google-deepmind / physics-IQ-benchmarkLinks
Benchmarking physical understanding in generative video models
☆222Updated last month
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:
- ☆154Updated 11 months ago
- PhysGen: Rigid-Body Physics-Grounded Image-to-Video Generation (ECCV 2024)☆320Updated last year
- [ICML 2025] Official PyTorch Implementation of "History-Guided Video Diffusion"☆572Updated 5 months ago
- [NeurIPS 2025] WorldMem: Long-term Consistent World Simulation with Memory☆288Updated last week
- A comprehensive list of papers investigating physical cognition in video generation, including papers, codes, and related websites.☆218Updated 2 weeks ago
- Code release for "PISA Experiments: Exploring Physics Post-Training for Video Diffusion Models by Watching Stuff Drop" (ICML 2025)☆47Updated 7 months ago
- A Video Tokenizer Evaluation Dataset☆141Updated 11 months ago
- [ICCV 2025] GameFactory: Creating New Games with Generative Interactive Videos☆451Updated 8 months ago
- Video Diffusion Alignment via Reward Gradients. We improve a variety of video diffusion models such as VideoCrafter, OpenSora, ModelScope…☆304Updated 9 months ago
- Generative World Explorer☆163Updated 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…☆680Updated last month
- Video Generation, Physical Commonsense, Semantic Adherence, VideoCon-Physics☆159Updated 7 months ago
- [ICLR 2024] LLM-grounded Video Diffusion Models (LVD): official implementation for the LVD paper☆163Updated last year
- [ICML2025] The code and data of Paper: Towards World Simulator: Crafting Physical Commonsense-Based Benchmark for Video Generation☆142Updated last year
- Official Implementation of Paper Transfer between Modalities with MetaQueries☆274Updated 2 months ago
- [NeurIPS 2025] The official repository of "Sekai: A Video Dataset towards World Exploration"☆202Updated last week
- [CVPR2025] PyTorch-based reimplementation of CrossFlow, as proposed in 'Flowing from Words to Pixels: A Noise-Free Framework for Cross-Mo…☆324Updated 6 months ago
- Physical laws underpin all existence, and harnessing them for generative modeling opens boundless possibilities for advancing science and…☆245Updated 7 months ago
- Cosmos-Predict2.5, the latest version of the Cosmos World Foundation Models (WFMs) family, specialized for simulating and predicting the …☆499Updated last week
- (CVPR 2025 Highlight) The Scene Language: Representing Scenes with Programs, Words, and Embeddings☆248Updated 5 months ago
- Official implementation for WorldScore: A Unified Evaluation Benchmark for World Generation☆170Updated last week
- [ICML 2024] Compositional Image Decomposition with Diffusion Models☆51Updated last year
- Code release for paper "Test-Time Training Done Right"☆329Updated 3 weeks ago
- Official implementation of "Self-Improving Video Generation"☆76Updated 7 months ago
- [NeurIPS 2025] VideoREPA: Learning Physics for Video Generation through Relational Alignment with Foundation Models☆131Updated last month
- ☆343Updated 4 months ago
- [CVPR 2025] Science-T2I: Addressing Scientific Illusions in Image Synthesis☆62Updated 7 months ago
- [ICCV 2025] Official repo for "GigaTok: Scaling Visual Tokenizers to 3 Billion Parameters for Autoregressive Image Generation"☆194Updated this week
- Adaptive Length Image Tokenization via Recurrent Allocation | How many tokens is an image worth ?☆138Updated 10 months ago
- Official repository of "GoT: Unleashing Reasoning Capability of Multimodal Large Language Model for Visual Generation and Editing"☆299Updated 2 months ago