{"total":53,"rows":[{"id":"2502.14191","title":"Multimodal RewardBench: Holistic Evaluation of Reward Models for Vision Language Models","created":"2025-02-20","cited_by_count":44,"area":"mllm"},{"id":"2509.11106","title":"Fluid Language Model Benchmarking","created":"2025-09-14","cited_by_count":35,"area":null},{"id":"2410.10139","title":"MMIE: Massive Multimodal Interleaved Comprehension Benchmark for Large Vision-Language Models","created":"2024-10-14","cited_by_count":33,"area":"mllm"},{"id":"2501.03225","title":"Automated Generation of Challenging Multiple-Choice Questions for Vision Language Model Evaluation","created":"2025-01-06","cited_by_count":30,"area":"mllm"},{"id":"2504.10514","title":"ColorBench: Can VLMs See and Understand the Colorful World? A Comprehensive Benchmark for Color Perception, Reasoning, and Robustness","created":"2025-04-10","cited_by_count":28,"area":"lr"},{"id":"2504.18838","title":"Toward Generalizable Evaluation in the LLM Era: A Survey Beyond Benchmarks","created":"2025-04-26","cited_by_count":28,"area":null},{"id":"2412.06141","title":"MMedPO: Aligning Medical Vision-Language Models with Clinical-Aware Multimodal Preference Optimization","created":"2024-12-09","cited_by_count":21,"area":"mllm"},{"id":"2505.11454","title":"HumaniBench: A Human-Centric Framework for Large Multimodal Models Evaluation","created":"2025-05-16","cited_by_count":19,"area":"mllm"},{"id":"2510.04401","title":"Your Vision-Language Model Can't Even Count to 20: Exposing the Failures of VLMs in Compositional Counting","created":"2025-10-06","cited_by_count":18,"area":"mllm"},{"id":"2503.20271","title":"ViLBench: A Suite for Vision-Language Process Reward Modeling","created":"2025-03-26","cited_by_count":16,"area":"lr"},{"id":"2512.00818","title":"Med-CMR: A Fine-Grained Benchmark Integrating Visual Evidence and Clinical Logic for Medical Complex Multimodal Reasoning","created":"2025-11-30","cited_by_count":14,"area":"lr"},{"id":"2505.12601","title":"Rethinking Predictive Modeling for LLM Routing: When Simple kNN Beats Complex Learned Routers","created":"2025-05-19","cited_by_count":11,"area":"lr"},{"id":"2502.06445","title":"Benchmarking Vision-Language Models on Optical Character Recognition in Dynamic Video Environments","created":"2025-02-10","cited_by_count":10,"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":"2512.04062","title":"Eval Factsheets: A Structured Framework for Documenting AI Evaluations","created":"2025-12-03","cited_by_count":9,"area":null},{"id":"2512.06581","title":"MedGRPO: Multi-Task Reinforcement Learning for Heterogeneous Medical Video Understanding","created":"2025-12-06","cited_by_count":8,"area":"lr"},{"id":"2512.02942","title":"Benchmarking Scientific Understanding and Reasoning for Video Generation using VideoScience-Bench","created":"2025-12-02","cited_by_count":7,"area":null},{"id":"2512.04763","title":"MemLoRA: Distilling Expert Adapters for On-Device Memory Systems","created":"2025-12-04","cited_by_count":7,"area":null},{"id":"2509.00484","title":"VideoRewardBench: Comprehensive Evaluation of Multimodal Reward Models for Video Understanding","created":"2025-08-30","cited_by_count":6,"area":"mllm"},{"id":"2511.17722","title":"Can Vision-Language Models Count? A Synthetic Benchmark and Analysis of Attention-Based Interventions","created":"2025-11-21","cited_by_count":6,"area":"mllm"},{"id":"2505.13946","title":"Visual Instruction Bottleneck Tuning","created":"2025-05-20","cited_by_count":5,"area":"mllm"},{"id":"2507.11932","title":"Hyperphantasia: A Benchmark for Evaluating the Mental Visualization Capabilities of Multimodal LLMs","created":"2025-07-16","cited_by_count":5,"area":"mllm"},{"id":"2509.17353","title":"Medical AI Consensus: A Multi-Agent Framework for Radiology Report Generation and Evaluation","created":"2025-09-22","cited_by_count":5,"area":"agents"},{"id":"2510.10880","title":"Where on Earth? A Vision-Language Benchmark for Probing Model Geolocation Skills Across Scales","created":"2025-10-13","cited_by_count":5,"area":"mllm"},{"id":"2411.05056","title":"Seeing is Deceiving: Exploitation of Visual Pathways in Multi-Modal Language Models","created":"2024-11-07","cited_by_count":4,"area":"mllm"},{"id":"2503.15633","title":"Vision-Speech Models: Teaching Speech Models to Converse about Images","created":"2025-03-19","cited_by_count":4,"area":"mllm"},{"id":"2602.21428","title":"PSF-Med: Measuring and Explaining Paraphrase Sensitivity in Medical Vision Language Models","created":"2026-02-24","cited_by_count":4,"area":"mllm"},{"id":"2503.23062","title":"Shape and Texture Recognition in Large Vision-Language Models","created":"2025-03-29","cited_by_count":3,"area":"mllm"},{"id":"2506.23725","title":"PAC Bench: Do Foundation Models Understand Prerequisites for Executing Manipulation Policies?","created":"2025-06-30","cited_by_count":3,"area":"mllm"},{"id":"2508.08508","title":"Re:Verse -- Can Your VLM Read a Manga?","created":"2025-08-11","cited_by_count":3,"area":"mllm"},{"id":"2602.00249","title":"SANEval: Open-Vocabulary Compositional Benchmarks with Failure-mode Diagnosis","created":"2026-01-30","cited_by_count":3,"area":null},{"id":"2505.06803","title":"Bridging Ears and Eyes: Analyzing Audio and Visual Large Language Models to Humans in Visible Sound Recognition and Reducing Their Sensory Gap via Cross-Modal Distillation","created":"2025-05-11","cited_by_count":2,"area":null},{"id":"2510.22045","title":"VLM-SlideEval: Evaluating VLMs on Structured Comprehension and Perturbation Sensitivity in PPT","created":"2025-10-24","cited_by_count":2,"area":"mllm"},{"id":"2511.20710","title":"Are Neuro-Inspired Multi-Modal Vision-Language Models Resilient to Membership Inference Privacy Leakage?","created":"2025-11-24","cited_by_count":2,"area":"mllm"},{"id":"2501.13223","title":"Data Matters Most: Auditing Social Bias in Contrastive Vision Language Models","created":"2025-01-22","cited_by_count":1,"area":"mllm"},{"id":"2505.05318","title":"Mapping User Trust in Vision Language Models: Research Landscape, Challenges, and Prospects","created":"2025-05-08","cited_by_count":1,"area":"mllm"},{"id":"2511.19647","title":"Robot-Powered Data Flywheels: Deploying Robots in the Wild for Continual Data Collection and Foundation Model Adaptation","created":"2025-11-24","cited_by_count":1,"area":null},{"id":"2601.00269","title":"FaithSCAN: Model-Driven Single-Pass Hallucination Detection for Faithful Visual Question Answering","created":"2026-01-01","cited_by_count":1,"area":"mllm"},{"id":"2602.15278","title":"Visual Persuasion: What Influences Decisions of Vision-Language Models?","created":"2026-02-17","cited_by_count":1,"area":"mllm"},{"id":"2605.24981","title":"Large Language Model Selection with Limited Annotations","created":"2026-05-24","cited_by_count":1,"area":null},{"id":"2606.01513","title":"Compliance-Scored Best-of-N Guardrail Orchestration for Multimodal Document Generation in Payments Dispute Defense","created":"2026-06-01","cited_by_count":1,"area":"safety"},{"id":"2606.03715","title":"Text-to-Image Models Need Less from Text Encoders Than You Think","created":"2026-06-02","cited_by_count":1,"area":null},{"id":"2608.07525","title":"Unified Hallucination Fuzzing for Multimodal Large Language Models","created":"2026-07-15","cited_by_count":1,"area":"mllm"},{"id":"2504.06313","title":"Text-to-Image Models and Their Representation of People from Different Nationalities Engaging in Activities","created":"2025-04-08","cited_by_count":0,"area":null},{"id":"2506.02027","title":"The End Of Universal Lifelong Identifiers: Identity Systems For The AI Era","created":"2025-05-29","cited_by_count":0,"area":null},{"id":"2509.08266","title":"Examining Vision Language Models through Multi-dimensional Experiments with Vision and Text Features","created":"2025-09-10","cited_by_count":0,"area":"mllm"},{"id":"2509.17907","title":"MEF: A Systematic Evaluation Framework for Text-to-Image Models","created":"2025-09-22","cited_by_count":0,"area":null},{"id":"2510.09418","title":"Large Language Model Selection with Limited Annotations","created":"2025-10-10","cited_by_count":0,"area":null},{"id":"2510.20482","title":"Reliable and Reproducible Demographic Inference for Fairness in Face Analysis","created":"2025-10-23","cited_by_count":0,"area":null},{"id":"2511.03768","title":"What's in Common? Multimodal Models Hallucinate When Reasoning Across Scenes","created":"2025-11-05","cited_by_count":0,"area":"lr"},{"id":"2603.22249","title":"EgoGroups: A Benchmark For Detecting Social Groups of People in the Wild","created":"2026-03-23","cited_by_count":0,"area":null},{"id":"2604.19083","title":"ProjLens: Unveiling the Role of Projectors in Multimodal Model Safety","created":"2026-04-21","cited_by_count":0,"area":"mllm"},{"id":"2609.31706","title":"Can't Find Waldo: Evaluating VLMs' Sensitivity to Image Resolution and Detail Level","created":"2026-09-20","cited_by_count":0,"area":"mllm"}],"next_cursor":null}