{"total":23,"rows":[{"id":"2501.03230","title":"Video-of-Thought: Step-by-Step Video Reasoning from Perception to Cognition","created":"2024-05-07","cited_by_count":153,"area":"lr"},{"id":"2208.05358","title":"CLEVR-Math: A Dataset for Compositional Language, Visual and Mathematical Reasoning","created":"2022-08-10","cited_by_count":120,"area":"lr"},{"id":"2302.04752","title":"Benchmarks for Automated Commonsense Reasoning: A Survey","created":"2023-02-09","cited_by_count":40,"area":"lr"},{"id":"2203.17271","title":"Do Vision-Language Pretrained Models Learn Composable Primitive Concepts?","created":"2022-03-31","cited_by_count":31,"area":"lr"},{"id":"2404.01591","title":"Language Model Guided Interpretable Video Action Reasoning","created":"2024-04-02","cited_by_count":8,"area":"lr"},{"id":"2406.09240","title":"Comparison Visual Instruction Tuning","created":"2024-06-13","cited_by_count":8,"area":"lr"},{"id":"2405.17201","title":"Diagnosing the Compositional Knowledge of Vision Language Models from a Game-Theoretic View","created":"2024-05-27","cited_by_count":7,"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":"2412.11026","title":"SceneLLM: Implicit Language Reasoning in LLM for Dynamic Scene Graph Generation","created":"2024-12-15","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":"2602.17555","title":"GraphThinker: Reinforcing Temporally Grounded Video Reasoning with Event Graph Thinking","created":"2026-02-19","cited_by_count":5,"area":"lr"},{"id":"2505.03581","title":"DyGEnc: Encoding a Sequence of Textual Scene Graphs to Reason and Answer Questions in Dynamic Scenes","created":"2025-05-06","cited_by_count":4,"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":"2509.13161","title":"Enhancing Video Large Language Models with Structured Multi-Video Collaborative Reasoning","created":"2025-09-16","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":"2606.25842","title":"Graph it first! Enabling Reasoning on Long-form Egocentric Videos through Scene Graphs","created":"2026-06-24","cited_by_count":1,"area":"lr"},{"id":"2607.02425","title":"Learning to Evolve Scenes: Reasoning about Human Activities with Scene Graphs","created":"2026-07-02","cited_by_count":1,"area":"lr"},{"id":"2202.11337","title":"Commonsense Reasoning for Identifying and Understanding the Implicit Need of Help and Synthesizing Assistive Actions","created":"2022-02-23","cited_by_count":0,"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":"2602.10518","title":"MapVerse: A Benchmark for Geospatial Question Answering on Diverse Real-World Maps","created":"2026-02-11","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"},{"id":"2609.08543","title":"STSG-VQA: Evidence-Grounded Temporal Question Answering from Surgical Spatio-Temporal Scene Graphs","created":"2026-09-08","cited_by_count":0,"area":"lr"},{"id":"2609.30952","title":"MVVBench: Benchmarking 4D Reasoning in Vision-Language Models","created":"2026-09-25","cited_by_count":0,"area":"lr"}],"next_cursor":null}