{"total":70,"rows":[{"id":"2603.19312","title":"LeWorldModel: Stable End-to-End Joint-Embedding Predictive Architecture from Pixels","created":"2026-03-13","cited_by_count":273,"area":"wm"},{"id":"2509.20328","title":"Video models are zero-shot learners and reasoners","created":"2025-09-24","cited_by_count":220,"area":"lr"},{"id":"2511.04670","title":"Cambrian-S: Towards Spatial Supersensing in Video","created":"2025-11-06","cited_by_count":134,"area":"wm"},{"id":"2603.14482","title":"V-JEPA 2.1: Unlocking Dense Features in Video Self-Supervised Learning","created":"2026-03-15","cited_by_count":117,"area":null},{"id":"2505.23656","title":"VideoREPA: Learning Physics for Video Generation through Relational Alignment with Foundation Models","created":"2025-05-29","cited_by_count":98,"area":"diffusion"},{"id":"2507.19468","title":"Back to the Features: DINO as a Foundation for Video World Models","created":"2025-07-25","cited_by_count":58,"area":"wm"},{"id":"2506.09849","title":"IntPhys 2: Benchmarking Intuitive Physics Understanding In Complex Synthetic Environments","created":"2025-06-11","cited_by_count":52,"area":null},{"id":"2509.21309","title":"NewtonGen: Physics-Consistent and Controllable Text-to-Video Generation via Neural Newtonian Dynamics","created":"2025-09-25","cited_by_count":41,"area":null},{"id":"2601.10553","title":"Inference-time Physics Alignment of Video Generative Models with Latent World Models","created":"2026-01-15","cited_by_count":37,"area":"wm"},{"id":"2506.09987","title":"A Shortcut-aware Video-QA Benchmark for Physical Understanding via Minimal Video Pairs","created":"2025-06-11","cited_by_count":30,"area":"lr"},{"id":"2512.00425","title":"What about gravity in video generation? Post-Training Newton's Laws with Verifiable Rewards","created":"2025-11-29","cited_by_count":25,"area":"diffusion"},{"id":"2602.11832","title":"JEPA-VLA: Video Predictive Embedding is Needed for VLA Models","created":"2026-02-12","cited_by_count":24,"area":"mllm"},{"id":"2602.07050","title":"Interpreting Physics in Video World Models","created":"2026-02-04","cited_by_count":22,"area":"wm"},{"id":"2506.04363","title":"WorldPrediction: A Benchmark for High-level World Modeling and Long-horizon Procedural Planning","created":"2025-06-04","cited_by_count":20,"area":"wm"},{"id":"2510.11512","title":"LikePhys: Evaluating Intuitive Physics Understanding in Video Diffusion Models via Likelihood Preference","created":"2025-10-13","cited_by_count":16,"area":"diffusion"},{"id":"2503.20822","title":"Synthetic Video Enhances Physical Fidelity in Video Synthesis","created":"2025-03-26","cited_by_count":15,"area":null},{"id":"2602.03604","title":"A Lightweight Library for Energy-Based Joint-Embedding Predictive Architectures","created":"2026-02-03","cited_by_count":14,"area":"wm"},{"id":"2509.24317","title":"Rethinking JEPA: Compute-Efficient Video SSL with Frozen Teachers","created":"2025-09-29","cited_by_count":12,"area":null},{"id":"2604.08503","title":"Phantom: Physics-Infused Video Generation via Joint Modeling of Visual and Latent Physical Dynamics","created":"2026-04-09","cited_by_count":12,"area":null},{"id":"2603.15381","title":"Why AI systems don't learn and what to do about it: Lessons on autonomous learning from cognitive science","created":"2026-03-16","cited_by_count":11,"area":null},{"id":"2604.14816","title":"NTIRE 2026 Challenge on Video Saliency Prediction: Methods and Results","created":"2026-04-16","cited_by_count":10,"area":null},{"id":"2605.15725","title":"DiLA: Disentangled Latent Action World Models","created":"2026-05-15","cited_by_count":10,"area":"wm"},{"id":"2606.05328","title":"The Invisible Hand of Physics: When Video Diffusion Models Know More Than They Show","created":"2026-06-03","cited_by_count":8,"area":"diffusion"},{"id":"2505.03176","title":"seq-JEPA: Autoregressive Predictive Learning of Invariant-Equivariant World Models","created":"2025-05-06","cited_by_count":7,"area":"wm"},{"id":"2512.00762","title":"Seeing the Wind from a Falling Leaf","created":"2025-11-30","cited_by_count":7,"area":null},{"id":"2602.13294","title":"VisPhyWorld: Probing Physical Reasoning via Code-Driven Video Reconstruction","created":"2026-02-09","cited_by_count":7,"area":"lr"},{"id":"2508.01835","title":"Diffusion-based 3D Hand Motion Recovery with Intuitive Physics","created":"2025-08-03","cited_by_count":5,"area":null},{"id":"2512.02016","title":"Objects in Generated Videos Are Slower Than They Appear: Models Suffer Sub-Earth Gravity and Don't Know Galileo's Principle...for now","created":"2025-12-01","cited_by_count":5,"area":"wm"},{"id":"2512.03350","title":"SeeU: Seeing the Unseen World via 4D Dynamics-aware Generation","created":"2025-12-03","cited_by_count":5,"area":null},{"id":"2506.20134","title":"From 2D to 3D Cognition: A Brief Survey of General World Models","created":"2025-06-25","cited_by_count":4,"area":"wm"},{"id":"2601.15533","title":"From Generative Engines to Actionable Simulators: The Imperative of Physical Grounding in World Models","created":"2026-01-21","cited_by_count":4,"area":"wm"},{"id":"2605.23878","title":"LaMo: Self-Supervised Latent Motion Priors for Physical Realism in Video Generation","created":"2026-05-22","cited_by_count":4,"area":"diffusion"},{"id":"2503.02552","title":"World Models for Anomaly Detection during Model-Based Reinforcement Learning Inference","created":"2025-03-04","cited_by_count":3,"area":"wm"},{"id":"2505.11719","title":"Zero-Shot Visual Generalization in Robot Manipulation","created":"2025-05-16","cited_by_count":3,"area":"offlinerl"},{"id":"2507.16572","title":"Pixels to Principles: Probing Intuitive Physics Understanding in Multimodal Language Models","created":"2025-07-22","cited_by_count":3,"area":"mllm"},{"id":"2604.21192","title":"How VLAs (Really) Work In Open-World Environments","created":"2026-04-23","cited_by_count":3,"area":"vla"},{"id":"2605.15618","title":"Latent Video Prediction Learns Better World Models","created":"2026-05-15","cited_by_count":3,"area":"wm"},{"id":"2605.30346","title":"YoCausal: How Far is Video Generation from World Model? A Causality Perspective","created":"2026-05-28","cited_by_count":3,"area":"wm"},{"id":"2606.09646","title":"How Do Video Foundation Models Encode Intuitive Physics? Probing Across Pretraining Paradigms","created":"2026-06-08","cited_by_count":3,"area":null},{"id":"2606.20707","title":"GEOPHYS: The Geometry of Physical Plausibility","created":"2026-06-15","cited_by_count":3,"area":null},{"id":"2607.27017","title":"What Can Latent World Models Know? Physical Parameter Identifiability in Multimodal Predictive Representations","created":"2026-07-29","cited_by_count":3,"area":"wm"},{"id":"2509.12263","title":"InPhyRe Discovers: Large Multimodal Models Struggle in Inductive Physical Reasoning","created":"2025-09-12","cited_by_count":2,"area":"mllm"},{"id":"2608.15156","title":"Low-Rank Dynamics-Effective Latent Carriers for Counterfactual Rollout in Learned World Models","created":"2026-08-15","cited_by_count":2,"area":"wm"},{"id":"2602.02381","title":"Self-Supervised Learning from Structural Invariance","created":"2026-02-02","cited_by_count":1,"area":null},{"id":"2603.14294","title":"Seeking Physics in Diffusion Noise","created":"2026-03-15","cited_by_count":1,"area":"diffusion"},{"id":"2604.03266","title":"Emergent Compositional Communication for Latent World Properties","created":"2026-03-18","cited_by_count":1,"area":null},{"id":"2607.16401","title":"Apple-$\\pi$: Benchmarking Thinking with Video Towards Law-Grounded Physical Intelligence","created":"2026-07-17","cited_by_count":1,"area":"wm"},{"id":"2607.16602","title":"PAVXploreRL: Physical-Action-Visual World Model Reinforcement Learning with Action Exploration","created":"2026-07-18","cited_by_count":1,"area":"wm"},{"id":"2609.10464","title":"Semigroup-JEPA: Latent Dynamics Consistency for Zero-Shot Physics Generalization","created":"2026-09-09","cited_by_count":1,"area":"wm"},{"id":"2609.33347","title":"MultiEcho: An Experimental Science of Learned Worlds","created":"2026-09-27","cited_by_count":1,"area":"wm"},{"id":"2512.00365","title":"Towards aligned body representations in vision models","created":"2025-11-29","cited_by_count":0,"area":null},{"id":"2512.06232","title":"Opinion: Learning Intuitive Physics May Require More than Visual Data","created":"2025-12-06","cited_by_count":0,"area":null},{"id":"2602.10009","title":"Discovering High Level Patterns from Simulation Traces","created":"2026-02-10","cited_by_count":0,"area":null},{"id":"2604.03302","title":"Beyond Static Vision: Scene Dynamic Field Unlocks Intuitive Physics Understanding in Multi-modal Large Language Models","created":"2026-03-30","cited_by_count":0,"area":"mllm"},{"id":"2605.15466","title":"Entity-Centric World Models: Interaction-Aware Masking for Causal Video Prediction","created":"2026-05-14","cited_by_count":0,"area":"wm"},{"id":"2606.05497","title":"LEVANTE-bench: Multi-Scale Comparison of VLMs to Children Using Cognitive Tasks (or, \"Is Your VLM Smarter Than a 5th Grader?\")","created":"2026-06-03","cited_by_count":0,"area":"mllm"},{"id":"2606.26410","title":"Neural Voxel Dynamics: Learning Volumetric Feature Advection for 3D Physics in V-JEPA Latent Space","created":"2026-06-24","cited_by_count":0,"area":null},{"id":"2606.26969","title":"Einstein World Models","created":"2026-06-25","cited_by_count":0,"area":"wm"},{"id":"2607.16274","title":"The JEPA Predictor: A Transferable Operator for Occluded Feature Completion","created":"2026-07-08","cited_by_count":0,"area":null},{"id":"2609.01551","title":"What, Where, and How: Probing Spatiotemporal Representations in Video Foundation Models","created":"2026-09-01","cited_by_count":0,"area":null},{"id":"2609.09250","title":"No Free Checker: A Survey of Verifiers for Robot Policies","created":"2026-09-08","cited_by_count":0,"area":null},{"id":"2609.22788","title":"Human-Level Accuracy, Non-Human Strategies: Revealing Model-Human Divergence in Video Physical Reasoning","created":"2026-09-19","cited_by_count":0,"area":null},{"id":"2609.34085","title":"AD-E2E-JEPA: A Joint-Embedding Predictive Architecture For End-to-End Autonomous Driving","created":"2026-09-28","cited_by_count":0,"area":"wm"},{"id":"2609.39235","title":"The Planning Limits of Latent World Models","created":"2026-09-30","cited_by_count":0,"area":"wm"},{"id":"2610.01039","title":"Bootstrapping Video Interaction Generation with Synthetic State Transitions","created":"2026-10-01","cited_by_count":0,"area":null},{"id":"2610.01947","title":"Latent JEPA: Abstract Future Prediction for Latent Reasoning in Chemistry","created":"2026-10-01","cited_by_count":0,"area":"lr"},{"id":"2610.03374","title":"EVEWorld: Physical Evolution Supervision for Embodied World Models","created":"2026-10-02","cited_by_count":0,"area":"wm"},{"id":"2610.07355","title":"Tracking Is Not Permanence: What Video World Models Keep of a Hidden Object","created":"2026-10-05","cited_by_count":0,"area":"wm"},{"id":"2610.16365","title":"World Models Need a Physical Registry: Learning Internal Predictive States for Physically Plausible World Models","created":"2026-10-12","cited_by_count":0,"area":"wm"},{"id":"2610.19375","title":"One-Step Prediction Fidelity Is a Poor Proxy for Planning Performance in JEPA World Models","created":"2026-10-14","cited_by_count":0,"area":"wm"}],"next_cursor":null}