{"total":34,"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":"2205.14895","title":"From Representation to Reasoning: Towards both Evidence and Commonsense Reasoning for Video Question-Answering","created":"2022-05-30","cited_by_count":51,"area":"lr"},{"id":"2506.09943","title":"CausalVQA: A Physically Grounded Causal Reasoning Benchmark for Video Models","created":"2025-06-11","cited_by_count":35,"area":"lr"},{"id":"2505.00681","title":"MINERVA: Evaluating Complex Video Reasoning","created":"2025-05-01","cited_by_count":32,"area":"lr"},{"id":"2512.15693","title":"Skyra: AI-Generated Video Detection via Grounded Artifact Reasoning","created":"2025-12-17","cited_by_count":25,"area":"lr"},{"id":"2506.05425","title":"SIV-Bench: A Video Benchmark for Social Interaction Understanding and Reasoning","created":"2025-06-05","cited_by_count":18,"area":"lr"},{"id":"2306.17778","title":"Look, Remember and Reason: Grounded reasoning in videos with language models","created":"2023-06-30","cited_by_count":14,"area":"lr"},{"id":"2506.08817","title":"Video-CoT: A Comprehensive Dataset for Spatiotemporal Understanding of Videos Based on Chain-of-Thought","created":"2025-06-10","cited_by_count":14,"area":"lr"},{"id":"2512.15153","title":"Explainable Action Form Assessment by Exploiting Multimodal Chain-of-Thoughts Reasoning","created":"2025-12-17","cited_by_count":14,"area":"lr"},{"id":"2408.12009","title":"CaRDiff: Video Salient Object Ranking Chain of Thought Reasoning for Saliency Prediction with Diffusion","created":"2024-08-21","cited_by_count":12,"area":"lr"},{"id":"2607.24904","title":"Mage-VL: An Efficient Codec-Native Streaming Multimodal Foundation Model","created":"2026-07-27","cited_by_count":10,"area":"lr"},{"id":"2511.23477","title":"Video-CoM: Interactive Video Reasoning via Chain of Manipulations","created":"2025-11-28","cited_by_count":9,"area":"lr"},{"id":"2305.16602","title":"Discovering Novel Actions from Open World Egocentric Videos with Object-Grounded Visual Commonsense Reasoning","created":"2023-05-26","cited_by_count":6,"area":"lr"},{"id":"2409.03206","title":"TC-LLaVA: Rethinking the Transfer from Image to Video Understanding with Temporal Considerations","created":"2024-09-05","cited_by_count":6,"area":"lr"},{"id":"2509.13175","title":"More performant and scalable: Rethinking contrastive vision-language pre-training of radiology in the LLM era","created":"2025-09-16","cited_by_count":6,"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":"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":"2605.03276","title":"VEBench:Benchmarking Large Multimodal Models for Real-World Video Editing","created":"2026-05-05","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":"2407.13094","title":"Rethinking Video-Text Understanding: Retrieval from Counterfactually Augmented Data","created":"2024-07-18","cited_by_count":1,"area":"lr"},{"id":"2412.10566","title":"EVLM: Self-Reflective Multimodal Reasoning for Cross-Dimensional Visual Editing","created":"2024-12-13","cited_by_count":1,"area":"lr"},{"id":"2506.22385","title":"Can Video Large Multimodal Models Think Like Doubters-or Double-Down: A Study on Defeasible Video Entailment","created":"2025-06-27","cited_by_count":1,"area":"lr"},{"id":"2601.23251","title":"Structure Over Scale: Learning Visual Reasoning from Pedagogical Video","created":"2026-01-30","cited_by_count":1,"area":"lr"},{"id":"2602.20608","title":"VAGNet: Grounding 3D Affordance from Human-Object Interactions in Videos","created":"2026-02-24","cited_by_count":1,"area":"lr"},{"id":"2603.02546","title":"On Discriminative vs. Generative classifiers: Rethinking MLLMs for Action Understanding","created":"2026-03-03","cited_by_count":1,"area":"lr"},{"id":"2605.15342","title":"Minerva-Ego: Spatiotemporal Hints for Egocentric Video Understanding","created":"2026-05-14","cited_by_count":1,"area":"lr"},{"id":"2606.02321","title":"Training-Free Composed Video Retrieval via Visual Representation-Guided Video-LLM Reasoning","created":"2026-06-01","cited_by_count":1,"area":"lr"},{"id":"2501.09304","title":"Finding the Trigger: Causal Abductive Reasoning on Video Events","created":"2025-01-16","cited_by_count":0,"area":"lr"},{"id":"2601.11322","title":"Enhancing Vision Language Models with Logic Reasoning for Situational Awareness","created":"2026-01-16","cited_by_count":0,"area":"lr"},{"id":"2603.10300","title":"From Imitation to Intuition: Intrinsic Reasoning for Open-Instance Video Classification","created":"2026-03-11","cited_by_count":0,"area":"lr"},{"id":"2606.22409","title":"Gold Points Sniper: Self-guided Visual Reasoning in VLM for Fine-grained Action Understanding","created":"2026-06-21","cited_by_count":0,"area":"lr"},{"id":"2608.24439","title":"DoublesEval: Diagnosing Multi-Agent Tactical Reasoning in Vision-Language Models via Professional Doubles Badminton","created":"2026-08-25","cited_by_count":0,"area":"lr"},{"id":"2609.38377","title":"PhyProbe: Rethinking Physical Consistency Evaluation in Generated Videos","created":"2026-09-29","cited_by_count":0,"area":"lr"}],"next_cursor":null}