{"total":14,"rows":[{"id":"2204.00598","title":"Socratic Models: Composing Zero-Shot Multimodal Reasoning with Language","created":"2022-04-01","cited_by_count":513,"area":"lr"},{"id":"2410.02763","title":"Vinoground: Scrutinizing LMMs over Dense Temporal Reasoning with Short Videos","created":"2024-10-03","cited_by_count":38,"area":"lr"},{"id":"2506.14827","title":"DAVID-XR1: Detecting AI-Generated Videos with Explainable Reasoning","created":"2025-06-13","cited_by_count":9,"area":"lr"},{"id":"2506.14512","title":"SIRI-Bench: Challenging VLMs' Spatial Intelligence through Complex Reasoning Tasks","created":"2025-06-17","cited_by_count":7,"area":"lr"},{"id":"2603.23404","title":"Unleashing Spatial Reasoning in Multimodal Large Language Models via Textual Representation Guided Reasoning","created":"2026-03-24","cited_by_count":6,"area":"lr"},{"id":"2503.06934","title":"LLaFEA: Frame-Event Complementary Fusion for Fine-Grained Spatiotemporal Understanding in LMMs","created":"2025-03-10","cited_by_count":5,"area":"lr"},{"id":"2509.19552","title":"iFinder: Structured Zero-Shot Vision-Based LLM Grounding for Dash-Cam Video Reasoning","created":"2025-09-23","cited_by_count":3,"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":"2601.13797","title":"PREGEN: Uncovering Latent Thoughts in Composed Video Retrieval","created":"2026-01-20","cited_by_count":1,"area":"lr"},{"id":"2608.13031","title":"UniTraffic-Agent: Unified Traffic Video Reasoning for AI City Challenge 2026 Track 3 with Two Out-of-Domain Evaluations","created":"2026-08-13","cited_by_count":1,"area":"lr"},{"id":"2412.08158","title":"How Vision-Language Tasks Benefit from Large Pre-trained Models: A Survey","created":"2024-12-11","cited_by_count":0,"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":"2606.21734","title":"HPP: Hierarchical Programmatic Probing for Long Video Understanding by Decoupling Perception and Reasoning","created":"2026-06-19","cited_by_count":0,"area":"lr"},{"id":"2608.18734","title":"CL4D: Contrastive Language-4D Pretraining for Vision-Language Reasoning in Dynamic Scenes","created":"2026-08-19","cited_by_count":0,"area":"lr"}],"next_cursor":null}