI data curation. Publishers submit data and domain experts stake $REPPO to assess quality within Datanets, programmable on-chain markets for any AI use case.show more

We’ve added a new prompt improver to the Anthropic... Console. Take an existing prompt and Claude will automatically refine it with prompt engineering techniques like chain-of-thought reasoning.show more

🤖 NVIDIA’s Gr00t N1.5 is now available in LeRobot!... This is the result of a great collaboration between the Hugging Face LeRobot team and NVIDIA Robotics ! Gr00t N1.5 highlights: 🦾 Cross-embodiment foundation model for robots 🧠 Multimodal inputs: vision, language, and proprioception 🪛Tested on the Libero benchmark and real-world hardware tasks 🌍Trained on real robot, synthetic, and internet-scale video data ⚙️ Flow matching action transformer for action predictionshow more

My favorite paper this year: "Video models are zero-shot... learners and reasoners" It illustrates that video models show emergent visual reasoning at scale - they can solve vision tasks they weren't trained for. This may be the "GPT moment" for vision. Let's break it down 👇show more

See how Gemini 3 Flash and Vision-Language-Action (VLA) models... work together to teach a robot how to play the board game First Orchard. This project shows how to use Gemini as the “brain” for tracking game rules and state, while the VLA handles complex physical manipulations like picking and placing fruit 🍎show more

Artificial Intelligence (#AI) models that process and interpret visual... data are called large vision models. These models, like large language models, are trained on large amounts of data. #midjourney #dalle #stablediffusion (1/8) 🧵 ⤵️show more

You can now add AI features, powered by the... latest Claude models, to your Lovable apps. Here's a favorite app from our team that uses Opus’ visual identification and deep reasoning skills + Sonnet’s fast web search, retrieval and synthesis.show more

Long-horizon visual goals remain surprisingly hard for robot manipulation.... We introduce Act2Goal, a goal-conditioned policy that uses a visual world model to reason about progress toward a goal, and practice it autonomously in the real world.show more

We're very excited to introduce TAPNext: a model that... sets a new state-of-art for Tracking Any Point in videos, by formulating the task as Next Token Prediction. For more, see: 🧵show more

Ever watched someone solve a hard math problem? Their... first attempt is rarely perfect. They sketch ideas, cross things out, and try new angles. This process of exploration is key to human reasoning and our latest research formalizes this as Meta Chain-of-Thought (1/8) 🧵👇show more

MiniMax M3.1 Flash is now live on Venice. MiniMax’s... frontier model for coding, agentic work and visual reasoning, at 3x the speed of M3. Available anonymously.show more

New Moondream 2B release! 🌛 visual reasoning (!!) 🌜better... object detection 🌛 improved UI understanding 🌜40% faster text generationshow more

THE NEXT TOP VISUAL OF THIS GENERATION