vision-x-nyu / pisa-experimentsLinks
Code release for "PISA Experiments: Exploring Physics Post-Training for Video Diffusion Models by Watching Stuff Drop" (ICML 2025)
☆39Updated 3 months ago
Alternatives and similar repositories for pisa-experiments
Users that are interested in pisa-experiments are comparing it to the libraries listed below
Sorting:
- Official Implementation of Paper Transfer between Modalities with MetaQueries☆219Updated last month
- A list of works on video generation towards world model☆162Updated 2 weeks ago
- [ICML2025] The code and data of Paper: Towards World Simulator: Crafting Physical Commonsense-Based Benchmark for Video Generation☆117Updated 10 months ago
- Official Pytorch implementation for LARP: Tokenizing Videos with a Learned Autoregressive Generative Prior (ICLR 2025 Oral).☆88Updated 6 months ago
- [CVPR 2025 (Oral)] Open implementation of "RandAR"☆188Updated last month
- [Neurips 2024] Video Diffusion Models are Training-free Motion Interpreter and Controller☆45Updated 3 weeks ago
- Video Generation, Physical Commonsense, Semantic Adherence, VideoCon-Physics☆143Updated 3 months ago
- Official PyTorch Implementation of "Latent Denoising Makes Good Visual Tokenizers"☆120Updated last month
- [ICCV2025]Code Release of Harmonizing Visual Representations for Unified Multimodal Understanding and Generation☆155Updated 3 months ago
- PyTorch implementation of DiffMoE, TC-DiT, EC-DiT and Dense DiT☆122Updated 4 months ago
- Code for: "Long-Context Autoregressive Video Modeling with Next-Frame Prediction"☆241Updated 4 months ago
- VideoREPA: Learning Physics for Video Generation through Relational Alignment with Foundation Models☆56Updated 2 months ago
- [ArXiv 2025] WorldMem: Long-term Consistent World Simulation with Memory☆207Updated 2 weeks ago
- A comprehensive list of papers investigating physical cognition in video generation, including papers, codes, and related websites.☆159Updated last week
- A survey for visual generation alignment☆51Updated 2 weeks ago
- ☆136Updated 7 months ago
- WISE: A World Knowledge-Informed Semantic Evaluation for Text-to-Image Generation☆143Updated last week
- [CVPR 2025, Highlight] The official implementation of the paper "Unleashing In-context Learning of Autoregressive Models for Few-shot Ima…☆23Updated 2 months ago
- Selftok: Discrete Visual Tokens of Autoregression, by Diffusion, and for Reasoning☆206Updated 2 months ago
- ☆38Updated 3 weeks ago
- “FlowAR: Scale-wise Autoregressive Image Generation Meets Flow Matching” FlowAR employs a simplest scale design and is compatible with an…☆145Updated 3 months ago
- official code repo of CVPR 2025 paper PhyT2V: LLM-Guided Iterative Self-Refinement for Physics-Grounded Text-to-Video Generation☆43Updated 3 weeks ago
- ☆30Updated 8 months ago
- ☆33Updated 3 weeks ago
- [CVPR 2024] On the Content Bias in Fréchet Video Distance☆123Updated 10 months ago
- ☆148Updated 2 months ago
- Official Implementation of VideoGen-of-Thought: Step-by-step generating multi-shot video with minimal manual intervention☆39Updated 4 months ago
- FQGAN: Factorized Visual Tokenization and Generation☆52Updated 4 months ago
- ☆27Updated 2 months ago
- [ICCV 2025] Official repo for "GigaTok: Scaling Visual Tokenizers to 3 Billion Parameters for Autoregressive Image Generation"☆177Updated 2 months ago