Toward Ambulatory Vision: Learning Visually-Grounded Active View Selection

Vision Bridge Transformer at Scale

[NeurIPS 2024] Depth Anything V2. A More Capable Foundation Model for Monocular Depth Estimation

G1: Bootstrapping Perception and Reasoning Abilities of Vision-Language Model via Reinforcement Learning

Witness the aha moment of VLM with less than $3.

[NIPS'25 Spotlight] Mulberry, an o1-like Reasoning and Reflection MLLM Implemented via Collective MCTS

A friendly programming language from the future

Stay in flow while building with AI

A step-by-step reasoning framework for 3D scene understanding

R1-VL: Learning to Reason with Multimodal Large Language Models via Step-wise Group Relative Policy Optimization

OS-Harm: A Benchmark for Measuring Safety of Computer Use Agents [NeurIPS 2025 Spotlight]

Nav-R1: Reasoning and Navigation in Embodied Scenes

Official repo of "Chain-of-Visual-Thought: Teaching VLMs to See and Think Better with Continuous Visual Tokens"

Official PyTorch implementation of "Aligned but Stereotypical? The Hidden Influence of System Prompts on Social Bias in LVLM-Based Text-to-Image Models"

[ECCV 2024 Oral] Code for paper: An Image is Worth 1/2 Tokens After Layer 2: Plug-and-Play Inference Acceleration for Large Vision-Language Models

[NeurIPS 2025] We propose a first RL-based personalized image captioning framework with well-defined verifiable rewards.

Code for the paper "GRPO is Secretly a Process Reward Model": https://arxiv.org/abs/2509.21154

SAM 3D Objects

The repository provides code for running inference and finetuning with the Meta Segment Anything Model 3 (SAM 3), links for downloading the trained model checkpoints, and example notebooks that sho…

[Neurips'24 Spotlight] Visual CoT: Advancing Multi-Modal Language Models with a Comprehensive Dataset and Benchmark for Chain-of-Thought Reasoning

Codes for Visual Sketchpad: Sketching as a Visual Chain of Thought for Multimodal Language Models

Think with 3D: Geometric Imagination Grounded Spatial Reasoning from Limited Views

Official repository for the A-OKVQA dataset

Code for 3D-LLM: Injecting the 3D World into Large Language Models

[CVPR 2023] Code for "3D Concept Learning and Reasoning from Multi-View Images"