{"total":166,"rows":[{"id":"2505.14362","title":"DeepEyes: Incentivizing \"Thinking with Images\" via Reinforcement Learning","created":"2025-05-20","cited_by_count":410,"area":"lr"},{"id":"2508.11630","title":"Thyme: Think Beyond Images","created":"2025-08-15","cited_by_count":167,"area":"lr"},{"id":"2502.13130","title":"Magma: A Foundation Model for Multimodal AI Agents","created":"2025-02-18","cited_by_count":139,"area":"agents"},{"id":"2506.10967","title":"Beyond Attention or Similarity: Maximizing Conditional Diversity for Token Pruning in MLLMs","created":"2025-06-12","cited_by_count":96,"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":"2505.02835","title":"R1-Reward: Training Multimodal Reward Model Through Stable Reinforcement Learning","created":"2025-05-05","cited_by_count":65,"area":"mllm"},{"id":"2504.09641","title":"TinyLLaVA-Video-R1: Towards Smaller LMMs for Video Reasoning","created":"2025-04-13","cited_by_count":62,"area":"lr"},{"id":"2508.15717","title":"StreamMem: Query-Agnostic KV Cache Memory for Streaming Video Understanding","created":"2025-08-21","cited_by_count":58,"area":"mllm"},{"id":"2605.25979","title":"LLaVA-OneVision-2: Towards Next-Generation Perceptual Intelligence","created":"2026-05-25","cited_by_count":39,"area":"mllm"},{"id":"2504.02438","title":"Scaling Video-Language Models to 10K Frames via Hierarchical Differential Distillation","created":"2025-04-03","cited_by_count":37,"area":"mllm"},{"id":"2503.11579","title":"Vamba: Understanding Hour-Long Videos with Hybrid Mamba-Transformers","created":"2025-03-14","cited_by_count":36,"area":"mllm"},{"id":"2509.12594","title":"The Better You Learn, The Smarter You Prune: Towards Efficient Vision-language-action Models via Differentiable Token Pruning","created":"2025-09-16","cited_by_count":36,"area":"vla"},{"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":"2505.21200","title":"Think Twice, Act Once: Token-Aware Compression and Action Reuse for Efficient Inference in Vision-Language-Action Models","created":"2025-05-27","cited_by_count":30,"area":"vla"},{"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":"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":"2510.00515","title":"Efficient Multi-modal Large Language Models via Progressive Consistency Distillation","created":"2025-10-01","cited_by_count":22,"area":"mllm"},{"id":"2503.21307","title":"InternVL-X: Advancing and Accelerating InternVL Series with Efficient Visual Token Compression","created":"2025-03-27","cited_by_count":21,"area":"mllm"},{"id":"2505.22038","title":"Balanced Token Pruning: Accelerating Vision Language Models Beyond Local Optimization","created":"2025-05-28","cited_by_count":20,"area":"mllm"},{"id":"2507.23318","title":"FastDriveVLA: Efficient End-to-End Driving via Plug-and-Play Reconstruction-based Token Pruning","created":"2025-07-31","cited_by_count":20,"area":"vla"},{"id":"2503.10501","title":"TokenCarve: Information-Preserving Visual Token Compression in Multimodal Large Language Models","created":"2025-03-13","cited_by_count":19,"area":"mllm"},{"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":"2503.12926","title":"Task-Oriented Feature Compression for Multimodal Understanding via Device-Edge Co-Inference","created":"2025-03-17","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":"2506.13642","title":"Stream-Omni: Simultaneous Multimodal Interactions with Large Language-Vision-Speech Model","created":"2025-06-16","cited_by_count":18,"area":"mllm"},{"id":"2602.08024","title":"FlashVID: Efficient Video Large Language Models via Training-free Tree-based Spatiotemporal Token Merging","created":"2026-02-08","cited_by_count":18,"area":"inference"},{"id":"2602.23699","title":"HiDrop: Hierarchical Vision Token Reduction in MLLMs via Late Injection, Concave Pyramid Pruning, and Early Exit","created":"2026-02-27","cited_by_count":18,"area":"mllm"},{"id":"2510.17205","title":"$\\mathcal{V}isi\\mathcal{P}runer$: Decoding Discontinuous Cross-Modal Dynamics for Efficient Multimodal LLMs","created":"2025-10-20","cited_by_count":17,"area":"mllm"},{"id":"2512.06866","title":"Less Is More, but Where? Dynamic Token Compression via LLM-Guided Keyframe Prior","created":"2025-12-07","cited_by_count":15,"area":"inference"},{"id":"2505.21233","title":"CROP: Contextual Region-Oriented Visual Token Pruning","created":"2025-05-27","cited_by_count":14,"area":"inference"},{"id":"2509.21789","title":"Visual Multi-Agent System: Mitigating Hallucination Snowballing via Visual Flow","created":"2025-09-26","cited_by_count":13,"area":"mllm"},{"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":"2510.02745","title":"Retrv-R1: A Reasoning-Driven MLLM Framework for Universal and Efficient Multimodal Retrieval","created":"2025-10-03","cited_by_count":12,"area":"lr"},{"id":"2503.06362","title":"Adaptive Audio-Visual Speech Recognition via Matryoshka-Based Multimodal LLMs","created":"2025-03-09","cited_by_count":11,"area":"mllm"},{"id":"2507.08064","title":"PUMA: Layer-Pruned Language Model for Efficient Unified Multimodal Retrieval with Modality-Adaptive Learning","created":"2025-07-10","cited_by_count":11,"area":"distill"},{"id":"2508.00553","title":"HiPrune: Hierarchical Attention for Efficient Token Pruning in Vision-Language Models","created":"2025-08-01","cited_by_count":11,"area":"mllm"},{"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":"2504.17040","title":"DyMU: Dynamic Merging and Virtual Unmerging for Efficient VLMs","created":"2025-04-23","cited_by_count":10,"area":"mllm"},{"id":"2510.13251","title":"Map the Flow: Revealing Hidden Pathways of Information in VideoLLMs","created":"2025-10-15","cited_by_count":10,"area":"mllm"},{"id":"2511.07250","title":"MVU-Eval: Towards Multi-Video Understanding Evaluation for Multimodal LLMs","created":"2025-11-10","cited_by_count":10,"area":"mllm"},{"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":"2505.18812","title":"SAMA: Towards Multi-Turn Referential Grounded Video Chat with Large Language Models","created":"2025-05-24","cited_by_count":8,"area":"mllm"},{"id":"2504.15415","title":"IV-Bench: A Benchmark for Image-Grounded Video Perception and Reasoning in Multimodal LLMs","created":"2025-04-21","cited_by_count":7,"area":"lr"},{"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":"2507.10069","title":"ElasticMM: Efficient Multimodal LLMs Serving with Elastic Multimodal Parallelism","created":"2025-07-14","cited_by_count":7,"area":"mllm"},{"id":"2510.23479","title":"MergeMix: A Unified Augmentation Paradigm for Visual and Multi-Modal Understanding","created":"2025-10-27","cited_by_count":7,"area":"mllm"},{"id":"2510.19496","title":"CARES: Context-Aware Resolution Selector for VLMs","created":"2025-10-22","cited_by_count":6,"area":"mllm"},{"id":"2511.00141","title":"FLoC: Facility Location-Based Efficient Visual Token Compression for Long Video Understanding","created":"2025-10-31","cited_by_count":6,"area":"lr"},{"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":"2504.04540","title":"The Point, the Vision and the Text: Does Point Cloud Boost Spatial Reasoning of Large Language Models? A Bias-Controlled Study","created":"2025-04-06","cited_by_count":5,"area":"lr"},{"id":"2505.13946","title":"Visual Instruction Bottleneck Tuning","created":"2025-05-20","cited_by_count":5,"area":"mllm"},{"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":"2506.19072","title":"HAWAII: Hierarchical Visual Knowledge Transfer for Efficient Vision-Language Models","created":"2025-06-23","cited_by_count":5,"area":"mllm"},{"id":"2508.00955","title":"From Generator to Embedder: Harnessing Innate Abilities of Multimodal LLMs via Building Zero-Shot Discriminative Embedding Model","created":"2025-08-01","cited_by_count":5,"area":"mllm"},{"id":"2509.23928","title":"HiViS: Hiding Visual Tokens from the Drafter for Speculative Decoding in Vision-Language Models","created":"2025-09-28","cited_by_count":5,"area":"mllm"},{"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":"2602.09483","title":"Beyond Next-Token Alignment: Distilling Multimodal Large Language Models via Token Interactions","created":"2026-02-10","cited_by_count":5,"area":"mllm"},{"id":"2602.22963","title":"FactGuard: Agentic Video Misinformation Detection via Reinforcement Learning","created":"2026-02-26","cited_by_count":5,"area":"lr"},{"id":"2606.20280","title":"ELVA: Exploring Ranking-Driven Universal Multimodal Retrieval","created":"2026-06-18","cited_by_count":5,"area":"mllm"},{"id":"2503.10665","title":"Small Vision-Language Models: A Survey on Compact Architectures and Techniques","created":"2025-03-09","cited_by_count":4,"area":"mllm"},{"id":"2504.04653","title":"LEO-MINI: An Efficient Multimodal Large Language Model using Conditional Token Reduction and Mixture of Multi-Modal Experts","created":"2025-04-07","cited_by_count":4,"area":"mllm"},{"id":"2508.17807","title":"Attention Debiasing for Token Pruning in Vision Language Models","created":"2025-08-25","cited_by_count":4,"area":"mllm"},{"id":"2509.11815","title":"SpecVLM: Fast Speculative Decoding in Vision-Language Models","created":"2025-09-15","cited_by_count":4,"area":"mllm"},{"id":"2510.11129","title":"video-SALMONN S: Memory-Enhanced Streaming Audio-Visual LLM","created":"2025-10-13","cited_by_count":4,"area":null},{"id":"2510.14624","title":"Efficient Video Sampling: Pruning Temporally Redundant Tokens for Faster VLM Inference","created":"2025-10-16","cited_by_count":4,"area":"mllm"},{"id":"2510.24331","title":"What do vision-language models see in the context? Investigating multimodal in-context learning","created":"2025-10-28","cited_by_count":4,"area":"mllm"},{"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":"2602.18702","title":"Think with Grounding: Curriculum Reinforced Reasoning with Video Grounding for Long Video Understanding","created":"2026-02-21","cited_by_count":4,"area":"lr"},{"id":"2602.23959","title":"Thinking with Images as Continuous Actions: Numerical Visual Chain-of-Thought","created":"2026-02-27","cited_by_count":4,"area":"lr"},{"id":"2604.18260","title":"Geometry-Guided 3D Visual Token Pruning for Video-Language Models","created":"2026-04-20","cited_by_count":4,"area":"mllm"},{"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":"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":"2504.19627","title":"VCM: Vision Concept Modeling Based on Implicit Contrastive Learning with Vision-Language Instruction Fine-Tuning","created":"2025-04-28","cited_by_count":3,"area":"lr"},{"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":"2506.07138","title":"Learning Compact Vision Tokens for Efficient Large Multimodal Models","created":"2025-06-08","cited_by_count":3,"area":"mllm"},{"id":"2506.13564","title":"State-Space Hierarchical Compression with Gated Attention and Learnable Sampling for Hour-Long Video Understanding in Large Multimodal Models","created":"2025-06-16","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":"2508.06038","title":"Fourier Compressor: Frequency-Domain Visual Token Compression for Vision-Language Models","created":"2025-08-08","cited_by_count":3,"area":"mllm"},{"id":"2508.18381","title":"Language-Specific Layer Matters: Efficient Multilingual Enhancement for Large Vision-Language Models","created":"2025-08-25","cited_by_count":3,"area":"mllm"},{"id":"2602.05275","title":"Magic-MM-Embedding: Towards Visual-Token-Efficient Universal Multimodal Embedding with MLLMs","created":"2026-02-05","cited_by_count":3,"area":"mllm"},{"id":"2603.07990","title":"MJ1: Multimodal Judgment via Grounded Verification","created":"2026-03-09","cited_by_count":3,"area":null},{"id":"2603.15167","title":"Question-guided Visual Compression with Memory Feedback for Long-Term Video Understanding","created":"2026-03-16","cited_by_count":3,"area":"mllm"},{"id":"2603.21232","title":"QMoP: Query Guided Mixture-of-Projector for Efficient Visual Token Compression","created":"2026-03-22","cited_by_count":3,"area":"mllm"},{"id":"2608.09682","title":"Thinking With Tools, Not With Pixels: Tool Calls as Text Scaffolds for Visual Reasoning","created":"2026-08-10","cited_by_count":3,"area":"lr"},{"id":"2503.06794","title":"Does Acceleration Cause Hidden Instability in Vision Language Models? Uncovering Instance-Level Divergence Through a Large-Scale Empirical Study","created":"2025-03-09","cited_by_count":2,"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":"2506.03928","title":"Vision Remember: Recovering Visual Information in Efficient LVLM with Vision Feature Resampling","created":"2025-06-04","cited_by_count":2,"area":"mllm"},{"id":"2506.16112","title":"AutoV: Loss-Oriented Ranking for Visual Prompt Retrieval in LVLMs","created":"2025-06-19","cited_by_count":2,"area":"mllm"},{"id":"2509.00969","title":"Seeing More, Saying More: Lightweight Language Experts are Dynamic Video Token Compressors","created":"2025-08-31","cited_by_count":2,"area":"inference"},{"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":"2510.08789","title":"Q-Router: Agentic Video Quality Assessment with Expert Model Routing and Artifact Localization","created":"2025-10-09","cited_by_count":2,"area":"agents"},{"id":"2512.01949","title":"Script: Graph-Structured and Query-Conditioned Semantic Token Pruning for Multimodal Large Language Models","created":"2025-12-01","cited_by_count":2,"area":"mllm"},{"id":"2512.18496","title":"Adaptive-VoCo: Complexity-Aware Visual Token Compression for Vision-Language Models","created":"2025-12-20","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":"2602.04509","title":"Model-Dowser: Data-Free Importance Probing to Mitigate Catastrophic Forgetting in Multimodal Large Language Models","created":"2026-02-04","cited_by_count":2,"area":"mllm"},{"id":"2602.04864","title":"When LLaVA Meets Objects: Token Composition for Vision-Language-Models","created":"2026-02-04","cited_by_count":2,"area":"mllm"},{"id":"2602.06034","title":"V-Retrver: Evidence-Driven Agentic Reasoning for Universal Multimodal Retrieval","created":"2026-02-05","cited_by_count":2,"area":"lr"},{"id":"2603.26486","title":"ClipTTT: CLIP-Guided Test-Time Training Helps LVLMs See Better","created":"2026-03-27","cited_by_count":2,"area":"mllm"}],"next_cursor":"100"}