{"total":140,"rows":[{"id":"2504.13181","title":"Perception Encoder: The best visual embeddings are not at the output of the network","created":"2025-04-17","cited_by_count":326,"area":null},{"id":"2508.05629","title":"On the Generalization of SFT: A Reinforcement Learning Perspective with Reward Rectification","created":"2025-08-07","cited_by_count":127,"area":"lr"},{"id":"2504.17343","title":"TimeChat-Online: 80% Visual Tokens are Naturally Redundant in Streaming Videos","created":"2025-04-24","cited_by_count":97,"area":null},{"id":"2411.11922","title":"SAMURAI: Adapting Segment Anything Model for Zero-Shot Visual Tracking with Motion-Aware Memory","created":"2024-11-18","cited_by_count":94,"area":null},{"id":"2508.04416","title":"Thinking With Videos: Multimodal Tool-Augmented Reinforcement Learning for Long Video Reasoning","created":"2025-08-06","cited_by_count":91,"area":"lr"},{"id":"2410.23266","title":"TOMATO: Assessing Visual Temporal Reasoning Capabilities in Multimodal Foundation Models","created":"2024-10-30","cited_by_count":73,"area":"lr"},{"id":"2512.10942","title":"VL-JEPA: Joint Embedding Predictive Architecture for Vision-language","created":"2025-12-11","cited_by_count":68,"area":"mllm"},{"id":"2502.05173","title":"VideoRoPE: What Makes for Good Video Rotary Position Embedding?","created":"2025-02-07","cited_by_count":65,"area":null},{"id":"2504.15376","title":"Towards Understanding Camera Motions in Any Video","created":"2025-04-21","cited_by_count":64,"area":null},{"id":"2501.01986","title":"FrameFusion: Combining Similarity and Importance for Video Token Reduction on Large Vision Language Models","created":"2024-12-30","cited_by_count":54,"area":"mllm"},{"id":"2506.15220","title":"video-SALMONN 2: Caption-Enhanced Audio-Visual Large Language Models","created":"2025-06-18","cited_by_count":47,"area":null},{"id":"2412.13180","title":"Feather the Throttle: Revisiting Visual Token Pruning for Vision-Language Model Acceleration","created":"2024-12-17","cited_by_count":41,"area":"mllm"},{"id":"2503.12329","title":"CapArena: Benchmarking and Analyzing Detailed Image Captioning in the LLM Era","created":"2025-03-16","cited_by_count":41,"area":null},{"id":"2505.22654","title":"VScan: Rethinking Visual Token Reduction for Efficient Large Vision-Language Models","created":"2025-05-28","cited_by_count":41,"area":"lr"},{"id":"2411.17686","title":"Filter, Correlate, Compress: Training-Free Token Reduction for MLLM Acceleration","created":"2024-11-26","cited_by_count":39,"area":"mllm"},{"id":"2503.17349","title":"Beyond Semantics: Rediscovering Spatial Awareness in Vision-Language Models","created":"2025-03-21","cited_by_count":37,"area":"lr"},{"id":"2504.14693","title":"Video-MMLU: A Massive Multi-Discipline Lecture Understanding Benchmark","created":"2025-04-20","cited_by_count":37,"area":null},{"id":"2412.03324","title":"A Stitch in Time Saves Nine: Small VLM is a Precise Guidance for Accelerating Large VLMs","created":"2024-12-04","cited_by_count":35,"area":"mllm"},{"id":"2504.04158","title":"JarvisIR: Elevating Autonomous Driving Perception with Intelligent Image Restoration","created":"2025-04-05","cited_by_count":34,"area":"driving"},{"id":"2510.12720","title":"Omni-Captioner: Data Pipeline, Models, and Benchmark for Omni Detailed Perception","created":"2025-10-14","cited_by_count":30,"area":null},{"id":"2507.13353","title":"VideoITG: Multimodal Video Understanding with Instructed Temporal Grounding","created":"2025-07-17","cited_by_count":29,"area":null},{"id":"2510.10395","title":"AVoCaDO: An Audiovisual Video Captioner Driven by Temporal Orchestration","created":"2025-10-12","cited_by_count":27,"area":null},{"id":"2512.22315","title":"VideoZoomer: Reinforcement-Learned Temporal Focusing for Long Video Reasoning","created":"2025-12-26","cited_by_count":27,"area":"lr"},{"id":"2505.19650","title":"Modality Curation: Building Universal Embeddings for Advanced Multimodal Information Retrieval","created":"2025-05-26","cited_by_count":26,"area":null},{"id":"2502.14914","title":"CAPability: A Comprehensive Visual Caption Benchmark for Evaluating Both Correctness and Thoroughness","created":"2025-02-19","cited_by_count":25,"area":"mllm"},{"id":"2507.20198","title":"A Survey of Token Compression for Efficient Multimodal Large Language Models","created":"2025-07-27","cited_by_count":25,"area":"mllm"},{"id":"2602.13823","title":"Embed-RL: Reinforcement Learning for Reasoning-Driven Multimodal Embeddings","created":"2026-02-14","cited_by_count":24,"area":"lr"},{"id":"2502.12782","title":"VidCapBench: A Comprehensive Benchmark of Video Captioning for Controllable Text-to-Video Generation","created":"2025-02-18","cited_by_count":23,"area":null},{"id":"2504.16082","title":"MR. Video: \"MapReduce\" is the Principle for Long Video Understanding","created":"2025-04-22","cited_by_count":23,"area":null},{"id":"2503.15871","title":"MASH-VLM: Mitigating Action-Scene Hallucination in Video-LLMs through Disentangled Spatial-Temporal Representations","created":"2025-03-20","cited_by_count":22,"area":null},{"id":"2508.05211","title":"VFlowOpt: A Token Pruning Framework for LMMs with Visual Information Flow-Guided Optimization","created":"2025-08-07","cited_by_count":22,"area":"mllm"},{"id":"2412.09501","title":"Lyra: An Efficient and Speech-Centric Framework for Omni-Cognition","created":"2024-12-12","cited_by_count":20,"area":"mllm"},{"id":"2510.05091","title":"Factuality Matters: When Image Generation and Editing Meet Structured Visuals","created":"2025-10-06","cited_by_count":20,"area":"lr"},{"id":"2501.00513","title":"CaReBench: A Fine-Grained Benchmark for Video Captioning and Retrieval","created":"2024-12-31","cited_by_count":19,"area":null},{"id":"2506.03179","title":"Vid-SME: Membership Inference Attacks against Large Video Understanding Models","created":"2025-05-29","cited_by_count":19,"area":"mllm"},{"id":"2507.11336","title":"UGC-VideoCaptioner: An Omni UGC Video Detail Caption Model and New Benchmarks","created":"2025-07-15","cited_by_count":19,"area":null},{"id":"2411.10979","title":"VidComposition: Can MLLMs Analyze Compositions in Compiled Videos?","created":"2024-11-17","cited_by_count":18,"area":"mllm"},{"id":"2503.10742","title":"Keyframe-oriented Vision Token Pruning: Enhancing Efficiency of Large Vision Language Models on Long-Form Video Processing","created":"2025-03-13","cited_by_count":18,"area":"mllm"},{"id":"2506.00993","title":"FlexSelect: Flexible Token Selection for Efficient Long Video Understanding","created":"2025-06-01","cited_by_count":18,"area":null},{"id":"2510.07143","title":"Are We Using the Right Benchmark: An Evaluation Framework for Visual Token Compression Methods","created":"2025-10-08","cited_by_count":17,"area":"mllm"},{"id":"2412.04449","title":"p-MoD: Building Mixture-of-Depths MLLMs via Progressive Ratio Decay","created":"2024-12-05","cited_by_count":16,"area":"mllm"},{"id":"2506.07371","title":"ARGUS: Hallucination and Omission Evaluation in Video-LLMs","created":"2025-06-09","cited_by_count":16,"area":null},{"id":"2510.17681","title":"PICABench: How Far Are We from Physically Realistic Image Editing?","created":"2025-10-20","cited_by_count":16,"area":null},{"id":"2604.18572","title":"Back into Plato's Cave: Examining Cross-modal Representational Convergence at Scale","created":"2026-04-20","cited_by_count":16,"area":null},{"id":"2503.14075","title":"Growing a Multi-head Twig via Distillation and Reinforcement Learning to Accelerate Large Vision-Language Models","created":"2025-03-18","cited_by_count":15,"area":"mllm"},{"id":"2504.00502","title":"ShortV: Efficient Multimodal Large Language Models by Freezing Visual Tokens in Ineffective Layers","created":"2025-04-01","cited_by_count":14,"area":"mllm"},{"id":"2505.01583","title":"TEMPURA: Temporal Event Masked Prediction and Understanding for Reasoning in Action","created":"2025-05-02","cited_by_count":14,"area":"lr"},{"id":"2505.13928","title":"LoVR: A Benchmark for Long Video Retrieval in Multimodal Contexts","created":"2025-05-20","cited_by_count":14,"area":null},{"id":"2601.19267","title":"DiaDem: Advancing Dialogue Descriptions in Audiovisual Video Captioning for Multimodal Large Language Models","created":"2026-01-27","cited_by_count":13,"area":"mllm"},{"id":"2503.16980","title":"VQToken: Neural Discrete Token Representation Learning for Extreme Token Reduction in Video Large Language Models","created":"2025-03-21","cited_by_count":12,"area":"inference"},{"id":"2503.21817","title":"Skip-Vision: Efficient and Scalable Acceleration of Vision-Language Models via Adaptive Token Skipping","created":"2025-03-26","cited_by_count":12,"area":"mllm"},{"id":"2508.18634","title":"OwlCap: Harmonizing Motion-Detail for Video Captioning via HMD-270K and Caption Set Equivalence Reward","created":"2025-08-26","cited_by_count":12,"area":null},{"id":"2601.10592","title":"Action100M: A Large-scale Video Action Dataset","created":"2026-01-15","cited_by_count":12,"area":null},{"id":"2602.08683","title":"OneVision-Encoder: Codec-Aligned Sparsity as a Foundational Principle for Multimodal Intelligence","created":"2026-02-09","cited_by_count":12,"area":null},{"id":"2412.02071","title":"Progress-Aware Video Frame Captioning","created":"2024-12-03","cited_by_count":11,"area":null},{"id":"2412.19794","title":"MVTamperBench: Evaluating Robustness of Vision-Language Models","created":"2024-12-27","cited_by_count":11,"area":"mllm"},{"id":"2505.17020","title":"CrossLMM: Decoupling Long Video Sequences from LMMs via Dual Cross-Attention Mechanisms","created":"2025-05-22","cited_by_count":11,"area":"mllm"},{"id":"2506.20066","title":"ToSA: Token Merging with Spatial Awareness","created":"2025-06-24","cited_by_count":11,"area":"inference"},{"id":"2510.02295","title":"VideoNSA: Native Sparse Attention Scales Video Understanding","created":"2025-10-02","cited_by_count":11,"area":"mllm"},{"id":"2512.04000","title":"Divide, then Ground: Adapting Frame Selection to Query Types for Long-Form Video Understanding","created":"2025-12-03","cited_by_count":11,"area":"mllm"},{"id":"2602.08711","title":"TimeChat-Captioner: Scripting Multi-Scene Videos with Time-Aware and Structural Audio-Visual Captions","created":"2026-02-09","cited_by_count":11,"area":null},{"id":"2503.24379","title":"Any2Caption:Interpreting Any Condition to Caption for Controllable Video Generation","created":"2025-03-31","cited_by_count":10,"area":null},{"id":"2504.01328","title":"Slow-Fast Architecture for Video Multi-Modal Large Language Models","created":"2025-04-02","cited_by_count":10,"area":"mllm"},{"id":"2411.17773","title":"Efficient Multi-modal Large Language Models via Visual Token Grouping","created":"2024-11-26","cited_by_count":9,"area":"mllm"},{"id":"2505.20124","title":"TUNA: Comprehensive Fine-grained Temporal Understanding Evaluation on Dense Dynamic Videos","created":"2025-05-26","cited_by_count":9,"area":null},{"id":"2507.02591","title":"AuroraLong: Bringing RNNs Back to Efficient Open-Ended Video Understanding","created":"2025-07-03","cited_by_count":9,"area":null},{"id":"2510.27571","title":"Towards Universal Video Retrieval: Generalizing Video Embedding via Synthesized Multimodal Pyramid Curriculum","created":"2025-10-31","cited_by_count":9,"area":null},{"id":"2601.22155","title":"UEval: A Benchmark for Unified Multimodal Generation","created":"2026-01-29","cited_by_count":9,"area":"lr"},{"id":"2602.13013","title":"Towards Universal Video MLLMs with Attribute-Structured and Quality-Verified Instructions","created":"2026-02-13","cited_by_count":9,"area":null},{"id":"2604.05546","title":"Efficient Inference for Large Vision-Language Models: Bottlenecks, Techniques, and Prospects","created":"2026-04-07","cited_by_count":9,"area":"lr"},{"id":"2502.16427","title":"Fine-Grained Captioning of Long Videos through Scene Graph Consolidation","created":"2025-02-23","cited_by_count":8,"area":"mllm"},{"id":"2509.26636","title":"AccidentBench: Benchmarking Multimodal Understanding and Reasoning in Vehicle Accidents and Beyond","created":"2025-09-30","cited_by_count":8,"area":null},{"id":"2510.05034","title":"Video-LMM Post-Training: A Deep Dive into Video Reasoning with Large Multimodal Models","created":"2025-10-06","cited_by_count":8,"area":"lr"},{"id":"2510.24134","title":"VC4VG: Optimizing Video Captions for Text-to-Video Generation","created":"2025-10-28","cited_by_count":8,"area":null},{"id":"2505.18757","title":"ToDRE: Effective Visual Token Pruning via Token Diversity and Task Relevance","created":"2025-05-24","cited_by_count":7,"area":"mllm"},{"id":"2510.02425","title":"Words That Make Language Models Perceive","created":"2025-10-02","cited_by_count":7,"area":null},{"id":"2510.18726","title":"IF-VidCap: Can Video Caption Models Follow Instructions?","created":"2025-10-21","cited_by_count":7,"area":"mllm"},{"id":"2503.10691","title":"Reasoning is All You Need for Video Generalization: A Counterfactual Benchmark with Sub-question Evaluation","created":"2025-03-12","cited_by_count":6,"area":"lr"},{"id":"2504.20384","title":"FiLA-Video: Spatio-Temporal Compression for Fine-Grained Long Video Understanding","created":"2025-04-29","cited_by_count":6,"area":null},{"id":"2511.19436","title":"VDC-Agent: When Video Detailed Captioners Evolve Themselves via Agentic Self-Reflection","created":"2025-11-24","cited_by_count":6,"area":"agents"},{"id":"2602.07960","title":"D-ORCA: Dialogue-Centric Optimization for Robust Audio-Visual Captioning","created":"2026-02-08","cited_by_count":6,"area":null},{"id":"2503.04240","title":"DiffPO: Diffusion-styled Preference Optimization for Efficient Inference-Time Alignment of Large Language Models","created":"2025-03-06","cited_by_count":5,"area":"alignment"},{"id":"2506.02850","title":"METok: Multi-Stage Event-based Token Compression for Efficient Long Video Understanding","created":"2025-06-03","cited_by_count":5,"area":"inference"},{"id":"2507.12841","title":"AnyCap Project: A Unified Framework, Dataset, and Benchmark for Controllable Omni-modal Captioning","created":"2025-07-17","cited_by_count":5,"area":null},{"id":"2510.11606","title":"ExpVid: A Benchmark for Experiment Video Understanding & Reasoning","created":"2025-10-13","cited_by_count":5,"area":"lr"},{"id":"2603.01400","title":"Token Reduction via Local and Global Contexts Optimization for Efficient Video Large Language Models","created":"2026-03-02","cited_by_count":5,"area":"inference"},{"id":"2604.05650","title":"See the Forest for the Trees: Loosely Speculative Decoding via Visual-Semantic Guidance for Efficient Inference of Video LLMs","created":"2026-04-07","cited_by_count":5,"area":"inference"},{"id":"2509.14199","title":"Dense Video Understanding with Gated Residual Tokenization","created":"2025-09-17","cited_by_count":4,"area":null},{"id":"2511.16595","title":"TimeViper: A Hybrid Mamba-Transformer Vision-Language Model for Efficient Long Video Understanding","created":"2025-11-20","cited_by_count":4,"area":"mllm"},{"id":"2603.22911","title":"ForestPrune: High-ratio Visual Token Compression for Video Multimodal Large Language Models via Spatial-Temporal Forest Modeling","created":"2026-03-24","cited_by_count":4,"area":"mllm"},{"id":"2606.07433","title":"Watch, Remember, Reason: Human-View Video Understanding with MLLMs","created":"2026-06-05","cited_by_count":4,"area":"lr"},{"id":"2503.18712","title":"LLaVAction: evaluating and training multi-modal large language models for action understanding","created":"2025-03-24","cited_by_count":3,"area":"mllm"},{"id":"2505.17423","title":"VIBE: Annotation-Free Video-to-Text Information Bottleneck Evaluation for TL;DR","created":"2025-05-23","cited_by_count":3,"area":null},{"id":"2505.18855","title":"Inference Compute-Optimal Video Vision Language Models","created":"2025-05-24","cited_by_count":3,"area":"mllm"},{"id":"2506.00835","title":"SynPO: Synergizing Descriptiveness and Preference Optimization for Video Detailed Captioning","created":"2025-06-01","cited_by_count":3,"area":"alignment"},{"id":"2508.13460","title":"Revisiting MLLM Token Technology through the Lens of Classical Visual Coding","created":"2025-08-19","cited_by_count":3,"area":"mllm"},{"id":"2510.03341","title":"OpusAnimation: Code-Based Dynamic Chart Generation","created":"2025-10-02","cited_by_count":3,"area":null},{"id":"2601.08273","title":"HIPPO: Accelerating Video Large Language Models Inference via Holistic-aware Parallel Speculative Decoding","created":"2026-01-13","cited_by_count":3,"area":"inference"},{"id":"2603.29437","title":"SeGPruner: Semantic-Geometric Visual Token Pruner for 3D Question Answering","created":"2026-03-31","cited_by_count":3,"area":"mllm"},{"id":"2604.21718","title":"Building a Precise Video Language with Human-AI Oversight","created":"2026-04-22","cited_by_count":3,"area":null}],"next_cursor":"100"}