{"list":"other","total":66,"rows":[{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"2405.21075","title":"Video-MME: The First-Ever Comprehensive Evaluation Benchmark of Multi-modal LLMs in Video Analysis","created":"2024-05-31","cited_by_count":1413},{"id":"2312.07104","title":"SGLang: Efficient Execution of Structured Language Model Programs","created":"2023-12-12","cited_by_count":1141},{"id":"2307.16449","title":"MovieChat: From Dense Token to Sparse Memory for Long Video Understanding","created":"2023-07-31","cited_by_count":542},{"id":"2509.17765","title":"Qwen3-Omni Technical Report","created":"2025-09-22","cited_by_count":497},{"id":"2406.08035","title":"LVBench: An Extreme Long Video Understanding Benchmark","created":"2024-06-12","cited_by_count":410},{"id":"2311.04934","title":"Prompt Cache: Modular Attention Reuse for Low-Latency Inference","created":"2023-11-07","cited_by_count":268},{"id":"2404.05726","title":"MA-LMM: Memory-Augmented Large Multimodal Model for Long-Term Video Understanding","created":"2024-04-08","cited_by_count":229},{"id":"2501.00574","title":"VideoChat-Flash: Hierarchical Compression for Long-Context Video Modeling","created":"2024-12-31","cited_by_count":220},{"id":"2409.14485","title":"Video-XL: Extra-Long Vision Language Model for Hour-Scale Video Understanding","created":"2024-09-22","cited_by_count":213},{"id":"2310.07240","title":"CacheGen: KV Cache Compression and Streaming for Fast Large Language Model Serving","created":"2023-10-11","cited_by_count":203},{"id":"2312.17235","title":"A Simple LLM Framework for Long-Range Video Question-Answering","created":"2023-12-28","cited_by_count":178},{"id":"2411.13093","title":"Video-RAG: Visually-aligned Retrieval-Augmented Long Video Comprehension","created":"2024-11-20","cited_by_count":138},{"id":"2503.00540","title":"Streaming Video Question-Answering with In-context Video KV-Cache Retrieval","created":"2025-03-01","cited_by_count":117},{"id":"2505.18079","title":"Deep Video Discovery: Agentic Search with Tool Use for Long-form Video Understanding","created":"2025-05-23","cited_by_count":98},{"id":"2412.12075","title":"CG-Bench: Clue-grounded Question Answering Benchmark for Long Video Understanding","created":"2024-12-16","cited_by_count":85},{"id":"2410.03226","title":"Frame-Voyager: Learning to Query Frames for Video Large Language Models","created":"2024-10-04","cited_by_count":83},{"id":"2506.23825","title":"Flash-VStream: Efficient Real-Time Understanding for Long Video Streams","created":"2025-06-30","cited_by_count":81},{"id":"2509.24871","title":"StreamForest: Efficient Online Video Understanding with Persistent Event Memory","created":"2025-09-29","cited_by_count":78},{"id":"2604.27393","title":"MiniCPM-o 4.5: Towards Real-Time Full-Duplex Omni-Modal Interaction","created":"2026-04-30","cited_by_count":78},{"id":"2501.19201","title":"Efficient Reasoning with Hidden Thinking","created":"2025-01-31","cited_by_count":75},{"id":"2406.12846","title":"DrVideo: Document Retrieval Based Long Video Understanding","created":"2024-06-18","cited_by_count":65},{"id":"2510.10689","title":"OmniVideoBench: Towards Audio-Visual Understanding Evaluation for Omni MLLMs","created":"2025-10-12","cited_by_count":59},{"id":"2411.19772","title":"LongVALE: Vision-Audio-Language-Event Benchmark Towards Time-Aware Omni-Modal Perception of Long Videos","created":"2024-11-29","cited_by_count":51},{"id":"2505.18227","title":"Token Reduction Should Go Beyond Efficiency in Generative Models -- From Vision, Language to Multimodality","created":"2025-05-23","cited_by_count":50},{"id":"2512.14698","title":"TimeLens: Rethinking Video Temporal Grounding with Multimodal LLMs","created":"2025-12-16","cited_by_count":50},{"id":"2412.12444","title":"LazyDiT: Lazy Learning for the Acceleration of Diffusion Transformers","created":"2024-12-17","cited_by_count":37},{"id":"2512.05774","title":"Active Video Perception: Iterative Evidence Seeking for Agentic Long Video Understanding","created":"2025-12-05","cited_by_count":29},{"id":"2409.18962","title":"Exploring Token Pruning in Vision State Space Models","created":"2024-09-27","cited_by_count":28},{"id":"2502.06020","title":"Temporal Working Memory: Query-Guided Segment Refinement for Enhanced Multimodal Understanding","created":"2025-02-09","cited_by_count":28},{"id":"2511.07278","title":"StreamKV: Streaming Video Question-Answering with Segment-based KV Cache Retrieval and Compression","created":"2025-11-10","cited_by_count":26},{"id":"2412.12441","title":"Numerical Pruning for Efficient Autoregressive Models","created":"2024-12-17","cited_by_count":25},{"id":"2602.04804","title":"OmniSIFT: Modality-Asymmetric Token Compression for Efficient Omni-modal Large Language Models","created":"2026-02-04","cited_by_count":25},{"id":"2603.19217","title":"LVOmniBench: Pioneering Long Audio-Video Understanding Evaluation for Omnimodal LLMs","created":"2026-03-19","cited_by_count":24},{"id":"2505.14708","title":"DraftAttention: Fast Video Diffusion via Low-Resolution Attention Guidance","created":"2025-05-17","cited_by_count":22},{"id":"2507.05116","title":"VOTE: Vision-Language-Action Optimization with Trajectory Ensemble Voting","created":"2025-07-07","cited_by_count":22},{"id":"2511.14582","title":"OmniZip: Audio-Guided Dynamic Token Compression for Fast Omnimodal Large Language Models","created":"2025-11-18","cited_by_count":22},{"id":"2410.15567","title":"Pruning Foundation Models for High Accuracy without Retraining","created":"2024-10-21","cited_by_count":20},{"id":"2511.05489","title":"TimeSearch-R: Adaptive Temporal Search for Long-Form Video Understanding via Self-Verification Reinforcement Learning","created":"2025-11-07","cited_by_count":20},{"id":"2411.14901","title":"ReVisionLLM: Recursive Vision-Language Model for Temporal Grounding in Hour-Long Videos","created":"2024-11-22","cited_by_count":18},{"id":"2410.14725","title":"Rethinking Token Reduction for State Space Models","created":"2024-10-16","cited_by_count":15},{"id":"2506.13589","title":"AdaVideoRAG: Omni-Contextual Adaptive Retrieval-Augmented Efficient Long Video Understanding","created":"2025-06-16","cited_by_count":15},{"id":"2409.17372","title":"Search for Efficient Large Language Models","created":"2024-09-25","cited_by_count":14},{"id":"2411.01171","title":"Fast and Memory-Efficient Video Diffusion Using Streamlined Inference","created":"2024-11-02","cited_by_count":14},{"id":"2603.14145","title":"MMOU: A Massive Multi-Task Omni Understanding and Reasoning Benchmark for Long and Complex Real-World Videos","created":"2026-03-14","cited_by_count":14},{"id":"2505.14709","title":"FastCar: Cache Attentive Replay for Fast Auto-Regressive Video Generation on the Edge","created":"2025-05-17","cited_by_count":10},{"id":"2509.11480","title":"Cross-Platform Scaling of Vision-Language-Action Models from Edge to Cloud GPUs","created":"2025-09-15","cited_by_count":8},{"id":"2512.14273","title":"Zoom-Zero: Reinforced Coarse-to-Fine Video Understanding via Temporal Zoom-in","created":"2025-12-16","cited_by_count":8},{"id":"2601.13719","title":"Hierarchical Long Video Understanding with Audiovisual Entity Cohesion and Agentic Search","created":"2026-01-20","cited_by_count":8},{"id":"2606.14702","title":"OmniVideo-100K: A Dataset for Audio-Visual Reasoning through Structured Scripts and Evidence Chains","created":"2026-06-12","cited_by_count":8},{"id":"2605.16681","title":"A Survey of Advancing Audio Super-Resolution and Bandwidth Extension from Discriminative to Generative Models","created":"2026-05-15","cited_by_count":6},{"id":"2604.16592","title":"Human Cognition in Machines: A Unified Perspective of World Models","created":"2026-04-17","cited_by_count":5},{"id":"2505.21817","title":"ALTER: All-in-One Layer Pruning and Temporal Expert Routing for Efficient Diffusion Generation","created":"2025-05-27","cited_by_count":4},{"id":"2604.17422","title":"Where to Focus: Query-Modulated Multimodal Keyframe Selection for Long Video Understanding","created":"2026-04-19","cited_by_count":4},{"id":"2606.07577","title":"OmniMem: Perturbation-aware Memory Compression for Streaming Audio-Visual LLMs","created":"2026-05-26","cited_by_count":4},{"id":"2606.19341","title":"Native Active Perception as Reasoning for Omni-Modal Understanding","created":"2026-06-17","cited_by_count":4},{"id":"2608.30294","title":"Dynamic Hub-and-Spoke Memory for Streaming Video Understanding","created":"2026-08-31","cited_by_count":4},{"id":"2605.20035","title":"Stage-adaptive Token Selection for Efficient Omni-modal LLMs","created":"2026-05-19","cited_by_count":3},{"id":"2608.05703","title":"StreamArena: Toward Continuous, Interactive, and Long-Horizon Agentic Streaming Video Understanding","created":"2026-08-06","cited_by_count":3},{"id":"2412.05781","title":"Open-Source Acceleration of Stable-Diffusion.cpp Deployable on All Devices","created":"2024-12-08","cited_by_count":2},{"id":"2608.01660","title":"Ground, Cover, and Refine: Evidence-Centric Frame Selection for Long-Video Question Answering","created":"2026-08-03","cited_by_count":2},{"id":"2508.06869","title":"VSI: Visual Subtitle Integration for Keyframe Selection to enhance Long Video Understanding","created":"2025-08-09","cited_by_count":1},{"id":"2604.22245","title":"Listening with Time: Precise Temporal Awareness for Long-Form Audio Understanding","created":"2026-04-24","cited_by_count":1},{"id":"2605.07593","title":"TraceAV-Bench: Benchmarking Multi-Hop Trajectory Reasoning over Long Audio-Visual Videos","created":"2026-05-08","cited_by_count":1},{"id":"2605.20414","title":"PlanRAG-Audio: Planning and Retrieval Augmented Generation for Long-form Audio Understanding","created":"2026-05-19","cited_by_count":1},{"id":"2605.22907","title":"VideoOdyssey: A Benchmark for Ultra-Long-Context and Omni-Modal Video Understanding","created":"2026-05-21","cited_by_count":1}],"next_cursor":null}