Official implementation of Tuna-2: Pixel Embeddings Beat Vision Encoders for Unified Understanding and Generation

Reference code for the Meta-Harness paper.

[ICLR2026] Everything in Its Place: Benchmarking Spatial Intelligence of Text-to-Image Models

[ICLR 2026] Uni-CoT: Towards Unified Chain-of-Thought Reasoning Across Text and Vision

Official codebase for "Self Forcing: Bridging Training and Inference in Autoregressive Video Diffusion" (NeurIPS 2025 Spotlight)

Benchmarking physical understanding in generative video models

[ICLR 2026] "VTool-R1: VLMs Learn to Think with Images via Reinforcement Learning on Multimodal Tool Use"

EasyR1: An Efficient, Scalable, Multi-Modality RL Training Framework based on veRL

Long-RL: Scaling RL to Long Sequences (NeurIPS 2025)

Lets make video diffusion practical!

A framework for few-shot evaluation of language models.

Fully open data curation for reasoning models

Leaderboard Comparing LLM Performance at Producing Hallucinations when Summarizing Short Documents

verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework

One-for-All Multimodal Evaluation Toolkit Across Text, Image, Video, and Audio Tasks

[NeurIPS 2025] SpatialLM: Training Large Language Models for Structured Indoor Modeling

Explore the Multimodal “Aha Moment” on 2B Model

[CVPR 2025] EgoLife: Towards Egocentric Life Assistant

[ICLR'25] Reconstructive Visual Instruction Tuning

✨✨[NeurIPS 2025] VITA-1.5: Towards GPT-4o Level Real-Time Vision and Speech Interaction

The first behavioral foundation model to control a virtual physics-based humanoid agent for a wide range of whole-body tasks.

HunyuanVideo: A Systematic Framework For Large Video Generation Model

The repository provides code for running inference with the Meta Segment Anything Model 2 (SAM 2), links for downloading the trained model checkpoints, and example notebooks that show how to use th…

Allegro is a powerful text-to-video model that generates high-quality videos up to 6 seconds at 15 FPS and 720p resolution from simple text input.

PyTorch implementation of MAR+DiffLoss https://arxiv.org/abs/2406.11838