{"total":24,"rows":[{"id":"2504.14693","title":"Video-MMLU: A Massive Multi-Discipline Lecture Understanding Benchmark","created":"2025-04-20","cited_by_count":37,"area":null},{"id":"2503.19903","title":"Scaling Vision Pre-Training to 4K Resolution","created":"2025-03-25","cited_by_count":28,"area":null},{"id":"2505.11293","title":"Breaking the Batch Barrier (B3) of Contrastive Learning via Smart Batch Mining","created":"2025-05-16","cited_by_count":28,"area":null},{"id":"2601.11035","title":"Your One-Stop Solution for AI-Generated Video Detection","created":"2026-01-16","cited_by_count":15,"area":null},{"id":"2602.13191","title":"CoPE-VideoLM: Leveraging Codec Primitives For Efficient Video Language Modeling","created":"2026-02-13","cited_by_count":11,"area":null},{"id":"2503.05949","title":"Bayesian Fields: Task-driven Open-Set Semantic Gaussian Splatting","created":"2025-03-07","cited_by_count":5,"area":null},{"id":"2505.11945","title":"Top-Down Compression: Revisit Efficient Vision Token Projection for Visual Instruction Tuning","created":"2025-05-17","cited_by_count":3,"area":null},{"id":"2510.12444","title":"A Review of Longitudinal Radiology Report Generation: Dataset Composition, Methods, and Performance Evaluation","created":"2025-10-14","cited_by_count":3,"area":null},{"id":"2512.18028","title":"Embodied4C: Measuring What Matters for Embodied Vision-Language Navigation","created":"2025-12-19","cited_by_count":3,"area":null},{"id":"2605.17260","title":"LiteFrame: Efficient Vision Encoders Unlock Frame Scaling in Video LLMs","created":"2026-05-17","cited_by_count":2,"area":null},{"id":"2509.06306","title":"Video-based Generalized Category Discovery via Memory-Guided Consistency-Aware Contrastive Learning","created":"2025-09-08","cited_by_count":1,"area":null},{"id":"2510.14965","title":"ChangingGrounding: 3D Visual Grounding in Changing Scenes","created":"2025-10-16","cited_by_count":1,"area":null},{"id":"2511.02507","title":"Keeping it Local, Tiny and Real: Automated Report Generation on Edge Computing Devices for Mechatronic-Based Cognitive Systems","created":"2025-11-04","cited_by_count":1,"area":null},{"id":"2602.20161","title":"Mobile-O: Unified Multimodal Understanding and Generation on Mobile Device","created":"2026-02-23","cited_by_count":1,"area":null},{"id":"2602.22819","title":"Face Time Traveller : Travel Through Ages Without Losing Identity","created":"2026-02-26","cited_by_count":1,"area":null},{"id":"2608.10497","title":"SapiensID 2.0: Aligning Human Recognition Foundation Models with Human Perception","created":"2026-08-11","cited_by_count":1,"area":null},{"id":"2503.03579","title":"Intent-Handover: Grounding Language in Human-Usage Regions for Trustworthy Robot-to-Human Handovers","created":"2025-03-05","cited_by_count":0,"area":null},{"id":"2603.00126","title":"QuickGrasp: Responsive Video-Language Querying Service via Accelerated Tokenization and Edge-Augmented Inference","created":"2026-02-23","cited_by_count":0,"area":null},{"id":"2604.00912","title":"ProCap: Projection-Aware Captioning for Spatial Augmented Reality","created":"2026-04-01","cited_by_count":0,"area":null},{"id":"2605.22976","title":"LLM Code Smells: A Taxonomy and Detection Approach","created":"2026-05-21","cited_by_count":0,"area":null},{"id":"2608.26496","title":"RTNav: Towards Real-Time Zero-Shot Object Navigation","created":"2026-08-27","cited_by_count":0,"area":null},{"id":"2609.04392","title":"FAVE: Foveated Adaptive Visual Encoding for Efficient Fine-Grained Visual Understanding","created":"2026-09-03","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":"2609.14473","title":"PuzzleMate: Benchmarking MLLMs for Egocentric Puzzle Assistance","created":"2026-09-13","cited_by_count":0,"area":null}],"next_cursor":null}