{"total":43,"rows":[{"id":"2307.06281","title":"MMBench: Is Your Multi-modal Model an All-around Player?","created":"2023-07-12","cited_by_count":2141,"area":"lr"},{"id":"2407.01284","title":"We-Math: Does Your Large Multimodal Model Achieve Human-like Mathematical Reasoning?","created":"2024-07-01","cited_by_count":286,"area":"lr"},{"id":"2406.11161","title":"Emotion-LLaMA: Multimodal Emotion Recognition and Reasoning with Instruction Tuning","created":"2024-06-17","cited_by_count":121,"area":"lr"},{"id":"2407.08739","title":"MAVIS: Mathematical Visual Instruction Tuning with an Automatic Data Engine","created":"2024-07-11","cited_by_count":113,"area":"lr"},{"id":"2311.16101","title":"How Many Unicorns Are in This Image? A Safety Evaluation Benchmark for Vision LLMs","created":"2023-11-27","cited_by_count":108,"area":"lr"},{"id":"2503.02318","title":"Audio-Reasoner: Improving Reasoning Capability in Large Audio Language Models","created":"2025-03-04","cited_by_count":95,"area":"lr"},{"id":"2310.20550","title":"CapsFusion: Rethinking Image-Text Data at Scale","created":"2023-10-31","cited_by_count":90,"area":"lr"},{"id":"2311.18799","title":"X-InstructBLIP: A Framework for aligning X-Modal instruction-aware representations to LLMs and Emergent Cross-modal Reasoning","created":"2023-11-30","cited_by_count":80,"area":"lr"},{"id":"2311.15596","title":"EgoThink: Evaluating First-Person Perspective Thinking Capability of Vision-Language Models","created":"2023-11-27","cited_by_count":60,"area":"lr"},{"id":"2407.10299","title":"Follow the Rules: Reasoning for Video Anomaly Detection with Large Language Models","created":"2024-07-14","cited_by_count":57,"area":"lr"},{"id":"2311.15209","title":"See and Think: Embodied Agent in Virtual Environment","created":"2023-11-26","cited_by_count":54,"area":"lr"},{"id":"2408.15769","title":"A Survey on Evaluation of Multimodal Large Language Models","created":"2024-08-28","cited_by_count":46,"area":"lr"},{"id":"2406.02030","title":"Multimodal Reasoning with Multimodal Knowledge Graph","created":"2024-06-04","cited_by_count":44,"area":"lr"},{"id":"2410.11623","title":"VidEgoThink: Assessing Egocentric Video Understanding Capabilities for Embodied AI","created":"2024-10-15","cited_by_count":34,"area":"lr"},{"id":"2508.12587","title":"Multimodal Chain of Continuous Thought for Latent-Space Reasoning in Vision-Language Models","created":"2025-08-18","cited_by_count":32,"area":"lr"},{"id":"2405.09713","title":"SOK-Bench: A Situated Video Reasoning Benchmark with Aligned Open-World Knowledge","created":"2024-05-15","cited_by_count":25,"area":"lr"},{"id":"2410.14702","title":"Polymath: A Challenging Multi-modal Mathematical Reasoning Benchmark","created":"2024-10-06","cited_by_count":22,"area":"lr"},{"id":"2403.12884","title":"HYDRA: A Hyper Agent for Dynamic Compositional Visual Reasoning","created":"2024-03-19","cited_by_count":18,"area":"lr"},{"id":"2512.12772","title":"JointAVBench: A Benchmark for Joint Audio-Visual Reasoning Evaluation","created":"2025-12-14","cited_by_count":17,"area":"lr"},{"id":"2501.06430","title":"Open Eyes, Then Reason: Fine-grained Visual Mathematical Understanding in MLLMs","created":"2025-01-11","cited_by_count":16,"area":"lr"},{"id":"2508.01181","title":"Benchmarking and Bridging Emotion Conflicts for Multimodal Emotion Reasoning","created":"2025-08-02","cited_by_count":12,"area":"lr"},{"id":"2501.01426","title":"Unifying Specialized Visual Encoders for Video Language Models","created":"2025-01-02","cited_by_count":10,"area":"lr"},{"id":"2408.12114","title":"SPARK: Multi-Vision Sensor Perception and Reasoning Benchmark for Large-scale Vision-Language Models","created":"2024-08-22","cited_by_count":9,"area":"lr"},{"id":"2503.23219","title":"Aurelia: Test-time Reasoning Distillation in Audio-Visual LLMs","created":"2025-03-29","cited_by_count":9,"area":"lr"},{"id":"2504.19549","title":"DEEMO: De-identity Multimodal Emotion Recognition and Reasoning","created":"2025-04-28","cited_by_count":7,"area":"lr"},{"id":"2505.13403","title":"MR. Judge: Multimodal Reasoner as a Judge","created":"2025-05-19","cited_by_count":7,"area":"lr"},{"id":"2503.09158","title":"FaVChat: Hierarchical Prompt-Query Guided Facial Video Understanding with Data-Efficient GRPO","created":"2025-03-12","cited_by_count":6,"area":"lr"},{"id":"2601.15316","title":"The Paradigm Shift: A Comprehensive Survey on Large Vision Language Models for Multimodal Fake News Detection","created":"2026-01-16","cited_by_count":6,"area":"lr"},{"id":"2604.12735","title":"AffectAgent: Collaborative Multi-Agent Reasoning for Retrieval-Augmented Multimodal Emotion Recognition","created":"2026-04-14","cited_by_count":6,"area":"lr"},{"id":"2408.03160","title":"User-in-the-loop Evaluation of Multimodal LLMs for Activity Assistance","created":"2024-08-04","cited_by_count":5,"area":"lr"},{"id":"2409.18996","title":"From Linguistic Giants to Sensory Maestros: A Survey on Cross-Modal Reasoning with Large Language Models","created":"2024-09-19","cited_by_count":4,"area":"lr"},{"id":"2602.07054","title":"AVERE: Improving Audiovisual Emotion Reasoning with Preference Optimization","created":"2026-02-04","cited_by_count":4,"area":"lr"},{"id":"2601.19204","title":"MATA: A Trainable Hierarchical Automaton System for Multi-Agent Visual Reasoning","created":"2026-01-27","cited_by_count":3,"area":"lr"},{"id":"2603.24696","title":"LLaVA-LE: Large Language-and-Vision Assistant for Lunar Exploration","created":"2026-03-25","cited_by_count":1,"area":"lr"},{"id":"2604.18829","title":"DUALVISION: RGB-Infrared Multimodal Large Language Models for Robust Visual Reasoning","created":"2026-04-20","cited_by_count":1,"area":"lr"},{"id":"2606.11385","title":"DeceptionX: From Multimodal Evidence to Explainable Deception Detection","created":"2026-06-09","cited_by_count":1,"area":"lr"},{"id":"2607.10238","title":"Benchmarking Dynamic Affective Reasoning: A Viewer-Centric Video Emotion Dataset","created":"2026-07-11","cited_by_count":1,"area":"lr"},{"id":"2607.21013","title":"EmoAgent-R1: Towards Multimodal Emotion Understanding with Reinforcement Learning-based Dynamic Agent Specialization","created":"2026-07-23","cited_by_count":1,"area":"lr"},{"id":"2601.18321","title":"Integrating Fine-Grained Audio-Visual Evidence for Robust Multimodal Emotion Reasoning","created":"2026-01-26","cited_by_count":0,"area":"lr"},{"id":"2603.17980","title":"Feeling the Space: Egomotion-Aware Video Representation for Efficient and Accurate 3D Scene Understanding","created":"2026-03-18","cited_by_count":0,"area":"lr"},{"id":"2604.00013","title":"C2F-Thinker: Coarse-to-Fine Reasoning with Hint-Guided Reinforcement Learning for Multimodal Sentiment Analysis","created":"2026-03-10","cited_by_count":0,"area":"lr"},{"id":"2604.03995","title":"A Systematic Study of Cross-Modal Typographic Attacks on Audio-Visual Reasoning","created":"2026-04-05","cited_by_count":0,"area":"lr"},{"id":"2606.14591","title":"AudioDER: A Deduplication-Enhanced Reasoning Dataset for Post-Training Large Audio-Language Models","created":"2026-06-12","cited_by_count":0,"area":"lr"}],"next_cursor":null}