{"total":14,"rows":[{"id":"2408.15769","title":"A Survey on Evaluation of Multimodal Large Language Models","created":"2024-08-28","cited_by_count":46,"area":"lr"},{"id":"2509.25373","title":"From Perception to Cognition: A Survey of Vision-Language Interactive Reasoning in Multimodal Large Language Models","created":"2025-09-29","cited_by_count":26,"area":"lr"},{"id":"2503.19622","title":"Exploring Hallucination of Large Multimodal Models in Video Understanding: Benchmark, Analysis and Mitigation","created":"2025-03-25","cited_by_count":20,"area":"lr"},{"id":"2510.23569","title":"EgoThinker: Unveiling Egocentric Reasoning with Spatio-Temporal CoT","created":"2025-10-27","cited_by_count":16,"area":"lr"},{"id":"2508.07470","title":"AURA: A Fine-Grained Benchmark and Decomposed Metric for Audio-Visual Reasoning","created":"2025-08-10","cited_by_count":8,"area":"lr"},{"id":"2603.02872","title":"Think-as-You-See: Streaming Chain-of-Thought Reasoning for Large Vision-Language Models","created":"2026-03-03","cited_by_count":6,"area":"lr"},{"id":"2505.08455","title":"VCRBench: Exploring Long-form Causal Reasoning Capabilities of Large Video Language Models","created":"2025-05-13","cited_by_count":5,"area":"lr"},{"id":"2603.15386","title":"RieMind: Geometry-Grounded Spatial Agent for Scene Understanding","created":"2026-03-16","cited_by_count":4,"area":"lr"},{"id":"2604.20473","title":"Video-ToC: Video Tree-of-Cue Reasoning","created":"2026-04-22","cited_by_count":1,"area":"lr"},{"id":"2604.22226","title":"Towards Temporal Compositional Reasoning in Long-Form Sports Videos","created":"2026-04-24","cited_by_count":1,"area":"lr"},{"id":"2605.11559","title":"When Looking Is Not Enough: Visual Attention Structure Reveals Hallucination in MLLMs","created":"2026-05-12","cited_by_count":1,"area":"lr"},{"id":"2511.18463","title":"Decoupling Perception from Reasoning for Hallucination-Resistant Video Understanding","created":"2025-11-23","cited_by_count":0,"area":"lr"},{"id":"2603.15008","title":"Clue Matters: Leveraging Latent Visual Clues to Empower Video Reasoning","created":"2026-03-16","cited_by_count":0,"area":"lr"},{"id":"2609.28991","title":"Beneath the Scores: Rethinking Hallucination Evaluation for Video Understanding Models","created":"2026-09-24","cited_by_count":0,"area":"lr"}],"next_cursor":null}