{"total":36,"rows":[{"id":"2512.01989","title":"PAI-Bench: A Comprehensive Benchmark For Physical AI","created":"2025-12-01","cited_by_count":34,"area":"mllm"},{"id":"2505.01481","title":"VideoHallu: Evaluating and Mitigating Multi-modal Hallucinations on Synthetic Video Understanding","created":"2025-05-02","cited_by_count":32,"area":"mllm"},{"id":"2505.17012","title":"SpatialScore: Towards Comprehensive Evaluation for Spatial Intelligence","created":"2025-05-22","cited_by_count":24,"area":"mllm"},{"id":"2506.21356","title":"ShotBench: Expert-Level Cinematic Understanding in Vision-Language Models","created":"2025-06-26","cited_by_count":22,"area":"mllm"},{"id":"2502.11163","title":"AI Sees Your Location, But With A Bias Toward The Wealthy World","created":"2025-02-16","cited_by_count":14,"area":"mllm"},{"id":"2505.14728","title":"MORALISE: A Structured Benchmark for Moral Alignment in Visual Language Models","created":"2025-05-20","cited_by_count":10,"area":"mllm"},{"id":"2510.08759","title":"Dissecting Embodied Abilities in Multimodal Language Models through Skill-level Evaluation and Diagnosis","created":"2025-10-09","cited_by_count":8,"area":"mllm"},{"id":"2606.10400","title":"Do Vision-Language Models See or Guess? Measuring and Reducing Textual-Prior Reliance with a Phrasing-Controlled Benchmark","created":"2026-06-09","cited_by_count":8,"area":"mllm"},{"id":"2506.08708","title":"PhyBlock: A Progressive Benchmark for Physical Understanding and Planning via 3D Block Assembly","created":"2025-06-10","cited_by_count":7,"area":"mllm"},{"id":"2511.10946","title":"Abstract 3D Perception for Spatial Intelligence in Vision-Language Models","created":"2025-11-14","cited_by_count":7,"area":"mllm"},{"id":"2503.10110","title":"IMPACT: Intelligent Motion Planning with Acceptable Contact Trajectories via Vision-Language Models","created":"2025-03-13","cited_by_count":5,"area":"mllm"},{"id":"2608.13167","title":"TRAPSBench: Vision-Language Models Encode but Fail to Express Epistemic Restraint","created":"2026-08-13","cited_by_count":5,"area":"mllm"},{"id":"2505.24073","title":"mRAG: Elucidating the Design Space of Multi-modal Retrieval-Augmented Generation","created":"2025-05-29","cited_by_count":4,"area":"mllm"},{"id":"2506.20566","title":"HRIBench: Benchmarking Vision-Language Models for Real-Time Human Perception in Human-Robot Interaction","created":"2025-06-25","cited_by_count":4,"area":"mllm"},{"id":"2508.04280","title":"Enhancing Vision-Language Model Training with Reinforcement Learning in Synthetic Worlds for Real-World Success","created":"2025-08-06","cited_by_count":4,"area":"mllm"},{"id":"2503.09348","title":"MOAT: Evaluating LMMs for Capability Integration and Instruction Grounding","created":"2025-03-12","cited_by_count":2,"area":"mllm"},{"id":"2506.23101","title":"From Individuals to Interactions: Benchmarking Gender Bias in Multimodal Large Language Models from the Lens of Social Relationship","created":"2025-06-29","cited_by_count":2,"area":"mllm"},{"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":"2604.00799","title":"Multimodal Language Models Cannot Spot Spatial Inconsistencies","created":"2026-04-01","cited_by_count":2,"area":"mllm"},{"id":"2506.03371","title":"Toward Reliable VLM: A Fine-Grained Benchmark and Framework for Exposure, Bias, and Inference in Korean Street Views","created":"2025-06-03","cited_by_count":1,"area":"mllm"},{"id":"2506.05440","title":"BYO-Eval: Build Your Own Dataset for Fine-Grained Visual Assessment of Multimodal Language Models","created":"2025-06-05","cited_by_count":1,"area":"mllm"},{"id":"2512.10342","title":"CoSPlan: Corrective Sequential Planning via Scene Graph Incremental Updates","created":"2025-12-11","cited_by_count":1,"area":"mllm"},{"id":"2607.01503","title":"Disentangling Pictorial Cue Understanding from Language Bias in VLMs via Depth Ordering Task","created":"2026-07-01","cited_by_count":1,"area":"mllm"},{"id":"2609.10895","title":"ReactHuman: A Physics-Grounded Benchmark for Human-Like Reactive Decision-Making in Embodied Multimodal LLMs","created":"2026-09-09","cited_by_count":1,"area":"mllm"},{"id":"2511.00110","title":"Chain of Time: In-Context Physical Simulation with Image Generation Models","created":"2025-10-30","cited_by_count":0,"area":"mllm"},{"id":"2603.16958","title":"PhysQuantAgent: An Inference Pipeline of Mass Estimation for Vision-Language Models","created":"2026-03-17","cited_by_count":0,"area":"mllm"},{"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":"2604.22829","title":"Lost in Motion: Vision Language Models Fail the Dynamic Gauges Test","created":"2026-04-19","cited_by_count":0,"area":"mllm"},{"id":"2606.23892","title":"REALM: A Unified Red-Teaming Benchmark for Physical-World VLMs","created":"2026-06-22","cited_by_count":0,"area":"mllm"},{"id":"2607.07189","title":"Does AI Understand Imaging? A Systematic Benchmark of Agentic AI for Computational Imaging Tasks","created":"2026-07-08","cited_by_count":0,"area":"mllm"},{"id":"2609.11022","title":"New Evidence, Same Choice: Testing Physical Experiment Selection in Vision Language Models","created":"2026-09-10","cited_by_count":0,"area":"mllm"},{"id":"2609.21493","title":"PolyBridgeBench: Benchmarking Multimodal LLMs for Physics-Grounded Bridge Design","created":"2026-09-18","cited_by_count":0,"area":"mllm"},{"id":"2609.34072","title":"PhysFieldBench: Can Multimodal Models Understand Physical Fields?","created":"2026-09-28","cited_by_count":0,"area":"mllm"},{"id":"2610.13790","title":"OccludeBench: Can VLMs Find What's Missing?","created":"2026-10-09","cited_by_count":0,"area":"mllm"},{"id":"2610.14397","title":"RealityBench: Simulated Environments to Evaluate a Vision Language Model's Ability to Document Human Physical Work","created":"2026-10-09","cited_by_count":0,"area":"mllm"},{"id":"2610.15722","title":"PhySimCode: A Benchmark and Evaluation Method for Physics Video to Code Generation","created":"2026-10-11","cited_by_count":0,"area":"mllm"}],"next_cursor":null}