{"total":76,"rows":[{"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":"2503.14905","title":"Spot the Fake: Large Multimodal Model-Based Synthetic Image Detection with Artifact Explanation","created":"2025-03-19","cited_by_count":68,"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":"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":"2505.14454","title":"Video Compression Commander: Plug-and-Play Inference Acceleration for Video Large Language Models","created":"2025-05-20","cited_by_count":38,"area":"inference"},{"id":"2505.19147","title":"Shifting AI Efficiency From Model-Centric to Data-Centric Compression","created":"2025-05-25","cited_by_count":29,"area":"mllm"},{"id":"2509.01552","title":"Variation-aware Vision Token Dropping for Faster Large Vision-Language Models","created":"2025-09-01","cited_by_count":27,"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":"2510.00515","title":"Efficient Multi-modal Large Language Models via Progressive Consistency Distillation","created":"2025-10-01","cited_by_count":22,"area":"mllm"},{"id":"2510.07293","title":"AudioMarathon: A Comprehensive Benchmark for Long-Context Audio Understanding and Efficiency in Audio LLMs","created":"2025-10-08","cited_by_count":22,"area":"inference"},{"id":"2509.23883","title":"DocPruner: A Storage-Efficient Framework for Multi-Vector Visual Document Retrieval via Adaptive Patch-Level Embedding Pruning","created":"2025-09-28","cited_by_count":20,"area":null},{"id":"2508.07871","title":"CATP: Contextually Adaptive Token Pruning for Efficient and Enhanced Multimodal In-Context Learning","created":"2025-08-11","cited_by_count":18,"area":"mllm"},{"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":"2508.13305","title":"Prune2Drive: A Plug-and-Play Framework for Accelerating Vision-Language Models in Autonomous Driving","created":"2025-08-18","cited_by_count":16,"area":"mllm"},{"id":"2505.17670","title":"Towards General Continuous Memory for Vision-Language Models","created":"2025-05-23","cited_by_count":15,"area":"mllm"},{"id":"2510.17777","title":"SparseVILA: Decoupling Visual Sparsity for Efficient VLM Inference","created":"2025-10-20","cited_by_count":15,"area":"mllm"},{"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":"2511.02650","title":"Can Visual Input Be Compressed? A Visual Token Compression Benchmark for Large Multimodal Models","created":"2025-11-04","cited_by_count":13,"area":"mllm"},{"id":"2602.03060","title":"IVC-Prune: Revealing the Implicit Visual Coordinates in LVLMs for Vision Token Pruning","created":"2026-02-03","cited_by_count":12,"area":"mllm"},{"id":"2510.02295","title":"VideoNSA: Native Sparse Attention Scales Video Understanding","created":"2025-10-02","cited_by_count":11,"area":"mllm"},{"id":"2603.07135","title":"The Model Knows Which Tokens Matter: Automatic Token Selection via Noise Gating","created":"2026-03-07","cited_by_count":11,"area":"mllm"},{"id":"2604.12890","title":"Towards Long-horizon Agentic Multimodal Search","created":"2026-04-14","cited_by_count":11,"area":"agents"},{"id":"2602.07574","title":"ViCA: Efficient Multimodal LLMs with Vision-Only Cross-Attention","created":"2026-02-07","cited_by_count":10,"area":"mllm"},{"id":"2602.19549","title":"Sculpting the Vector Space: Towards Efficient Multi-Vector Visual Document Retrieval via Prune-then-Merge Framework","created":"2026-02-23","cited_by_count":10,"area":null},{"id":"2601.19325","title":"Innovator-VL: A Multimodal Large Language Model for Scientific Discovery","created":"2026-01-27","cited_by_count":8,"area":"mllm"},{"id":"2512.19443","title":"D2Pruner: Debiased Importance and Structural Diversity for MLLM Token Pruning","created":"2025-12-22","cited_by_count":7,"area":"mllm"},{"id":"2603.00510","title":"What Do Visual Tokens Really Encode? Uncovering Sparsity and Redundancy in Multimodal Large Language Models","created":"2026-02-28","cited_by_count":7,"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":"2604.17087","title":"EvoComp: Learning Visual Token Compression for Multimodal Large Language Models via Semantic-Guided Evolutionary Labeling","created":"2026-04-18","cited_by_count":5,"area":"mllm"},{"id":"2605.05668","title":"Large Vision-Language Models Get Lost in Attention","created":"2026-05-07","cited_by_count":5,"area":"mllm"},{"id":"2605.10343","title":"EvoStreaming: Your Offline Video Model Is a Natively Streaming Assistant","created":"2026-05-11","cited_by_count":5,"area":null},{"id":"2507.15428","title":"EgoPrune: Efficient Token Pruning for Egomotion Video Reasoning in Embodied Agent","created":"2025-07-21","cited_by_count":4,"area":"lr"},{"id":"2509.21991","title":"ERGO: Efficient High-Resolution Visual Understanding for Vision-Language Models","created":"2025-09-26","cited_by_count":4,"area":"mllm"},{"id":"2604.06871","title":"Do We Need Distinct Representations for Every Speech Token? Unveiling and Exploiting Redundancy in Large Speech Language Models","created":"2026-04-08","cited_by_count":4,"area":null},{"id":"2507.20630","title":"TransPrune: Token Transition Pruning for Efficient Large Vision-Language Model","created":"2025-07-28","cited_by_count":3,"area":"mllm"},{"id":"2509.23663","title":"HIVTP: A Training-Free Method to Improve VLMs Efficiency via Hierarchical Visual Token Pruning Using Middle-Layer-Based Importance Score","created":"2025-09-28","cited_by_count":3,"area":"mllm"},{"id":"2511.07237","title":"The Few Govern the Many:Unveiling Few-Layer Dominance for Time Series Models","created":"2025-11-10","cited_by_count":3,"area":null},{"id":"2603.05663","title":"Keeping the Evidence Chain: Semantic Evidence Allocation for Training-Free Token Pruning in Video Temporal Grounding","created":"2026-03-05","cited_by_count":3,"area":"inference"},{"id":"2605.12309","title":"G$^2$TR: Generation-Guided Visual Token Reduction for Separate-Encoder Unified Multimodal Models","created":"2026-05-12","cited_by_count":3,"area":"inference"},{"id":"2605.25179","title":"Locality Matters for Training-Free Audio Token Compression in Audio-Language Models","created":"2026-05-24","cited_by_count":3,"area":"inference"},{"id":"2606.18681","title":"Moving Beyond Diversity: Visual Token Pruning as Subspace Reconstruction for Efficient VLMs","created":"2026-06-17","cited_by_count":3,"area":"mllm"},{"id":"2606.24156","title":"Accelerating Multimodal Large Language Models with Prior-Corrected Token Reduction","created":"2026-06-23","cited_by_count":3,"area":"mllm"},{"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":"2506.13166","title":"GreedyPrune: Retenting Critical Visual Token Set for Large Vision Language Models","created":"2025-06-16","cited_by_count":2,"area":"mllm"},{"id":"2509.19191","title":"Reading Images Like Texts: Sequential Image Understanding in Vision-Language Models","created":"2025-09-23","cited_by_count":2,"area":"mllm"},{"id":"2510.26213","title":"OmniDocLayout: Towards Diverse Document Layout Generation via Coarse-to-Fine LLM Learning","created":"2025-10-30","cited_by_count":2,"area":null},{"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":"2603.27375","title":"Bridging Visual Representation and Reinforcement Learning from Verifiable Rewards in Large Vision-Language Models","created":"2026-03-28","cited_by_count":2,"area":"lr"},{"id":"2604.03072","title":"MI-Pruner: Crossmodal Mutual Information-guided Token Pruner for Efficient MLLMs","created":"2026-04-03","cited_by_count":2,"area":"mllm"},{"id":"2605.17260","title":"LiteFrame: Efficient Vision Encoders Unlock Frame Scaling in Video LLMs","created":"2026-05-17","cited_by_count":2,"area":null},{"id":"2509.17197","title":"SignalLLM: A General-Purpose LLM Agent Framework for Automated Signal Processing","created":"2025-09-21","cited_by_count":1,"area":"agents"},{"id":"2512.09010","title":"Towards Lossless Ultimate Vision Token Compression for VLMs","created":"2025-12-09","cited_by_count":1,"area":"mllm"},{"id":"2604.11240","title":"Decoupled Similarity for Task-Aware Token Pruning in Large Vision-Language Models","created":"2026-04-13","cited_by_count":1,"area":"mllm"},{"id":"2604.16235","title":"Optimizing Korean-Centric LLMs via Token Pruning","created":"2026-04-17","cited_by_count":1,"area":"inference"},{"id":"2604.17320","title":"Towards Joint Quantization and Token Pruning of Vision-Language Models","created":"2026-04-19","cited_by_count":1,"area":"mllm"},{"id":"2604.19145","title":"ST-Prune: Training-Free Spatio-Temporal Token Pruning for Vision-Language Models in Autonomous Driving","created":"2026-04-21","cited_by_count":1,"area":"mllm"},{"id":"2604.23717","title":"HeadRouter: Dynamic Head-Weight Routing for Task-Adaptive Audio Token Pruning in Large Audio Language Models","created":"2026-04-26","cited_by_count":1,"area":"inference"},{"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":"2606.24165","title":"Spectral Evolution-Guided Token Pruning in Multimodal Large Language Models","created":"2026-06-23","cited_by_count":1,"area":"lr"},{"id":"2606.31903","title":"Attend, Transform, or Silence: Operator-Level Visual Skipping for Efficient Multimodal LLM Inference","created":"2026-06-30","cited_by_count":1,"area":"mllm"},{"id":"2608.00345","title":"ORCA: ORgan-Centroid Aggregation for Training-Free 3D CT Visual Token Compression","created":"2026-07-31","cited_by_count":1,"area":"mllm"},{"id":"2609.01224","title":"S$^2$Prune: Spatially Structured Visual Token Pruning for Multimodal Large Language Models","created":"2026-09-01","cited_by_count":1,"area":"mllm"},{"id":"2511.22599","title":"DisCEdge: Distributed Context Management for Large Language Models at the Edge","created":"2025-11-27","cited_by_count":0,"area":null},{"id":"2603.12208","title":"ForensicZip: More Tokens are Better but Not Necessary in Forensic Vision-Language Models","created":"2026-03-12","cited_by_count":0,"area":"mllm"},{"id":"2604.11627","title":"POINTS-Long: Adaptive Dual-Mode Visual Reasoning in MLLMs","created":"2026-04-13","cited_by_count":0,"area":"lr"},{"id":"2604.12767","title":"CLASP: Class-Adaptive Layer Fusion and Dual-Stage Pruning for Multimodal Large Language Models","created":"2026-04-14","cited_by_count":0,"area":"mllm"},{"id":"2606.21848","title":"Keyless Attention: Value-Space Routing and Value-Only Caching for Efficient Transformers","created":"2026-06-20","cited_by_count":0,"area":"inference"},{"id":"2606.27660","title":"MVPruner: Dynamic Token Pruning for Accelerating Multi-view Vision-Language Models in Autonomous Driving","created":"2026-06-26","cited_by_count":0,"area":"mllm"},{"id":"2608.00077","title":"Beyond Accuracy: Auditing Spatial Provenance in Visual Token Pruning for OCR-Critical MLLM Inference","created":"2026-07-29","cited_by_count":0,"area":"inference"},{"id":"2608.25630","title":"SeVeR: Selective Visual Exposure and Retrieval for 3D Medical Image Question Answering","created":"2026-08-26","cited_by_count":0,"area":null},{"id":"2608.28316","title":"Conditional Visual Evidence Utility: State-Dependent Rank Reversals in Frozen Vision-Language Encoders","created":"2026-08-28","cited_by_count":0,"area":null},{"id":"2608.30163","title":"Doc-REFRAG: Rethinking Multimodal Document Retrieval-Augmented Generation","created":"2026-08-31","cited_by_count":0,"area":"rag"},{"id":"2609.22562","title":"AdaMerge: Tuning-Free Patch Compression for Multi-Vector Visual Document Retrieval","created":"2026-09-18","cited_by_count":0,"area":null},{"id":"2609.34558","title":"ACPruner: Visual Token Pruning as Biased Attention Coverage Maximization in LVLMs","created":"2026-09-28","cited_by_count":0,"area":"mllm"},{"id":"2609.34867","title":"P4Q: Co-designing Token Pruning and Quantization for Vision-Language Model Acceleration","created":"2026-09-28","cited_by_count":0,"area":"mllm"},{"id":"2609.39924","title":"CoVisco: Codec-Native Vision Encoder with Native Token Compression for Unified Image-Video Understanding","created":"2026-09-30","cited_by_count":0,"area":"mllm"}],"next_cursor":null}