{"total":20,"rows":[{"id":"2603.21389","title":"Task-Specific Efficiency Analysis: When Small Language Models Outperform Large Language Models","created":"2026-03-22","cited_by_count":15,"area":null},{"id":"2502.01481","title":"Intrinsic Entropy of Context Length Scaling in LLMs","created":"2025-02-03","cited_by_count":14,"area":null},{"id":"2503.17690","title":"CountLLM: Towards Generalizable Repetitive Action Counting via Large Language Model","created":"2025-03-22","cited_by_count":14,"area":null},{"id":"2603.19929","title":"RAM: Recover Any 3D Human Motion in-the-Wild","created":"2026-03-20","cited_by_count":12,"area":null},{"id":"2605.23071","title":"The Efficiency Frontier: A Unified Framework for Cost-Performance Optimization in LLM Context Management","created":"2026-05-21","cited_by_count":6,"area":null},{"id":"2603.17840","title":"Video Understanding: From Geometry and Semantics to Unified Models","created":"2026-03-18","cited_by_count":5,"area":null},{"id":"2502.16175","title":"Mojito: LLM-Aided Motion Instructor with Jitter-Reduced Inertial Tokens","created":"2025-02-22","cited_by_count":4,"area":null},{"id":"2509.20006","title":"Revisiting Image Manipulation Localization under Realistic Manipulation Scenarios","created":"2025-09-24","cited_by_count":3,"area":null},{"id":"2511.05369","title":"Dense Motion Captioning","created":"2025-11-07","cited_by_count":3,"area":null},{"id":"2605.05646","title":"MUSE: Resolving Manifold Misalignment in Visual Tokenization via Topological Orthogonality","created":"2026-05-07","cited_by_count":3,"area":null},{"id":"2512.03918","title":"UniMo: Unifying 2D Video and 3D Human Motion with an Autoregressive Framework","created":"2025-12-03","cited_by_count":2,"area":null},{"id":"2508.15845","title":"Coarse-to-Fine Personalized LLM Impressions for Streamlined Radiology Reports","created":"2025-08-19","cited_by_count":1,"area":null},{"id":"2512.22249","title":"Temporal Visual Semantics-Induced Human Motion Understanding with Large Language Models","created":"2025-12-24","cited_by_count":1,"area":null},{"id":"2605.07354","title":"Task-Oriented Communication for Human Action Understanding via Edge-Cloud Co-Inference","created":"2026-05-08","cited_by_count":1,"area":null},{"id":"2609.08117","title":"DriveMotion: A Large-Scale Multi-Source Benchmark for Driver Motion Sequence Modeling and Forecasting","created":"2026-09-08","cited_by_count":1,"area":null},{"id":"2602.09035","title":"E2CAR: An Efficient 2D-CNN Framework for Real-Time EEG Artifact Removal on Edge Devices","created":"2026-01-30","cited_by_count":0,"area":null},{"id":"2606.14724","title":"VigilFormer: Deformable Attention for Video Anomaly Detection with Causal Risk Inference","created":"2026-05-31","cited_by_count":0,"area":null},{"id":"2606.18861","title":"URDF Synthesis from RGB-D Sequences via Differentiable Joint Inference and Energy-Consistent Verification","created":"2026-06-17","cited_by_count":0,"area":null},{"id":"2606.20888","title":"Fine-grained Human Motion Understanding with Language Models","created":"2026-06-18","cited_by_count":0,"area":null},{"id":"2608.21194","title":"ES-VP : Energy-Shaped Dynamic Visual Prompting for Efficient Model Adaptation","created":"2026-08-21","cited_by_count":0,"area":null}],"next_cursor":null}