{"total":53,"rows":[{"id":"2505.05108","title":"Multi-agent Embodied AI: Advances and Future Directions","created":"2025-05-08","cited_by_count":36,"area":null},{"id":"2510.07550","title":"TRAVL: A Recipe for Making Video-Language Models Better Judges of Physics Implausibility","created":"2025-10-08","cited_by_count":18,"area":null},{"id":"2603.19607","title":"Physion-Eval: Evaluating Physical Realism in Generated Video via Human Reasoning","created":"2026-03-20","cited_by_count":14,"area":null},{"id":"2502.16435","title":"Human Cognitive Benchmarks Reveal Foundational Visual Gaps in MLLMs","created":"2025-02-23","cited_by_count":13,"area":null},{"id":"2502.20490","title":"EgoNormia: Benchmarking Physical Social Norm Understanding","created":"2025-02-27","cited_by_count":13,"area":null},{"id":"2509.08757","title":"SocialNav-SUB: Benchmarking VLMs for Scene Understanding in Social Robot Navigation","created":"2025-09-10","cited_by_count":10,"area":null},{"id":"2604.02296","title":"VOID: Video Object and Interaction Deletion","created":"2026-04-02","cited_by_count":9,"area":null},{"id":"2604.09415","title":"PhysInOne: Visual Physics Learning and Reasoning in One Suite","created":"2026-04-10","cited_by_count":9,"area":null},{"id":"2509.22970","title":"Robot Learning from Any Images","created":"2025-09-26","cited_by_count":7,"area":null},{"id":"2512.00762","title":"Seeing the Wind from a Falling Leaf","created":"2025-11-30","cited_by_count":7,"area":null},{"id":"2510.02311","title":"Inferring Dynamic Physical Properties from Video Foundation Models","created":"2025-10-02","cited_by_count":6,"area":null},{"id":"2602.00148","title":"Learning Physics-Grounded 4D Dynamics with Neural Gaussian Force Fields","created":"2026-01-29","cited_by_count":6,"area":null},{"id":"2602.07064","title":"OmniFysics: Towards Physical Intelligence Evolution via Omni-Modal Signal Processing and Network Optimization","created":"2026-02-05","cited_by_count":5,"area":null},{"id":"2512.04578","title":"LexGenius: An Expert-Level Benchmark for Large Language Models in Legal General Intelligence","created":"2025-12-04","cited_by_count":4,"area":null},{"id":"2602.19372","title":"Seeing Farther and Smarter: Value-Guided Multi-Path Reflection for VLM Policy Optimization","created":"2026-02-22","cited_by_count":4,"area":null},{"id":"2508.12668","title":"WP-CLIP: Leveraging CLIP to Predict W\\\"olfflin's Principles in Visual Art","created":"2025-08-18","cited_by_count":3,"area":null},{"id":"2605.14269","title":"PhyMotion: Structured 3D Motion Reward for Physics-Grounded Human Video Generation","created":"2026-05-14","cited_by_count":3,"area":null},{"id":"2605.20576","title":"$\\Delta$ynamics: Language-Based Representation for Inferring Rigid-Body Dynamics From Videos","created":"2026-05-20","cited_by_count":3,"area":null},{"id":"2610.03715","title":"4DCodeBench: Benchmarking Agents on Inverse Graphics of Dynamic Scenes","created":"2026-10-02","cited_by_count":3,"area":null},{"id":"2511.17649","title":"SWITCH: Benchmarking Modeling and Handling of Tangible Interfaces in Long-horizon Embodied Scenarios","created":"2025-11-20","cited_by_count":2,"area":null},{"id":"2512.01816","title":"Envision: Benchmarking Unified Understanding & Generation for Causal World Process Insights","created":"2025-12-01","cited_by_count":2,"area":null},{"id":"2605.30339","title":"Benchmarking Single-Factor Physical Video-to-Audio Generation","created":"2026-05-28","cited_by_count":2,"area":null},{"id":"2606.25306","title":"Physics Question Scene Graph: Fine-grained Evaluation of Physical Plausibility in Text-to-Video Generation","created":"2026-06-24","cited_by_count":2,"area":null},{"id":"2609.04200","title":"Principia: Relational Physics Tests for Video Models","created":"2026-09-03","cited_by_count":2,"area":null},{"id":"2601.16471","title":"Order from Chaos: Physical World Understanding from Glitchy Gameplay Videos","created":"2026-01-23","cited_by_count":1,"area":null},{"id":"2604.21873","title":"Grounding Video Reasoning in Physical Signals","created":"2026-04-23","cited_by_count":1,"area":null},{"id":"2605.07568","title":"Tracing the Arrow of Time: Diagnosing Temporal Information Flow in Video-LLMs","created":"2026-05-08","cited_by_count":1,"area":null},{"id":"2605.29283","title":"Do Physics Foundation Models Learn Generalizable Physics? A Bias-Aware Benchmark Across Physical Regimes and Distribution Shifts","created":"2026-05-28","cited_by_count":1,"area":null},{"id":"2606.03986","title":"NewtPhys: Do Foundation Models Understand Newtonian Physics?","created":"2026-06-02","cited_by_count":1,"area":null},{"id":"2601.18340","title":"Beyond Rigid: Benchmarking Non-Rigid Video Editing","created":"2026-01-26","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":"2602.13314","title":"Sim2Radar: Toward Bridging the Radar Sim-to-Real Gap with VLM-Guided Scene Reconstruction","created":"2026-02-10","cited_by_count":0,"area":null},{"id":"2603.01950","title":"Semantic Similarity is a Spurious Measure of Comic Understanding: Lessons Learned from Hallucinations in a Benchmarking Experiment","created":"2026-03-02","cited_by_count":0,"area":null},{"id":"2605.04515","title":"From Priors to Perception: Grounding Video-LLMs in Physical Reality","created":"2026-05-06","cited_by_count":0,"area":null},{"id":"2605.14040","title":"Physics-R1: An Audited Olympiad Corpus and Released Verifiers for Visual Physics Reasoning","created":"2026-05-13","cited_by_count":0,"area":null},{"id":"2605.16292","title":"Evidence of a Cognitive Shift in AI Education: How Students Are Rethinking Human Intelligence?","created":"2026-04-14","cited_by_count":0,"area":null},{"id":"2605.24782","title":"The Perception-Physics Paradox: Probing Scientific Alignment with TC-Bench","created":"2026-05-23","cited_by_count":0,"area":null},{"id":"2606.18586","title":"APT: Atomic Physical Transitions for Causal Video-Language Understanding","created":"2026-06-17","cited_by_count":0,"area":null},{"id":"2607.07962","title":"Beyond Thermal Imaging: Inferring Thermophysical Properties from Time-Resolved Thermal Observations","created":"2026-07-08","cited_by_count":0,"area":null},{"id":"2608.06361","title":"The Low Frequency Trap: Video Language Models Fail at Simple Event Bookkeeping","created":"2026-08-06","cited_by_count":0,"area":null},{"id":"2608.20009","title":"ExPhy: A Benchmark for Explicit Physical Property Learning in Multi-Object Trajectory Forecasting","created":"2026-08-20","cited_by_count":0,"area":null},{"id":"2609.06190","title":"One Perturbation Is Not Enough: Identifiability and Blind Baselines for Behavioral AI Evaluation","created":"2026-09-05","cited_by_count":0,"area":null},{"id":"2609.19815","title":"SnapPhysics: A Physics-Aware Scene Graph from a Single View for Interactive Mixed Reality Scenes","created":"2026-09-17","cited_by_count":0,"area":null},{"id":"2609.21259","title":"CogGym: Towards Large-Scale Comparative Evaluation of Human and Machine Cognition","created":"2026-09-18","cited_by_count":0,"area":null},{"id":"2609.25738","title":"OmniFysics-Nano-V2 Technical Report: Understanding the Physical World Across Modalities","created":"2026-09-22","cited_by_count":0,"area":null},{"id":"2609.31714","title":"OmniFysics-Captioner Technical Report: Grounding Omni-Modal Understanding in the Physical World for Better Captioning","created":"2026-09-21","cited_by_count":0,"area":null},{"id":"2609.34480","title":"When Does an Image Determine the Answer? Benchmarking Visual Answerability across Charts and Scenes","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2609.37030","title":"MotionInsight: Diagnosing Object Motion Deficiencies in Generated Videos","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2610.06511","title":"ArtifactArena: Evaluating Models by What They Build in the Physical World","created":"2026-10-05","cited_by_count":0,"area":null},{"id":"2610.13021","title":"EmbodiedCLBench: Evaluating Continual Learning for Self-Evolving Embodied Agents","created":"2026-10-09","cited_by_count":0,"area":null},{"id":"2610.15228","title":"Words to World: Benchmarking LLMs in Interactive Physical Environments","created":"2026-10-10","cited_by_count":0,"area":null},{"id":"2610.19266","title":"LAMP: 3D Source-Aware Lighting Estimation at Multiple Points","created":"2026-10-13","cited_by_count":0,"area":null},{"id":"2610.19823","title":"PhyMetric: Diagnosing Physical Plausibility in Text-to-Video Generation via Scene-Level QA","created":"2026-10-14","cited_by_count":0,"area":null}],"next_cursor":null}