{"total":31,"rows":[{"id":"2507.13353","title":"VideoITG: Multimodal Video Understanding with Instructed Temporal Grounding","created":"2025-07-17","cited_by_count":29,"area":null},{"id":"2506.00993","title":"FlexSelect: Flexible Token Selection for Efficient Long Video Understanding","created":"2025-06-01","cited_by_count":18,"area":null},{"id":"2508.09486","title":"Video-EM: Event-Centric Episodic Memory for Long-Form Video Understanding","created":"2025-08-13","cited_by_count":10,"area":null},{"id":"2510.02262","title":"From Frames to Clips: Training-free Adaptive Key Clip Selection for Long-Form Video Understanding","created":"2025-10-02","cited_by_count":9,"area":null},{"id":"2512.14017","title":"KFS-Bench: Comprehensive Evaluation of Key Frame Sampling in Long Video Understanding","created":"2025-12-16","cited_by_count":6,"area":null},{"id":"2510.20622","title":"SeViCES: Unifying Semantic-Visual Evidence Consensus for Long Video Understanding","created":"2025-10-23","cited_by_count":5,"area":null},{"id":"2512.14870","title":"HERBench: A Benchmark for Multi-Evidence Integration in Video Question Answering","created":"2025-12-16","cited_by_count":4,"area":null},{"id":"2510.04022","title":"Video-in-the-Loop: Span-Grounded Long Video QA with Interleaved Reasoning","created":"2025-10-05","cited_by_count":3,"area":null},{"id":"2602.17478","title":"QuPAINT: Physics-Aware Instruction Tuning Approach to Quantum Material Discovery","created":"2026-02-19","cited_by_count":3,"area":null},{"id":"2603.23186","title":"ViKey: Enhancing Temporal Understanding in Videos via Visual Prompting","created":"2026-03-24","cited_by_count":3,"area":null},{"id":"2609.00291","title":"StreamScout: Learning When to Look Deeper for Streaming Video Understanding","created":"2026-08-31","cited_by_count":3,"area":null},{"id":"2509.08016","title":"Video Parallel Scaling: Aggregating Diverse Frame Subsets for VideoLLMs","created":"2025-09-09","cited_by_count":2,"area":null},{"id":"2605.22678","title":"Swift Sampling: Selecting Temporal Surprises via Taylor Series","created":"2026-05-21","cited_by_count":2,"area":null},{"id":"2601.03781","title":"MVP: Enhancing Video Large Language Models via Self-supervised Masked Video Prediction","created":"2026-01-07","cited_by_count":1,"area":null},{"id":"2603.20180","title":"Adaptive Greedy Frame Selection for Long Video Understanding","created":"2026-03-20","cited_by_count":1,"area":null},{"id":"2605.09223","title":"CREST: Curvature-Regulated Event-Centric Sampling for Efficient Long-Video Understanding","created":"2026-05-09","cited_by_count":1,"area":null},{"id":"2605.23826","title":"Decomposing Queries into Tool Calls for Long-Video Keyframe Retrieval","created":"2026-05-22","cited_by_count":1,"area":null},{"id":"2606.20711","title":"Video2Code: Generating Interactive Webpages from UI Videos via Action-Aware Revisit","created":"2026-06-16","cited_by_count":1,"area":null},{"id":"2607.27895","title":"MMHBench: A Multi-Perspective Benchmark for Mental Health Understanding in Long-Form Videos","created":"2026-07-30","cited_by_count":1,"area":null},{"id":"2608.03918","title":"When and Where to Look: Adaptive Visual Evidence Scheduling for Efficient Long Video Understanding","created":"2026-08-04","cited_by_count":1,"area":null},{"id":"2609.15128","title":"Omni-Streaming Thinking","created":"2026-09-14","cited_by_count":1,"area":null},{"id":"2508.11955","title":"Temporal Grounding as a Learning Signal for Referring Video Object Segmentation","created":"2025-08-16","cited_by_count":0,"area":null},{"id":"2603.22466","title":"Color When It Counts: Grayscale-Guided Online Triggering for Always-On Streaming Video Sensing","created":"2026-03-23","cited_by_count":0,"area":null},{"id":"2604.02371","title":"Internalized Reasoning for Long-Context Visual Document Understanding","created":"2026-03-31","cited_by_count":0,"area":null},{"id":"2608.05780","title":"Evidence-Driven Dynamic Visual Selector for Efficient Long Video Understanding","created":"2026-08-06","cited_by_count":0,"area":null},{"id":"2608.07585","title":"LAVE: Latent Visual Evidence-Enhanced Planning for Video Tool-use Agents","created":"2026-08-05","cited_by_count":0,"area":null},{"id":"2608.22359","title":"Pre-Decoding Acoustic Triage for Budgeted Vision-Language Captioning of Untrimmed Egocentric Video","created":"2026-08-23","cited_by_count":0,"area":null},{"id":"2608.27929","title":"Training-Free Temporal Abstraction for General Video Understanding","created":"2026-08-28","cited_by_count":0,"area":null},{"id":"2609.10355","title":"Why Is Video Still So Expensive? A Survey of Inference-Efficiency Mechanisms in Video and Audiovisual LLMs","created":"2026-09-09","cited_by_count":0,"area":null},{"id":"2609.12202","title":"QuPAINT: Physics-Aware Multimodal Reasoning for Quantum Material Characterization","created":"2026-09-10","cited_by_count":0,"area":null},{"id":"2610.19050","title":"Focus, Align, and Diffuse: Time-Series-Aware Keyframe Diffusion for Cardiac Dynamic Synthesis from Sparse Observations","created":"2026-10-13","cited_by_count":0,"area":null}],"next_cursor":null}