{"total":20,"rows":[{"id":"2305.13786","title":"Perception Test: A Diagnostic Benchmark for Multimodal Video Models","created":"2023-05-23","cited_by_count":314,"area":"lr"},{"id":"2302.04752","title":"Benchmarks for Automated Commonsense Reasoning: A Survey","created":"2023-02-09","cited_by_count":40,"area":"lr"},{"id":"2405.03690","title":"How Good is my Video LMM? Complex Video Reasoning and Robustness Evaluation Suite for Video-LMMs","created":"2024-05-06","cited_by_count":30,"area":"lr"},{"id":"2406.10889","title":"VELOCITI: Benchmarking Video-Language Compositional Reasoning with Strict Entailment","created":"2024-06-16","cited_by_count":10,"area":"lr"},{"id":"2404.01591","title":"Language Model Guided Interpretable Video Action Reasoning","created":"2024-04-02","cited_by_count":8,"area":"lr"},{"id":"2403.10107","title":"Enhancing Human-Centered Dynamic Scene Understanding via Multiple LLMs Collaborated Reasoning","created":"2024-03-15","cited_by_count":6,"area":"lr"},{"id":"2503.10691","title":"Reasoning is All You Need for Video Generalization: A Counterfactual Benchmark with Sub-question Evaluation","created":"2025-03-12","cited_by_count":6,"area":"lr"},{"id":"2310.13473","title":"Benchmarking Sequential Visual Input Reasoning and Prediction in Multimodal Large Language Models","created":"2023-10-20","cited_by_count":5,"area":"lr"},{"id":"2510.11606","title":"ExpVid: A Benchmark for Experiment Video Understanding & Reasoning","created":"2025-10-13","cited_by_count":5,"area":"lr"},{"id":"2512.05513","title":"Know-Show: Benchmarking Video-Language Models on Spatio-Temporal Grounded Reasoning","created":"2025-12-05","cited_by_count":5,"area":"lr"},{"id":"2605.27894","title":"Towards Unified Vision-Language Models with Incomplete Multi-Modal Inputs","created":"2026-05-27","cited_by_count":5,"area":"lr"},{"id":"2511.12263","title":"CrossVid: A Comprehensive Benchmark for Evaluating Cross-Video Reasoning in Multimodal Large Language Models","created":"2025-11-15","cited_by_count":4,"area":"lr"},{"id":"2603.27593","title":"STRIDE: When to Speak Meets Sequence Denoising for Streaming Video Understanding","created":"2026-03-29","cited_by_count":4,"area":"lr"},{"id":"2210.12460","title":"Collaborative Reasoning on Multi-Modal Semantic Graphs for Video-Grounded Dialogue Generation","created":"2022-10-22","cited_by_count":3,"area":"lr"},{"id":"2309.06680","title":"STUPD: A Synthetic Dataset for Spatial and Temporal Relation Reasoning","created":"2023-09-13","cited_by_count":3,"area":"lr"},{"id":"2510.13808","title":"VisCoP: Visual Probing for Video Domain Adaptation of Vision Language Models","created":"2025-10-15","cited_by_count":2,"area":"lr"},{"id":"2210.13984","title":"Inferring Past Human Actions in Homes with Abductive Reasoning","created":"2022-10-24","cited_by_count":1,"area":"lr"},{"id":"2608.15869","title":"Beyond Visual CoT: Internalized Visual Thinking for Proactive Video Reasoning","created":"2026-08-16","cited_by_count":1,"area":"lr"},{"id":"2506.16701","title":"Language-driven Description Generation and Common Sense Reasoning for Video Action Recognition","created":"2025-06-20","cited_by_count":0,"area":"lr"},{"id":"2606.01591","title":"TLG: Temporal-Logic Grounding for Video Question Answering via Source-Annotation Reconstruction and Category-Targeted Reasoning","created":"2026-06-01","cited_by_count":0,"area":"lr"}],"next_cursor":null}