vision-x-nyu / pisa-experimentsLinks
Code release for "PISA Experiments: Exploring Physics Post-Training for Video Diffusion Models by Watching Stuff Drop" (ICML 2025)
☆32Updated 3 weeks ago
Alternatives and similar repositories for pisa-experiments
Users that are interested in pisa-experiments are comparing it to the libraries listed below
Sorting:
- Video Generation, Physical Commonsense, Semantic Adherence, VideoCon-Physics☆106Updated last month
- A comprehensive list of papers investigating physical cognition in video generation, including papers, codes, and related websites.☆106Updated last week
- ☆129Updated 5 months ago
- Diffusion Powers Video Tokenizer for Comprehension and Generation (CVPR 2025)☆68Updated 3 months ago
- A list of works on video generation towards world model☆101Updated last week
- Official Pytorch implementation for LARP: Tokenizing Videos with a Learned Autoregressive Generative Prior (ICLR 2025 Oral).☆71Updated 3 months ago
- ElasticTok: Adaptive Tokenization for Image and Video☆69Updated 7 months ago
- [CVPR 2025] Science-T2I: Addressing Scientific Illusions in Image Synthesis☆55Updated last month
- [Neurips 2024] Video Diffusion Models are Training-free Motion Interpreter and Controller☆42Updated last month
- [ICLR 2024] Seer: Language Instructed Video Prediction with Latent Diffusion Models☆33Updated last year
- [CVPR 25] A framework named B^2-DiffuRL for RL-based diffusion model fine-tuning.☆29Updated 2 months ago
- Codes accompanying the paper "Toward Guidance-Free AR Visual Generation via Condition Contrastive Alignment"☆32Updated 3 months ago
- [arXiv: 2502.05178] QLIP: Text-Aligned Visual Tokenization Unifies Auto-Regressive Multimodal Understanding and Generation☆74Updated 3 months ago
- [ICML2025] The code and data of Paper: Towards World Simulator: Crafting Physical Commonsense-Based Benchmark for Video Generation☆107Updated 7 months ago
- Code Release of Harmonizing Visual Representations for Unified Multimodal Understanding and Generation☆117Updated 2 weeks ago
- [CVPR 2024] On the Content Bias in Fréchet Video Distance☆113Updated 8 months ago
- Official implementation for WorldScore: A Unified Evaluation Benchmark for World Generation☆105Updated last month
- PyTorch implementation of DiffMoE, TC-DiT, EC-DiT and Dense DiT☆98Updated last month
- Code release for NeurIPS 2023 paper SlotDiffusion: Object-centric Learning with Diffusion Models☆87Updated last year
- Seeing from Another Perspective: Evaluating Multi-View Understanding in MLLMs☆38Updated 2 weeks ago
- ☆50Updated 5 months ago
- [ICML 2024] Compositional Image Decomposition with Diffusion Models☆50Updated 10 months ago
- FQGAN: Factorized Visual Tokenization and Generation☆50Updated 2 months ago
- A collection of vision foundation models unifying understanding and generation.☆55Updated 5 months ago
- EgoVid-5M: A Large-Scale Video-Action Dataset for Egocentric Video Generation☆104Updated 6 months ago
- official repo for "VideoScore: Building Automatic Metrics to Simulate Fine-grained Human Feedback for Video Generation" [EMNLP2024]☆88Updated 3 months ago
- Selftok: Discrete Visual Tokens of Autoregression, by Diffusion, and for Reasoning☆112Updated this week
- [NeurIPS 2024 D&B Track] Official Repo for "LVD-2M: A Long-take Video Dataset with Temporally Dense Captions"☆59Updated 7 months ago
- Adaptive Length Image Tokenization via Recurrent Allocation | How many tokens is an image worth ?☆120Updated 3 months ago
- Empowering Unified MLLM with Multi-granular Visual Generation☆124Updated 4 months ago