Stars
The official implementation of "Recast the Past: Stable Long Video Generation with Full Context Memory"
The offical repo for "Dream-RSI: Recursive Self-Improvement through Evolving Worlds"
FLUX 3 Action: open weights 7B world action model from Black Forest Labs. Train, fine-tune and run action prediction for robots (DROID, SO-101), simulators and games.
[CVPR 2026 Highlight] High-Quality Text-to-Video Generation with Alpha Channel
Official implementation of Hidden Decoding at Scale, scaling latent computation per token through multiple hidden streams while keeping the Transformer backbone fixed.
GPT-Policy: In-Context Robot Learning with VLM Agents
GPT-6 Astra for embodied AI and robotics.
DeepSeek Harness: Everything is a Plugin.
Robot-agent harness with a CLI and local Web console for LIBERO short evaluation
ReWorld: An Interactive World Model with Long-Horizon Memory
This is a repo to track the latest autoregressive visual generation papers.
Sekai2: From World Exploration to Interactive World Modeling
On-Policy Self-Distillation for Post-Training Few-Step Autoregressive Video Generators
ICLR'26: TTOM: Test-Time Optimization and Memorization for Compositional Video Generation
[ICML 2026] The official implementation of paper "Unified Multimodal Autoregressive Modeling with Shared Context—Visual Tokenizer is Key to Unification"
Official codebase for "Self Forcing: Bridging Training and Inference in Autoregressive Video Diffusion" (NeurIPS 2025 Spotlight)
code for "Diffusion Forcing: Next-token Prediction Meets Full-Sequence Diffusion"
Code for RepWAM: World Action Modeling with Representation Visual-Action Tokenizers
[NeurIPS 2026] Next Forcing: World Action Modeling with Multi-Chunk Prediction (MCP)
ARM: An AutoRegressive Large Multimodal Model with Discrete Representations
[NeurIPS-26] Official repository of "IDEAL: In-DEpth ALignment Makes A Discrete Representation AutoEncoder"
[CVPR 2026 Best Paper Finalist & NeurIPS 2026]
[SIGGRAPH Asia 2026] DiffusionOPD: A Unified Perspective of On-Policy Distillation in Diffusion Models