{"total":75,"rows":[{"id":"2410.04417","title":"SparseVLM: Visual Token Sparsification for Efficient Vision-Language Model Inference","created":"2024-10-06","cited_by_count":391,"area":"mllm"},{"id":"2410.17247","title":"PyramidDrop: Accelerating Your Large Vision-Language Models via Pyramid Visual Redundancy Reduction","created":"2024-10-22","cited_by_count":294,"area":"mllm"},{"id":"2412.00447","title":"ATP-LLaVA: Adaptive Token Pruning for Large Vision Language Models","created":"2024-11-30","cited_by_count":89,"area":"mllm"},{"id":"2411.10803","title":"Multi-Stage Vision Token Dropping: Towards Efficient Multimodal Large Language Model","created":"2024-11-16","cited_by_count":68,"area":"mllm"},{"id":"2505.05467","title":"StreamBridge: Turning Your Offline Video Large Language Model into a Proactive Streaming Assistant","created":"2025-05-08","cited_by_count":63,"area":null},{"id":"2503.18278","title":"TopV: Compatible Token Pruning with Inference Time Optimization for Fast and Low-Memory Multimodal Vision Language Model","created":"2025-03-24","cited_by_count":57,"area":"mllm"},{"id":"2412.02104","title":"Explainable and Interpretable Multimodal Large Language Models: A Comprehensive Survey","created":"2024-12-03","cited_by_count":52,"area":"mllm"},{"id":"2510.02912","title":"Don't Just Chase \"Highlighted Tokens\" in MLLMs: Revisiting Visual Holistic Context Retention","created":"2025-10-03","cited_by_count":47,"area":"mllm"},{"id":"2504.09644","title":"SegEarth-R1: Geospatial Pixel Reasoning via Large Language Model","created":"2025-04-13","cited_by_count":42,"area":"lr"},{"id":"2412.01292","title":"LSceneLLM: Enhancing Large 3D Scene Understanding Using Adaptive Visual Preferences","created":"2024-12-02","cited_by_count":38,"area":"mllm"},{"id":"2509.22647","title":"CapRL: Stimulating Dense Image Caption Capabilities via Reinforcement Learning","created":"2025-09-26","cited_by_count":38,"area":"lr"},{"id":"2504.08748","title":"A Survey of Multimodal Retrieval-Augmented Generation","created":"2025-03-26","cited_by_count":37,"area":"rag"},{"id":"2501.02268","title":"What Kind of Visual Tokens Do We Need? Training-free Visual Token Pruning for Multi-modal Large Language Models from the Perspective of Graph","created":"2025-01-04","cited_by_count":36,"area":"mllm"},{"id":"2503.07588","title":"When Large Vision-Language Model Meets Large Remote Sensing Imagery: Coarse-to-Fine Text-Guided Token Pruning","created":"2025-03-10","cited_by_count":35,"area":"mllm"},{"id":"2503.08625","title":"SegAgent: Exploring Pixel Understanding Capabilities in MLLMs by Imitating Human Annotator Trajectories","created":"2025-03-11","cited_by_count":30,"area":null},{"id":"2412.00556","title":"Accelerating Multimodal Large Language Models by Searching Optimal Vision Token Reduction","created":"2024-11-30","cited_by_count":28,"area":"mllm"},{"id":"2412.05819","title":"[CLS] Token Tells Everything Needed for Training-free Efficient MLLMs","created":"2024-12-08","cited_by_count":26,"area":"mllm"},{"id":"2506.21862","title":"LLaVA-Scissor: Token Compression with Semantic Connected Components for Video LLMs","created":"2025-06-27","cited_by_count":26,"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":"2412.20105","title":"ST$^3$: Accelerating Multimodal Large Language Model by Spatial-Temporal Visual Token Trimming","created":"2024-12-28","cited_by_count":20,"area":"mllm"},{"id":"2501.16297","title":"FALCON: Resolving Visual Redundancy and Fragmentation in High-resolution Multimodal Large Language Models via Visual Registers","created":"2025-01-27","cited_by_count":20,"area":"mllm"},{"id":"2407.08706","title":"HiRes-LLaVA: Restoring Fragmentation Input in High-Resolution Large Vision-Language Models","created":"2024-07-11","cited_by_count":16,"area":"mllm"},{"id":"2409.13194","title":"ChemDFM-X: Towards Large Multimodal Model for Chemistry","created":"2024-09-20","cited_by_count":16,"area":null},{"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":"2502.20395","title":"R2-T2: Re-Routing in Test-Time for Multimodal Mixture-of-Experts","created":"2025-02-27","cited_by_count":12,"area":"lr"},{"id":"2503.09387","title":"VideoScan: Enabling Efficient Streaming Video Understanding via Frame-level Semantic Carriers","created":"2025-03-12","cited_by_count":12,"area":"mllm"},{"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":"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":"2510.16598","title":"VisionSelector: End-to-End Learnable Visual Token Compression for Efficient Multimodal LLMs","created":"2025-10-18","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":"2408.11795","title":"EE-MLLM: A Data-Efficient and Compute-Efficient Multimodal Large Language Model","created":"2024-08-21","cited_by_count":10,"area":"mllm"},{"id":"2504.00595","title":"Open-Qwen2VL: Compute-Efficient Pre-Training of Fully-Open Multimodal LLMs on Academic Resources","created":"2025-04-01","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":"2502.00717","title":"MINT: Mitigating Hallucinations in Large Vision-Language Models via Token Reduction","created":"2025-02-02","cited_by_count":8,"area":"mllm"},{"id":"2507.00505","title":"LLaVA-SP: Enhancing Visual Representation with Visual Spatial Tokens for MLLMs","created":"2025-07-01","cited_by_count":8,"area":"mllm"},{"id":"2502.11453","title":"Connector-S: A Survey of Connectors in Multi-modal Large Language Models","created":"2025-02-17","cited_by_count":7,"area":"mllm"},{"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":"2410.13694","title":"Exploring the Design Space of Visual Context Representation in Video MLLMs","created":"2024-10-17","cited_by_count":6,"area":"mllm"},{"id":"2503.04058","title":"EVE: Towards End-to-End Video Subtitle Extraction with Vision-Language Models","created":"2025-03-06","cited_by_count":6,"area":"mllm"},{"id":"2504.01655","title":"Q-Adapt: Adapting LMM for Visual Quality Assessment with Progressive Instruction Tuning","created":"2025-04-02","cited_by_count":6,"area":null},{"id":"2510.12793","title":"ViCO: A Training Strategy towards Semantic Aware Dynamic High-Resolution","created":"2025-10-14","cited_by_count":6,"area":"mllm"},{"id":"2512.10324","title":"EchoingPixels: Aliasing-Resistant Joint Token Reduction for Audio-Visual LLMs","created":"2025-12-11","cited_by_count":6,"area":"inference"},{"id":"2603.25155","title":"Photon: Speedup Volume Understanding with Efficient Multimodal Large Language Models","created":"2026-03-26","cited_by_count":6,"area":"mllm"},{"id":"2606.24422","title":"EgoSAT: A Comprehensive Benchmark of Egocentric Streaming Interaction Understanding","created":"2026-06-23","cited_by_count":6,"area":"mllm"},{"id":"2507.03262","title":"Investigating Redundancy in Multimodal Large Language Models with Multiple Vision Encoders","created":"2025-07-04","cited_by_count":5,"area":"mllm"},{"id":"2512.18747","title":"IPCV: Information-Preserving Compression for MLLM Visual Encoders","created":"2025-12-21","cited_by_count":5,"area":"mllm"},{"id":"2504.03154","title":"TokenFLEX: Unified VLM Training for Flexible Visual Tokens Inference","created":"2025-04-04","cited_by_count":4,"area":"mllm"},{"id":"2509.24837","title":"ZOO-Prune: Training-Free Token Pruning via Zeroth-Order Gradient Estimation in Vision-Language Models","created":"2025-09-29","cited_by_count":4,"area":"lr"},{"id":"2604.22281","title":"DocPrune:Efficient Document Question Answering via Background, Question, and Comprehension-aware Token Pruning","created":"2026-04-24","cited_by_count":4,"area":"mllm"},{"id":"2411.11435","title":"GLDesigner: Leveraging Multi-Modal LLMs as Designer for Enhanced Aesthetic Text Glyph Layouts","created":"2024-11-18","cited_by_count":3,"area":"mllm"},{"id":"2507.20842","title":"METEOR: Multi-Encoder Collaborative Token Pruning for Efficient Vision Language Models","created":"2025-07-28","cited_by_count":3,"area":"mllm"},{"id":"2511.15098","title":"A Comprehensive Study on Visual Token Redundancy for Discrete Diffusion-based Multimodal Large Language Models","created":"2025-11-19","cited_by_count":3,"area":"mllm"},{"id":"2512.12089","title":"VEGAS: Mitigating Hallucinations in Large Vision-Language Models via Vision-Encoder Attention Guided Adaptive Steering","created":"2025-12-12","cited_by_count":3,"area":"mllm"},{"id":"2602.20566","title":"BFA++: Hierarchical Best-Feature-Aware Token Prune for Multi-View Vision Language Action Model","created":"2026-02-24","cited_by_count":3,"area":"mllm"},{"id":"2505.12728","title":"SpecFLASH: A Latent-Guided Semi-autoregressive Speculative Decoding Framework for Efficient Multimodal Generation","created":"2025-05-19","cited_by_count":2,"area":"mllm"},{"id":"2505.14043","title":"Selective Structured State Space for Multispectral-fused Small Target Detection","created":"2025-05-20","cited_by_count":2,"area":"ssm"},{"id":"2506.01097","title":"Task-Related Token Compression in Multimodal Large Language Models from an Explainability Perspective","created":"2025-06-01","cited_by_count":2,"area":"mllm"},{"id":"2509.18733","title":"Knowledge Transfer from Interaction Learning","created":"2025-09-23","cited_by_count":2,"area":"mllm"},{"id":"2510.00078","title":"Adaptive and Resource-efficient Agentic AI Systems for Mobile and Embedded Devices: A Survey","created":"2025-09-30","cited_by_count":2,"area":"lr"},{"id":"2510.15162","title":"Train a Unified Multimodal Data Quality Classifier with Synthetic Data","created":"2025-10-16","cited_by_count":2,"area":"mllm"},{"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":"2509.18179","title":"The Describe-Then-Generate Bottleneck: How VLM Descriptions Alter Image Generation Outcomes","created":"2025-09-18","cited_by_count":1,"area":null},{"id":"2509.25151","title":"VideoAnchor: Reinforcing Subspace-Structured Visual Cues for Coherent Visual-Spatial Reasoning","created":"2025-09-29","cited_by_count":1,"area":"lr"},{"id":"2605.07568","title":"Tracing the Arrow of Time: Diagnosing Temporal Information Flow in Video-LLMs","created":"2026-05-08","cited_by_count":1,"area":null},{"id":"2502.00241","title":"Mordal: Automated Pretrained Model Selection for Vision Language Models","created":"2025-02-01","cited_by_count":0,"area":"mllm"},{"id":"2503.06472","title":"CalliReader: Contextualizing Chinese Calligraphy via an Embedding-Aligned Vision-Language Model","created":"2025-03-09","cited_by_count":0,"area":"mllm"},{"id":"2507.10302","title":"DisCo: Towards Distinct and Coherent Visual Encapsulation in Video MLLMs","created":"2025-07-14","cited_by_count":0,"area":"mllm"},{"id":"2509.22261","title":"InfiMed-Foundation: Pioneering Advanced Multimodal Medical Models with Compute-Efficient Pre-Training and Multi-Stage Fine-Tuning","created":"2025-09-26","cited_by_count":0,"area":"mllm"},{"id":"2602.02197","title":"Hierarchical Adaptive Eviction for KV Cache Management in Multimodal Language Models","created":"2026-02-02","cited_by_count":0,"area":"mllm"},{"id":"2602.11494","title":"Arbitrary Ratio Feature Compression via Next Token Prediction","created":"2026-02-12","cited_by_count":0,"area":null},{"id":"2603.27383","title":"Decompose, Mix, Adapt: A Unified Framework for Parameter-Efficient Neural Network Recombination and Compression","created":"2026-03-28","cited_by_count":0,"area":null},{"id":"2604.02689","title":"Efficient3D: A Unified Framework for Adaptive and Debiased Token Reduction in 3D MLLMs","created":"2026-04-03","cited_by_count":0,"area":"lr"},{"id":"2608.11024","title":"When Visual Signals Mislead: A Mechanistic Study of Attribute Hallucination in Vision-Language Models","created":"2026-08-11","cited_by_count":0,"area":"mllm"},{"id":"2608.18025","title":"How Far Should Tokenization Go? Predictive Effectiveness and Relational Losslessness","created":"2026-08-18","cited_by_count":0,"area":null},{"id":"2610.16744","title":"FoveaTree: Information-Density Trees for Query-Guided Visual Token Pruning in Video Large Language Models","created":"2026-10-12","cited_by_count":0,"area":"inference"}],"next_cursor":null}