MultiEcho: An Experimental Science of Learned Worlds
cs.LG
Submitted: 2026-09-27
Updated: 2026-09-27
Terminology
Sources
- V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning
- VideoPhy: Evaluating Physical Commonsense for Video Generation
- VideoPhy-2: A Challenging Action-Centric Physical Commonsense Evaluation in Video Generation
- CoPhy: Counterfactual Learning of Physical Dynamics
- Physion: Evaluating Physical Prediction from Vision in Humans and Machines
- Unifying (Machine) Vision via Counterfactual World Modeling
- CRONOS: Benchmarking Counterfactual Physical Consistency in Video Models
- IntPhys 2: Benchmarking Intuitive Physics Understanding In Complex Synthetic Environments
- Discovering Symbolic Models from Deep Learning with Inductive Biases
- Sobolev Training for Neural Networks
- CausalVQA: A Physically Grounded Causal Reasoning Benchmark for Video Models
- Intuitive physics understanding emerges from self-supervised pretraining on natural videos
- Causal Abstractions of Neural Networks
- "PhyWorldBench": A Comprehensive Evaluation of Physical Realism in Text-to-Video Models
- Recurrent World Models Facilitate Policy Evolution
- MMWorld: Towards Multi-discipline Multi-faceted World Model Evaluation in Videos
- PhysEditWorld: A Large-Scale Dataset Toward Physics-Editable World Models
- The Observer Effect in World Models: Invasive Adaptation Corrupts Latent Physics
- Filtered-CoPhy: Unsupervised Learning of Counterfactual Physics in Pixel Space
- Interpreting Physics in Video World Models
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: Local-Consistency Optimisation for Bayesian Neural Networks
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks