{"total":132,"rows":[{"id":"2503.06287","title":"Your Large Vision-Language Model Only Needs A Few Attention Heads For Visual Grounding","created":"2025-03-08","cited_by_count":83,"area":"mllm"},{"id":"2505.15269","title":"LiveVLM: Efficient Online Video Understanding via Streaming-Oriented KV Cache and Retrieval","created":"2025-05-21","cited_by_count":54,"area":"inference"},{"id":"2508.12587","title":"Multimodal Chain of Continuous Thought for Latent-Space Reasoning in Vision-Language Models","created":"2025-08-18","cited_by_count":32,"area":"lr"},{"id":"2507.19024","title":"A Survey of Multimodal Hallucination Evaluation and Detection","created":"2025-07-25","cited_by_count":27,"area":"mllm"},{"id":"2510.08510","title":"To Sink or Not to Sink: Visual Information Pathways in Large Vision-Language Models","created":"2025-10-09","cited_by_count":20,"area":"mllm"},{"id":"2510.00054","title":"HiDe: Rethinking The Zoom-IN method in High Resolution MLLMs via Hierarchical Decoupling","created":"2025-09-28","cited_by_count":17,"area":"lr"},{"id":"2509.16087","title":"See&Trek: Training-Free Spatial Prompting for Multimodal Large Language Model","created":"2025-09-19","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":"2511.14159","title":"MVI-Bench: A Comprehensive Benchmark for Evaluating Robustness to Misleading Visual Inputs in LVLMs","created":"2025-11-18","cited_by_count":15,"area":"mllm"},{"id":"2506.05551","title":"When Semantics Mislead Vision: Mitigating Large Multimodal Models Hallucinations in Scene Text Spotting and Understanding","created":"2025-06-05","cited_by_count":12,"area":"mllm"},{"id":"2603.06001","title":"Restoring Linguistic Grounding in VLA Models via Train-Free Attention Recalibration","created":"2026-03-06","cited_by_count":12,"area":"vla"},{"id":"2508.19972","title":"GLSim: Detecting Object Hallucinations in LVLMs via Global-Local Similarity","created":"2025-08-27","cited_by_count":11,"area":"mllm"},{"id":"2509.15178","title":"Unleashing the Potential of Multimodal LLMs for Zero-Shot Spatio-Temporal Video Grounding","created":"2025-09-18","cited_by_count":9,"area":"mllm"},{"id":"2509.16944","title":"Catching the Details: Self-Distilled RoI Predictors for Fine-Grained MLLM Perception","created":"2025-09-21","cited_by_count":9,"area":"mllm"},{"id":"2511.20032","title":"Tell Model Where to Look: Mitigating Hallucinations in MLLMs by Vision-Guided Attention","created":"2025-11-25","cited_by_count":9,"area":null},{"id":"2601.20279","title":"Hallucination Begins Where Saliency Drops","created":"2026-01-28","cited_by_count":9,"area":"mllm"},{"id":"2510.09017","title":"Value-State Gated Attention for Mitigating Extreme-Token Phenomena in Transformers","created":"2025-10-10","cited_by_count":8,"area":null},{"id":"2602.21445","title":"VLA Knows Its Limits: Adaptive Execution Horizons for Robot Policies","created":"2026-02-24","cited_by_count":8,"area":"vla"},{"id":"2603.17809","title":"Fine-Grained Post-Training Quantization for Large Vision Language Models with Quantization-Aware Integrated Gradients","created":"2026-03-18","cited_by_count":8,"area":"mllm"},{"id":"2504.09456","title":"Don't Deceive Me: Mitigating Gaslighting through Attention Reallocation in LMMs","created":"2025-04-13","cited_by_count":7,"area":"mllm"},{"id":"2510.16596","title":"SHIELD: Suppressing Hallucinations In LVLM Encoders via Bias and Vulnerability Defense","created":"2025-10-18","cited_by_count":7,"area":"mllm"},{"id":"2511.12738","title":"Direct Visual Grounding by Directing Attention of Visual Tokens","created":"2025-11-16","cited_by_count":7,"area":"mllm"},{"id":"2512.18813","title":"Revealing Perception and Generation Dynamics in LVLMs: Mitigating Hallucinations via Validated Dominance Correction","created":"2025-12-21","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":"2506.13060","title":"Rethinking Explainability in the Era of Multimodal AI","created":"2025-06-16","cited_by_count":6,"area":null},{"id":"2511.17722","title":"Can Vision-Language Models Count? A Synthetic Benchmark and Analysis of Attention-Based Interventions","created":"2025-11-21","cited_by_count":6,"area":"mllm"},{"id":"2603.14337","title":"On the Nature of Attention Sink that Shapes Decoding Strategy in Omni-LLMs","created":"2026-03-15","cited_by_count":6,"area":"lr"},{"id":"2604.06912","title":"Q-Zoom: Query-Aware Adaptive Perception for Efficient Multimodal Large Language Models","created":"2026-04-08","cited_by_count":6,"area":"mllm"},{"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":"2510.16785","title":"Segmentation as A Plug-and-Play Capability for Frozen Multimodal LLMs","created":"2025-10-19","cited_by_count":5,"area":"mllm"},{"id":"2510.22067","title":"Capturing Gaze Shifts for Guidance: Cross-Modal Fusion Enhancement for VLM Hallucination Mitigation","created":"2025-10-24","cited_by_count":5,"area":"mllm"},{"id":"2512.07730","title":"SAVE: Sparse Autoencoder-Driven Visual Information Enhancement for Mitigating Object Hallucination","created":"2025-12-08","cited_by_count":5,"area":"mllm"},{"id":"2601.00535","title":"FreeText: Training-Free Text Rendering in Diffusion Transformers via Attention Localization and Spectral Glyph Injection","created":"2026-01-02","cited_by_count":5,"area":"diffusion"},{"id":"2602.04268","title":"KVSmooth: Mitigating Hallucination in Multi-modal Large Language Models through Key-Value Smoothing","created":"2026-02-04","cited_by_count":5,"area":"mllm"},{"id":"2603.14184","title":"Deeper Thought, Weaker Aim: Understanding and Mitigating Perceptual Impairment during Reasoning in Multimodal Large Language Models","created":"2026-03-15","cited_by_count":5,"area":"lr"},{"id":"2605.05668","title":"Large Vision-Language Models Get Lost in Attention","created":"2026-05-07","cited_by_count":5,"area":"mllm"},{"id":"2605.10815","title":"Probing Cross-modal Information Hubs in Audio-Visual LLMs","created":"2026-05-11","cited_by_count":5,"area":null},{"id":"2605.19660","title":"OScaR: The Occam's Razor for Extreme KV Cache Quantization in LLMs and Beyond","created":"2026-05-19","cited_by_count":5,"area":"inference"},{"id":"2503.10779","title":"The Power of One: A Single Example is All it Takes for Segmentation in VLMs","created":"2025-03-13","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":"2509.07864","title":"Tracing and Mitigating Hallucinations in Multimodal LLMs via Dynamic Attention Localization","created":"2025-09-09","cited_by_count":4,"area":"mllm"},{"id":"2510.10285","title":"Reallocating Attention Across Layers to Reduce Multimodal Hallucination","created":"2025-10-11","cited_by_count":4,"area":"lr"},{"id":"2510.13698","title":"Attention Misses Visual Risk: Risk-Adaptive Steering for Multimodal Safety Alignment","created":"2025-10-15","cited_by_count":4,"area":"alignment"},{"id":"2512.01248","title":"TRivia: Self-supervised Fine-tuning of Vision-Language Models for Table Recognition","created":"2025-12-01","cited_by_count":4,"area":"mllm"},{"id":"2602.05228","title":"Surgery: Mitigating Harmful Fine-Tuning for Large Language Models via Attention Sink","created":"2026-02-05","cited_by_count":4,"area":"alignment"},{"id":"2602.12533","title":"AMPS: Adaptive Modality Preference Steering via Functional Entropy","created":"2026-02-13","cited_by_count":4,"area":"mllm"},{"id":"2603.14935","title":"Video-CoE: Reinforcing Video Event Prediction via Chain of Events","created":"2026-03-16","cited_by_count":4,"area":null},{"id":"2603.29676","title":"A Comprehensive Information-Decomposition Analysis of Large Vision-Language Models","created":"2026-03-31","cited_by_count":4,"area":"mllm"},{"id":"2604.03316","title":"When Sinks Help or Hurt: Unified Framework for Attention Sink in Large Vision-Language Models","created":"2026-04-01","cited_by_count":4,"area":"mllm"},{"id":"2605.30010","title":"EarlyTom: Early Token Compression Completes Fast Video Understanding","created":"2026-05-28","cited_by_count":4,"area":"inference"},{"id":"2606.05843","title":"Mechanistic Insights into Functional Sparsity in Multimodal LLMs via CoRe Heads","created":"2026-06-04","cited_by_count":4,"area":"mllm"},{"id":"2607.19139","title":"Text Template Tokens Are Implicit Semantic Registers in Diffusion Transformers","created":"2026-07-21","cited_by_count":4,"area":"diffusion"},{"id":"2608.07302","title":"Same Attention, Different Truths: Put Logit-Lens over Visual Attention to Detect and Mitigate LVLM Object Hallucination","created":"2026-08-07","cited_by_count":4,"area":"mllm"},{"id":"2505.17812","title":"Seeing It or Not? Interpretable Vision-aware Latent Steering to Mitigate Object Hallucinations","created":"2025-05-23","cited_by_count":3,"area":"mllm"},{"id":"2511.17793","title":"Attention Guided Alignment in Efficient Vision-Language Models","created":"2025-11-21","cited_by_count":3,"area":"mllm"},{"id":"2601.07645","title":"PlaM: Training-Free Plateau-Guided Model Merging for Better Visual Grounding in MLLMs","created":"2026-01-12","cited_by_count":3,"area":"lr"},{"id":"2602.00621","title":"Towards Interpretable Hallucination Analysis and Mitigation in LVLMs via Contrastive Neuron Steering","created":"2026-01-31","cited_by_count":3,"area":"mechinterp"},{"id":"2602.17186","title":"Focusing Where Vision Matters: Selective Training for Large Vision Language Models via Visual Information Gain","created":"2026-02-19","cited_by_count":3,"area":"mllm"},{"id":"2604.15809","title":"Aligning What Vision-Language Models See and Perceive with Adaptive Information Flow","created":"2026-04-17","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":"2607.15418","title":"DrawingVQA: A Real-World Benchmark for Multi-Depth Visual-Textual Reasoning on Construction Drawings","created":"2026-07-16","cited_by_count":3,"area":"lr"},{"id":"2509.12897","title":"Cross-Layer Vision Smoothing: Enhancing Visual Understanding via Sustained Focus on Key Objects in Large Vision-Language Models","created":"2025-09-16","cited_by_count":2,"area":"mllm"},{"id":"2509.22650","title":"RefAM: Attention Magnets for Zero-Shot Referral Segmentation","created":"2025-09-26","cited_by_count":2,"area":"diffusion"},{"id":"2510.04547","title":"Activation Quantization of Vision Encoders Needs Prefixing Registers","created":"2025-10-06","cited_by_count":2,"area":"mllm"},{"id":"2510.19592","title":"Decomposed Attention Fusion in MLLMs for Training-Free Video Reasoning Segmentation","created":"2025-10-22","cited_by_count":2,"area":"lr"},{"id":"2602.17419","title":"EAGLE: Expert-Augmented Attention Guidance for Tuning-Free Industrial Anomaly Detection in Multimodal Large Language Models","created":"2026-02-19","cited_by_count":2,"area":"mllm"},{"id":"2603.27898","title":"SAGE: Sink-Aware Grounded Decoding for Multimodal Hallucination Mitigation","created":"2026-03-29","cited_by_count":2,"area":"mllm"},{"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":"2604.21911","title":"When Prompts Override Vision: Prompt-Induced Hallucinations in LVLMs","created":"2026-04-23","cited_by_count":2,"area":"mllm"},{"id":"2605.11567","title":"Dynamic Execution Commitment of Vision-Language-Action Models","created":"2026-05-12","cited_by_count":2,"area":"vla"},{"id":"2605.17887","title":"Attention Sinks and Outliers in Attention Residuals","created":"2026-05-18","cited_by_count":2,"area":null},{"id":"2605.25244","title":"Inference Time Optimization with Confidence Dynamics","created":"2026-05-24","cited_by_count":2,"area":"lr"},{"id":"2605.25799","title":"Addressing Exacerbated Attention Sink for Source-Free Cross-Domain Few-Shot Learning","created":"2026-05-25","cited_by_count":2,"area":"mllm"},{"id":"2606.09303","title":"Reason Twice: Segmentation via Candidate Discovery and Comparative Reasoning","created":"2026-06-08","cited_by_count":2,"area":"lr"},{"id":"2606.31054","title":"ADAPT: Attention Dynamics Alignment with Preference Tuning for Faithful MLLMs","created":"2026-06-30","cited_by_count":2,"area":"mllm"},{"id":"2508.01653","title":"MAP: Mitigating Hallucinations in Large Vision-Language Models with Map-Level Attention Processing","created":"2025-08-03","cited_by_count":1,"area":"mllm"},{"id":"2508.02645","title":"Evaluating Variance in Visual Question Answering Benchmarks","created":"2025-08-04","cited_by_count":1,"area":"mllm"},{"id":"2601.13707","title":"Attention-space Contrastive Guidance for Efficient Hallucination Mitigation in LVLMs","created":"2026-01-20","cited_by_count":1,"area":null},{"id":"2602.00344","title":"When RAG Hurts: Diagnosing and Mitigating Attention Distraction in Retrieval-Augmented LVLMs","created":"2026-01-30","cited_by_count":1,"area":"mllm"},{"id":"2602.01984","title":"Enhancing Multi-Image Understanding through Delimiter Token Scaling","created":"2026-02-02","cited_by_count":1,"area":"mllm"},{"id":"2602.04304","title":"Beyond Static Cropping: Layer-Adaptive Visual Localization and Decoding Enhancement","created":"2026-02-04","cited_by_count":1,"area":"mllm"},{"id":"2602.09825","title":"SAKED: Mitigating Hallucination in Large Vision-Language Models via Stability-Aware Knowledge Enhanced Decoding","created":"2026-02-10","cited_by_count":1,"area":"mllm"},{"id":"2603.18453","title":"Learning Consistent Temporal Grounding between Related Tasks in Sports Coaching","created":"2026-03-19","cited_by_count":1,"area":null},{"id":"2603.22815","title":"Focus, Don't Prune: Identifying Instruction-Relevant Regions for Information-Rich Image Understanding","created":"2026-03-24","cited_by_count":1,"area":"lr"},{"id":"2604.10999","title":"TraversalBench: Challenging Paths to Follow for Vision Language Models","created":"2026-04-13","cited_by_count":1,"area":"mllm"},{"id":"2605.08453","title":"Sink vs. diagonal patterns as mechanisms for attention switch and oversmoothing prevention","created":"2026-05-08","cited_by_count":1,"area":null},{"id":"2605.18359","title":"RAVE: Re-Allocating Visual Attention in Large Multimodal Models","created":"2026-05-18","cited_by_count":1,"area":"mllm"},{"id":"2605.21954","title":"MLLMs Know When Before Speaking: Revealing and Recovering Temporal Grounding via Attention Cues","created":"2026-05-21","cited_by_count":1,"area":"mllm"},{"id":"2606.10147","title":"From Senses to Decisions: The Information Flow of Auditory and Visual Perception in Multimodal LLMs","created":"2026-06-08","cited_by_count":1,"area":"mllm"},{"id":"2606.15821","title":"The Truth Stays in the Family: Enhancing Contextual Grounding via Inherited Truthful Heads in Model Lineages","created":"2026-06-14","cited_by_count":1,"area":"mllm"},{"id":"2606.28322","title":"PerceptionRubrics: Calibrating Multimodal Evaluation to Human Perception","created":"2026-06-26","cited_by_count":1,"area":null},{"id":"2607.01707","title":"LASER: A Corrective Lens for LVLMs via Visual Attention Preservation and Sink Suppression","created":"2026-07-02","cited_by_count":1,"area":"lr"},{"id":"2607.17884","title":"ST-Veto: Spatio-Temporal Token Veto for Diffusion MLLMs via Taylor Prediction and Visual Grounding","created":"2026-07-20","cited_by_count":1,"area":"lr"},{"id":"2507.07685","title":"Rationale-Enhanced Decoding for Multi-modal Chain-of-Thought","created":"2025-07-10","cited_by_count":0,"area":"lr"},{"id":"2507.09071","title":"BlindSight: Harnessing Sparsity for Efficient Vision-Language Models","created":"2025-07-11","cited_by_count":0,"area":"mllm"},{"id":"2509.08266","title":"Examining Vision Language Models through Multi-dimensional Experiments with Vision and Text Features","created":"2025-09-10","cited_by_count":0,"area":"mllm"},{"id":"2512.19219","title":"Selective LoRA for Visual Tokens and Attention Heads","created":"2025-12-22","cited_by_count":0,"area":"mllm"},{"id":"2602.01530","title":"Logit Lens Supervision for Patch-Level Explanations in Vision-Language Models","created":"2026-02-02","cited_by_count":0,"area":"mllm"},{"id":"2602.02004","title":"ClueTracer: Question-to-Vision Clue Tracing for Training-Free Hallucination Suppression in Multimodal Reasoning","created":"2026-02-02","cited_by_count":0,"area":"lr"},{"id":"2602.13310","title":"Visual Para-Thinker: Divide-and-Conquer Reasoning for Visual Comprehension","created":"2026-02-10","cited_by_count":0,"area":"lr"}],"next_cursor":"100"}