{"total":16,"rows":[{"id":"2310.15166","title":"Large Language Models are Visual Reasoning Coordinators","created":"2023-10-23","cited_by_count":58,"area":"lr"},{"id":"2310.15747","title":"Large Language Models are Temporal and Causal Reasoners for Video Question Answering","created":"2023-10-24","cited_by_count":51,"area":"lr"},{"id":"2202.04800","title":"The Abduction of Sherlock Holmes: A Dataset for Visual Abductive Reasoning","created":"2022-02-10","cited_by_count":38,"area":"lr"},{"id":"2203.11130","title":"PACS: A Dataset for Physical Audiovisual CommonSense Reasoning","created":"2022-03-21","cited_by_count":18,"area":"lr"},{"id":"2310.05872","title":"ViCor: Bridging Visual Understanding and Commonsense Reasoning with Large Language Models","created":"2023-10-09","cited_by_count":12,"area":"lr"},{"id":"2307.09636","title":"Traffic-Domain Video Question Answering with Automatic Captioning","created":"2023-07-18","cited_by_count":10,"area":"lr"},{"id":"2311.05298","title":"Improving Vision-and-Language Reasoning via Spatial Relations Modeling","created":"2023-11-09","cited_by_count":5,"area":"lr"},{"id":"2311.12391","title":"From Wrong To Right: A Recursive Approach Towards Vision-Language Explanation","created":"2023-11-21","cited_by_count":4,"area":"lr"},{"id":"2405.16934","title":"Do Vision-Language Transformers Exhibit Visual Commonsense? An Empirical Study of VCR","created":"2024-05-27","cited_by_count":4,"area":"lr"},{"id":"2407.07778","title":"WorldAPIs: The World Is Worth How Many APIs? A Thought Experiment","created":"2024-07-10","cited_by_count":4,"area":"lr"},{"id":"2504.10077","title":"Towards Quantifying Commonsense Reasoning with Mechanistic Insights","created":"2025-04-14","cited_by_count":4,"area":"lr"},{"id":"2305.03204","title":"VideoOFA: Two-Stage Pre-Training for Video-to-Text Generation","created":"2023-05-04","cited_by_count":3,"area":"lr"},{"id":"2309.02290","title":"ATM: Action Temporality Modeling for Video Question Answering","created":"2023-09-05","cited_by_count":3,"area":"lr"},{"id":"2602.08996","title":"Generalizing Sports Feedback Generation by Watching Competitions and Reading Books: A Rock Climbing Case Study","created":"2026-02-09","cited_by_count":0,"area":"lr"},{"id":"2607.24064","title":"MarineEVT: Advancing Event-Centric Marine Video Understanding via Visual Tool Reasoning","created":"2026-07-27","cited_by_count":0,"area":"lr"},{"id":"2608.20814","title":"Enhancing Localized Reasoning for Long Video Understanding via Efficient Segment-to-Video Supervision","created":"2026-08-21","cited_by_count":0,"area":"lr"}],"next_cursor":null}