{"total":33,"rows":[{"id":"2502.05173","title":"VideoRoPE: What Makes for Good Video Rotary Position Embedding?","created":"2025-02-07","cited_by_count":65,"area":null},{"id":"2503.11315","title":"MMS-LLaMA: Efficient LLM-based Audio-Visual Speech Recognition with Minimal Multimodal Speech Tokens","created":"2025-03-14","cited_by_count":19,"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":"2602.13191","title":"CoPE-VideoLM: Leveraging Codec Primitives For Efficient Video Language Modeling","created":"2026-02-13","cited_by_count":11,"area":null},{"id":"2603.16952","title":"Embodied Foundation Models at the Edge: A Survey of Deployment Constraints and Mitigation Strategies","created":"2026-03-16","cited_by_count":9,"area":null},{"id":"2603.23523","title":"Do 3D Large Language Models Really Understand 3D Spatial Relationships?","created":"2026-03-06","cited_by_count":9,"area":null},{"id":"2505.23617","title":"One Trajectory, One Token: Grounded Video Tokenization via Panoptic Sub-object Trajectory","created":"2025-05-29","cited_by_count":7,"area":null},{"id":"2506.03990","title":"DynTok: Dynamic Compression of Visual Tokens for Efficient and Effective Video Understanding","created":"2025-06-04","cited_by_count":7,"area":null},{"id":"2506.10911","title":"NoLoCo: No-all-reduce Low Communication Training Method for Large Models","created":"2025-06-12","cited_by_count":5,"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":"2510.11129","title":"video-SALMONN S: Memory-Enhanced Streaming Audio-Visual LLM","created":"2025-10-13","cited_by_count":4,"area":null},{"id":"2503.00059","title":"Investigating and Enhancing Vision-Audio Capability in Omnimodal Large Language Models","created":"2025-02-27","cited_by_count":3,"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":"2603.07990","title":"MJ1: Multimodal Judgment via Grounded Verification","created":"2026-03-09","cited_by_count":3,"area":null},{"id":"2601.20742","title":"Compression Tells Intelligence: Visual Coding, Visual Token Technology, and the Unification","created":"2026-01-28","cited_by_count":2,"area":null},{"id":"2607.06468","title":"EgoPolice: A Benchmark for Egocentric Video Understanding in High-Stakes Police Body-Worn Camera Footage","created":"2026-07-07","cited_by_count":2,"area":null},{"id":"2503.21782","title":"Mobile-VideoGPT: Fast and Accurate Model for Mobile Video Understanding","created":"2025-03-27","cited_by_count":1,"area":null},{"id":"2504.10443","title":"Multimodal Long Video Modeling Based on Temporal Dynamic Context","created":"2025-04-14","cited_by_count":1,"area":null},{"id":"2506.11737","title":"Quizzard@INOVA Challenge 2025 -- Track A: Plug-and-Play Technique in Interleaved Multi-Image Model","created":"2025-06-13","cited_by_count":1,"area":null},{"id":"2601.12289","title":"ParaMETA: Towards Learning Disentangled Paralinguistic Speaking Styles Representations from Speech","created":"2026-01-18","cited_by_count":1,"area":null},{"id":"2605.06809","title":"LookWhen? Fast Video Recognition by Learning When, Where, and What to Compute","created":"2026-05-07","cited_by_count":1,"area":null},{"id":"2509.09794","title":"Synthetic Homes: A Multimodal Generative AI Pipeline for Residential Building Data Generation under Data Scarcity","created":"2025-09-11","cited_by_count":0,"area":null},{"id":"2511.01449","title":"Privacy Preserving Ordinal-Meta Learning with VLMs for Fine-Grained Fruit Quality Prediction","created":"2025-11-03","cited_by_count":0,"area":null},{"id":"2601.16615","title":"AuroraEdge-V-2B: A Faster And Stronger Edge Visual Large Language Model","created":"2026-01-23","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":"2606.20077","title":"The Hidden Evolution of Disguised Visual Context inside the VLM","created":"2026-06-18","cited_by_count":0,"area":null},{"id":"2607.02799","title":"Conversational Human Audio-visual Talking Dialogue Generation","created":"2026-07-02","cited_by_count":0,"area":null},{"id":"2607.06552","title":"MonoIR-RS: Infrared Remote Sensing Vision-Language Learning with CLIP and VLM Adaptation","created":"2026-07-07","cited_by_count":0,"area":null},{"id":"2607.27902","title":"One Patch Is Enough: Reinforcement-Optimized Visual Token Grounding for MLLM-Based Scene Text Spotting","created":"2026-07-30","cited_by_count":0,"area":null},{"id":"2608.25729","title":"LongVU-TTT: Causal Test-Time Training for Visual Resampling in Long Video Understanding","created":"2026-08-26","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":"2609.31668","title":"Query-aligned video frame selection for long video understanding","created":"2026-09-15","cited_by_count":0,"area":null},{"id":"2609.37685","title":"PAIQ: Patch-Aligned Semantic Injection via Residual Rotation","created":"2026-09-29","cited_by_count":0,"area":null}],"next_cursor":null}