| TrajAgent: An Agent Framework for Unified Trajectory Modelling | Oct 27, 2024 | Future predictionLanguage Modeling | CodeCode Available | 1 |
| MMWorld: Towards Multi-discipline Multi-faceted World Model Evaluation in Videos | Jun 12, 2024 | counterfactualFuture prediction | CodeCode Available | 1 |
| Compositional 4D Dynamic Scenes Understanding with Physics Priors for Video Question Answering | Jun 2, 2024 | counterfactualCounterfactual Reasoning | CodeCode Available | 1 |
| Scaling Lifelong Multi-Agent Path Finding to More Realistic Settings: Research Challenges and Opportunities | Apr 24, 2024 | Future predictionMulti-Agent Path Finding | CodeCode Available | 1 |
| DeepLag: Discovering Deep Lagrangian Dynamics for Intuitive Fluid Prediction | Feb 4, 2024 | Future predictionPrediction | CodeCode Available | 1 |
| HelmFluid: Learning Helmholtz Dynamics for Interpretable Fluid Prediction | Oct 16, 2023 | Future predictionPrediction | CodeCode Available | 1 |
| Video Diffusion Models with Local-Global Context Guidance | Jun 5, 2023 | Future predictionPrediction | CodeCode Available | 1 |
| Neural Foundations of Mental Simulation: Future Prediction of Latent Representations on Dynamic Scenes | May 19, 2023 | Future prediction | CodeCode Available | 1 |
| Rethinking Learning Approaches for Long-Term Action Anticipation | Oct 20, 2022 | Action AnticipationFuture prediction | CodeCode Available | 1 |
| EgoTaskQA: Understanding Human Tasks in Egocentric Videos | Oct 8, 2022 | Action Localizationcounterfactual | CodeCode Available | 1 |
