google-deepmind / physics-IQ-benchmarkLinks
Benchmarking physical understanding in generative video models
☆219Updated 3 weeks ago
Alternatives and similar repositories for physics-IQ-benchmark
Users that are interested in physics-IQ-benchmark are comparing it to the libraries listed below
Sorting:
- ☆150Updated 10 months ago
- PhysGen: Rigid-Body Physics-Grounded Image-to-Video Generation (ECCV 2024)☆317Updated last year
- [ICML 2025] Official PyTorch Implementation of "History-Guided Video Diffusion"☆554Updated 4 months ago
- [NeurIPS 2025] WorldMem: Long-term Consistent World Simulation with Memory☆268Updated 3 weeks ago
- Code release for "PISA Experiments: Exploring Physics Post-Training for Video Diffusion Models by Watching Stuff Drop" (ICML 2025)☆46Updated 6 months ago
- A Video Tokenizer Evaluation Dataset☆138Updated 10 months ago
- A comprehensive list of papers investigating physical cognition in video generation, including papers, codes, and related websites.☆203Updated last month
- [ICCV 2025] GameFactory: Creating New Games with Generative Interactive Videos☆440Updated 8 months ago
- Official Implementation of Paper Transfer between Modalities with MetaQueries☆269Updated last month
- Video Diffusion Alignment via Reward Gradients. We improve a variety of video diffusion models such as VideoCrafter, OpenSora, ModelScope…☆303Updated 8 months ago
- Video Generation, Physical Commonsense, Semantic Adherence, VideoCon-Physics☆157Updated 6 months ago
- [ICML2025] The code and data of Paper: Towards World Simulator: Crafting Physical Commonsense-Based Benchmark for Video Generation☆134Updated last year
- [ICLR 2024] LLM-grounded Video Diffusion Models (LVD): official implementation for the LVD paper☆161Updated last year
- [CVPR2025] PyTorch-based reimplementation of CrossFlow, as proposed in 'Flowing from Words to Pixels: A Noise-Free Framework for Cross-Mo…☆318Updated 5 months ago
- Generative World Explorer☆159Updated 5 months ago
- Cosmos-Predict2 is a collection of general-purpose world foundation models for Physical AI that can be fine-tuned into customized world m…☆670Updated 3 weeks ago
- [ICCV 2025] Official repo for "GigaTok: Scaling Visual Tokenizers to 3 Billion Parameters for Autoregressive Image Generation"☆194Updated 4 months ago
- [NeurIPS 2025] The official repository of "Sekai: A Video Dataset towards World Exploration"☆181Updated 4 months ago
- ☆326Updated 3 months ago
- Official repo of paper "Reconstruction Alignment Improves Unified Multimodal Models". Unlocking the Massive Zero-shot Potential in Unifie…☆310Updated last month
- UniDisc: A discrete diffusion model for joint multimodal generation, enabling controllable and efficient text-image synthesis, editing, a…☆131Updated 7 months ago
- Code release for paper "Test-Time Training Done Right"☆318Updated 2 months ago
- Official implementation for WorldScore: A Unified Evaluation Benchmark for World Generation☆163Updated 3 months ago
- Adaptive Length Image Tokenization via Recurrent Allocation | How many tokens is an image worth ?☆137Updated 9 months ago
- ☆30Updated 5 months ago
- Physical laws underpin all existence, and harnessing them for generative modeling opens boundless possibilities for advancing science and…☆237Updated 7 months ago
- Cosmos-Predict2.5, the latest version of the Cosmos World Foundation Models (WFMs) family, specialized for simulating and predicting the …☆410Updated last week
- [ICML 2024] Compositional Image Decomposition with Diffusion Models☆51Updated last year
- Selftok: Discrete Visual Tokens of Autoregression, by Diffusion, and for Reasoning☆228Updated 5 months ago
- [ICLR 2025] OpenVid-1M: A Large-Scale High-Quality Dataset for Text-to-video Generation☆365Updated 5 months ago