[ICLR2026] LikePhys, a training-free method that evaluates intuitive physics in video diffusion models by distinguishing physically valid and impossible videos using the denoising objective as an ELBO-based likelihood surrogate on a curated dataset of valid-invalid pairs.
☆19Mar 5, 2026Updated 7 months ago
Alternatives and similar repositories for LikePhys
Users that are interested in LikePhys are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- GeoPhys: The Geometry of Physical Plausibility (NeurIPS2026)☆34Oct 13, 2026Updated 2 weeks ago
- [CVPR 2026 Oral] SenCache: Accelerating Diffusion Model Inference via Sensitivity-Aware Caching☆30Jun 5, 2026Updated 4 months ago
- Official Implementation of Motion-JEPA: Preventing Temporal Feature Collapse by Capturing Visual Changes in Latent Space☆23Oct 23, 2026Updated last week
- [CVPR 2026 Highlight] Leveraging latent world model's physics understanding to improve the physics plausibility of video generation☆106Jul 17, 2026Updated 3 months ago
- A comprehensive list of papers investigating physical cognition in video generation, including papers, codes, and related websites.☆331Jun 23, 2026Updated 4 months ago
- 1-Click AI Models by DigitalOcean Gradient • AdDeploy popular AI models on DigitalOcean Gradient GPU virtual machines with just a single click. Zero configuration with optimized deployments.
- Code release for "PISA Experiments: Exploring Physics Post-Training for Video Diffusion Models by Watching Stuff Drop" (ICML 2025)☆61May 8, 2025Updated last year
- ResearchDoom fork of the Chocolate Doom engine.☆16Aug 10, 2026Updated 2 months ago
- ☆18Updated this week
- 😂😂😂Official Implementation for ICCV 2023 paper: OxfordTVG-HIC: Can Machine Make Humorous Captions from Images?☆11Feb 23, 2024Updated 2 years ago
- Official Repo for the VideoVerse☆15Mar 29, 2026Updated 7 months ago
- ☆13Feb 3, 2020Updated 6 years ago
- Official repository of PhysMaster: Mastering Physical Representation for Video Generation via Reinforcement Learning☆57Oct 16, 2025Updated last year
- Benchmarking physical understanding in generative video models☆385Oct 20, 2026Updated last week
- [ICCV'25] Radial Cross-Modal embeddings☆11Apr 27, 2026Updated 6 months ago
- GPU virtual machines on DigitalOcean Gradient AI • AdGet to production fast with high-performance AMD and NVIDIA GPUs you can spin up in seconds. The definition of operational simplicity.
- Examples and exercises for B16 - Algorithms.☆14Jul 30, 2026Updated 3 months ago
- HiCache: Hermite Polynomial-based Feature Cache for diffusion inference☆15Sep 7, 2026Updated last month
- SANE is a zero-shot inference pipeline for improving diffusion models with LLM reasoning.☆12Aug 1, 2025Updated last year
- ☆15Jun 21, 2025Updated last year
- [Technical Report] Multi-Stream Attention Residuals☆39Oct 12, 2026Updated 2 weeks ago
- A comprehensive and open-source reproduction of Jev.☆23Sep 29, 2026Updated last month
- Original code base for On Pretraining Data Diversity for Self-Supervised Learning☆14Dec 30, 2024Updated last year
- Code for Galgali et al, 2023☆15Jan 11, 2023Updated 3 years ago
- code for the paper, "flexible multitask computation in recurrent networks utilizes shared dynamical motifs"☆13Mar 2, 2025Updated last year
- End-to-end encrypted email - Proton Mail • AdSpecial offer: 40% Off Yearly / 80% Off First Month. All Proton services are open source and independently audited for security.
- ☆13Mar 12, 2025Updated last year
- Official Repository for "AdaMMS: Model Merging for Heterogeneous Multimodal Large Language Models with Unsupervised Coefficient Optimizat…☆15Apr 7, 2025Updated last year
- Self-Supervised Learning of Structured Dynamics from Videos☆22Jul 24, 2026Updated 3 months ago
- ☆16Oct 10, 2026Updated 3 weeks ago
- ☆26Sep 4, 2025Updated last year
- We implement MADDPG in a congestion env, and compare with several control groups to highlight the performance of MADDPG☆11Jul 14, 2021Updated 5 years ago
- [CVPR 2026] IOMM: Fast Pre-training of Unified Multimodal Models without Text-Image Pairs☆26Apr 11, 2026Updated 6 months ago
- Videoshop: Localized Semantic Video Editing with Noise-Extrapolated Diffusion Inversion☆45Aug 1, 2024Updated 2 years ago
- ☆50Jul 29, 2025Updated last year
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- [EMNLP 2026] An official Implementation of "Beyond the Current Observation: Evaluating Multimodal Large Language Models in Controllable N…☆42Updated this week
- The N=1 Guide to Grad School☆16May 13, 2013Updated 13 years ago
- ☆24Jun 22, 2023Updated 3 years ago
- ☆28Jun 3, 2022Updated 4 years ago
- Repo for "Physion: Evaluating Physical Prediction from Vision in Humans and Machines", presented at NeurIPS 2021 (Datasets & Benchmarks t…☆97Feb 9, 2023Updated 3 years ago
- The source code of FedDis☆21Jun 3, 2022Updated 4 years ago
- Open resource exchange platform for non-human primate neuroimaging☆22Oct 19, 2026Updated last week