{"total":84,"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":"2503.02175","title":"DivPrune: Diversity-based Visual Token Pruning for Large Multimodal Models","created":"2025-03-04","cited_by_count":181,"area":"mllm"},{"id":"2412.01818","title":"Beyond Text-Visual Attention: Exploiting Visual Cues for Effective Token Pruning in VLMs","created":"2024-12-02","cited_by_count":157,"area":"mllm"},{"id":"2410.03051","title":"AuroraCap: Efficient, Performant Video Detailed Captioning and a New Benchmark","created":"2024-10-04","cited_by_count":140,"area":null},{"id":"2502.13130","title":"Magma: A Foundation Model for Multimodal AI Agents","created":"2025-02-18","cited_by_count":139,"area":"agents"},{"id":"2410.10818","title":"TemporalBench: Benchmarking Fine-grained Temporal Understanding for Multimodal Video Models","created":"2024-10-14","cited_by_count":97,"area":null},{"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":"2412.00447","title":"ATP-LLaVA: Adaptive Token Pruning for Large Vision Language Models","created":"2024-11-30","cited_by_count":89,"area":"mllm"},{"id":"2412.13303","title":"FastVLM: Efficient Vision Encoding for Vision Language Models","created":"2024-12-17","cited_by_count":77,"area":"mllm"},{"id":"2409.20566","title":"MM1.5: Methods, Analysis & Insights from Multimodal LLM Fine-tuning","created":"2024-09-30","cited_by_count":76,"area":"mllm"},{"id":"2503.13111","title":"MM-Spatial: Exploring 3D Spatial Understanding in Multimodal LLMs","created":"2025-03-17","cited_by_count":73,"area":"mllm"},{"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,"area":"inference"},{"id":"2503.13646","title":"Omnia de EgoTempo: Benchmarking Temporal Understanding of Multi-Modal LLMs in Egocentric Videos","created":"2025-03-17","cited_by_count":44,"area":"mllm"},{"id":"2411.02393","title":"Adaptive Length Image Tokenization via Recurrent Allocation","created":"2024-11-04","cited_by_count":43,"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":"2509.18095","title":"MetaEmbed: Scaling Multimodal Retrieval at Test-Time with Flexible Late Interaction","created":"2025-09-22","cited_by_count":39,"area":null},{"id":"2406.19101","title":"DocKylin: A Large Multimodal Model for Visual Document Understanding with Efficient Visual Slimming","created":"2024-06-27","cited_by_count":35,"area":"mllm"},{"id":"2503.01776","title":"Beyond Matryoshka: Revisiting Sparse Coding for Adaptive Representation","created":"2025-03-03","cited_by_count":26,"area":null},{"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":"2501.03120","title":"CAT: Content-Adaptive Image Tokenization","created":"2025-01-06","cited_by_count":21,"area":null},{"id":"2410.13861","title":"PUMA: Empowering Unified MLLM with Multi-granular Visual Generation","created":"2024-10-17","cited_by_count":20,"area":null},{"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":"2602.02951","title":"N\\\"uwa: Mending the Spatial Integrity Torn by VLM Token Pruning","created":"2026-02-03","cited_by_count":15,"area":"mllm"},{"id":"2602.04215","title":"OAT: Ordered Action Tokenization","created":"2026-02-04","cited_by_count":15,"area":null},{"id":"2501.05037","title":"LongViTU: Instruction Tuning for Long-Form Video Understanding","created":"2025-01-09","cited_by_count":13,"area":null},{"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":"2504.00557","title":"Efficient LLaMA-3.2-Vision by Trimming Cross-attended Visual Features","created":"2025-04-01","cited_by_count":10,"area":"mllm"},{"id":"2410.02745","title":"AVG-LLaVA: An Efficient Large Multimodal Model with Adaptive Visual Granularity","created":"2024-09-20","cited_by_count":9,"area":"mllm"},{"id":"2411.11066","title":"TS-LLaVA: Constructing Visual Tokens through Thumbnail-and-Sampling for Training-Free Video Large Language Models","created":"2024-11-17","cited_by_count":9,"area":"mllm"},{"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":"2507.07997","title":"MGVQ: Could VQ-VAE Beat VAE? A Generalizable Tokenizer with Multi-group Quantization","created":"2025-07-10","cited_by_count":9,"area":null},{"id":"2506.06277","title":"ExAct: A Video-Language Benchmark for Expert Action Analysis","created":"2025-06-06","cited_by_count":8,"area":null},{"id":"2511.19820","title":"CropVLM: Learning to Zoom for Fine-Grained Vision-Language Perception","created":"2025-11-25","cited_by_count":8,"area":"mllm"},{"id":"2410.06718","title":"MatMamba: A Matryoshka State Space Model","created":"2024-10-09","cited_by_count":7,"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":"2509.26520","title":"Training Matryoshka Mixture-of-Experts for Elastic Inference-Time Expert Utilization","created":"2025-09-30","cited_by_count":7,"area":"moe"},{"id":"2512.18910","title":"Delta-LLaVA: Base-then-Specialize Alignment for Token-Efficient Vision-Language Models","created":"2025-12-21","cited_by_count":7,"area":"lr"},{"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":"2503.14237","title":"Make Your Training Flexible: Towards Deployment-Efficient Video Models","created":"2025-03-18","cited_by_count":6,"area":null},{"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":"2505.15755","title":"Exploring The Visual Feature Space for Multimodal Neural Decoding","created":"2025-05-21","cited_by_count":4,"area":null},{"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":"2510.04136","title":"MoME: Mixture of Matryoshka Experts for Audio-Visual Speech Recognition","created":"2025-10-05","cited_by_count":4,"area":"moe"},{"id":"2510.17700","title":"Elastic ViTs from Pretrained Models without Retraining","created":"2025-10-20","cited_by_count":4,"area":null},{"id":"2511.07253","title":"Omni-AVSR: Towards Unified Multimodal Speech Recognition with Large Language Models","created":"2025-11-10","cited_by_count":4,"area":null},{"id":"2603.05950","title":"Energy-Driven Adaptive Visual Token Pruning for Efficient Vision-Language Models","created":"2026-03-06","cited_by_count":4,"area":"mllm"},{"id":"2605.13803","title":"EvoGround: Self-Evolving Video Agents for Video Temporal Grounding","created":"2026-05-13","cited_by_count":4,"area":null},{"id":"2412.08771","title":"LLaVA-Zip: Adaptive Visual Token Compression with Intrinsic Image Information","created":"2024-12-11","cited_by_count":3,"area":"mllm"},{"id":"2503.04444","title":"ToFu: Visual Tokens Reduction via Fusion for Multi-modal, Multi-patch, Multi-image Task","created":"2025-03-06","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":"2506.00835","title":"SynPO: Synergizing Descriptiveness and Preference Optimization for Video Detailed Captioning","created":"2025-06-01","cited_by_count":3,"area":"alignment"},{"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":"2510.15050","title":"DRIFT: Transferring Reasoning Priors for Efficient MLLM Fine-Tuning","created":"2025-10-16","cited_by_count":3,"area":"lr"},{"id":"2602.20205","title":"OTPrune: Distribution-Aligned Visual Token Pruning via Optimal Transport","created":"2026-02-22","cited_by_count":3,"area":"lr"},{"id":"2604.07812","title":"HAWK: Head Importance-Aware Visual Token Pruning in Multimodal Models","created":"2026-04-09","cited_by_count":3,"area":"mllm"},{"id":"2606.12412","title":"Reroute, Don't Remove: Recoverable Visual Token Routing for Vision-Language Models","created":"2026-06-10","cited_by_count":3,"area":"mllm"},{"id":"2503.11794","title":"Semantic-Clipping: Efficient Vision-Language Modeling with Semantic-Guidedd Visual Selection","created":"2025-03-14","cited_by_count":2,"area":"mllm"},{"id":"2503.21757","title":"Fwd2Bot: LVLM Visual Token Compression with Double Forward Bottleneck","created":"2025-03-27","cited_by_count":2,"area":"mllm"},{"id":"2505.10940","title":"Who You Are Matters: Bridging Topics and Social Roles via LLM-Enhanced Logical Recommendation","created":"2025-05-16","cited_by_count":2,"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":"2602.04864","title":"When LLaVA Meets Objects: Token Composition for Vision-Language-Models","created":"2026-02-04","cited_by_count":2,"area":"mllm"},{"id":"2608.04132","title":"RUTA: Principled Visual Token Allocation via Rate-Utility Optimization","created":"2026-08-04","cited_by_count":2,"area":"lr"},{"id":"2501.10318","title":"HiMix: Reducing Computational Complexity in Large Vision-Language Models","created":"2025-01-17","cited_by_count":1,"area":"mllm"},{"id":"2508.11886","title":"EVTP-IVS: Effective Visual Token Pruning For Unifying Instruction Visual Segmentation In Multi-Modal Large Language Models","created":"2025-08-16","cited_by_count":1,"area":"mllm"},{"id":"2603.11220","title":"Frequency-Modulated Visual Restoration for Matryoshka Large Multimodal Models","created":"2026-03-11","cited_by_count":1,"area":"mllm"},{"id":"2603.12046","title":"Dr. SHAP-AV: Decoding Relative Modality Contributions via Shapley Attribution in Audio-Visual Speech Recognition","created":"2026-03-12","cited_by_count":1,"area":null},{"id":"2603.13349","title":"MURE: Hierarchical Multi-Resolution Encoding via Vision-Language Models for Visual Document Retrieval","created":"2026-03-07","cited_by_count":1,"area":"mllm"},{"id":"2603.18004","title":"Unified Spatio-Temporal Token Scoring for Efficient Video VLMs","created":"2026-03-18","cited_by_count":1,"area":"mllm"},{"id":"2605.30126","title":"PARCEL: Pool-Anchored Resampling with Conditioned Elastic Queries for Efficient Vision-Language Understanding","created":"2026-05-28","cited_by_count":1,"area":"mllm"},{"id":"2608.05707","title":"One Ranking, Any Budget: Matryoshka Evidence-to-Context Frame Selection for Long-Video Understanding","created":"2026-08-06","cited_by_count":1,"area":"mllm"},{"id":"2608.29285","title":"3D-MRL: Nested Multimodal 3D Representations via Matryoshka Representation Learning","created":"2026-08-29","cited_by_count":1,"area":"mllm"},{"id":"2508.16527","title":"Towards Open World Detection: A Survey","created":"2025-08-22","cited_by_count":0,"area":null},{"id":"2510.24672","title":"Eigenfunction Extraction for Ordered Representation Learning","created":"2025-10-28","cited_by_count":0,"area":null},{"id":"2602.00946","title":"ConsensusDrop: Fusing Visual and Cross-Modal Saliency for Efficient Vision Language Models","created":"2026-02-01","cited_by_count":0,"area":"mllm"},{"id":"2605.09160","title":"Objective-Specific Privileged Bases via Full-Prefix Matryoshka Learning","created":"2026-05-09","cited_by_count":0,"area":null},{"id":"2607.13500","title":"Attention-Free and Lightweight Token Reduction for Efficient Vision-Language Models","created":"2026-07-15","cited_by_count":0,"area":"mllm"},{"id":"2607.23373","title":"UltraViT: Latency-Optimized On-device Vision Encoder for Large Vision-Language Models","created":"2026-07-25","cited_by_count":0,"area":"mllm"},{"id":"2609.10297","title":"TRACE: Trajectory-robust Admission with Evidence Ordering for Efficient GUI Agents","created":"2026-09-09","cited_by_count":0,"area":"agents"},{"id":"2609.10346","title":"Beyond One-Size-Fits-All: Sample-Adaptive Strategy Routing for Vision Token Pruning in MLLMs","created":"2026-09-09","cited_by_count":0,"area":"mllm"},{"id":"2609.18623","title":"FIVE-VLA: Fast and EffectIVE Autonomous Driving with Recurrent Action Memory","created":"2026-09-16","cited_by_count":0,"area":"vla"},{"id":"2609.33397","title":"CoViST: Visual Token Compression via Composable States","created":"2026-09-27","cited_by_count":0,"area":"inference"},{"id":"2610.07987","title":"VisionWeave: Weaving Elastic Visual Representations as a Native Capability of MLLMs","created":"2026-10-06","cited_by_count":0,"area":"mllm"},{"id":"2610.17355","title":"WIRE: Weight Space Implicit Representation Encoding of Frozen Video LLMs","created":"2026-10-12","cited_by_count":0,"area":"inference"}],"next_cursor":null}