{"total":58,"rows":[{"id":"2601.10611","title":"Molmo2: Open Weights and Data for Vision-Language Models with Video Understanding and Grounding","created":"2026-01-15","cited_by_count":139,"area":"mllm"},{"id":"2605.18740","title":"Vision-OPD: Learning to See Fine Details for Multimodal LLMs via On-Policy Self-Distillation","created":"2026-05-18","cited_by_count":77,"area":"mllm"},{"id":"2602.11858","title":"Zooming without Zooming: Region-to-Image Distillation for Fine-Grained Multimodal Perception","created":"2026-02-12","cited_by_count":50,"area":"mllm"},{"id":"2512.02924","title":"AutoNeural: Co-Designing Vision-Language Models for NPU Inference","created":"2025-12-02","cited_by_count":17,"area":"mllm"},{"id":"2511.21662","title":"Multi-Crit: Benchmarking Multimodal Judges on Pluralistic Criteria-Following","created":"2025-11-26","cited_by_count":15,"area":"mllm"},{"id":"2603.28069","title":"MolmoPoint: Better Pointing for VLMs with Grounding Tokens","created":"2026-03-30","cited_by_count":15,"area":"mllm"},{"id":"2607.04884","title":"HunyuanOCR-1.5: Making Lightweight OCR VLMs Faster and Better","created":"2026-07-06","cited_by_count":14,"area":"mllm"},{"id":"2601.22575","title":"PhoStream: Benchmarking Real-World Streaming for Omnimodal Assistants in Mobile Scenarios","created":"2026-01-30","cited_by_count":10,"area":"mllm"},{"id":"2602.07026","title":"Modality Gap-Driven Subspace Alignment Training Paradigm For Multimodal Large Language Models","created":"2026-02-02","cited_by_count":10,"area":"mllm"},{"id":"2602.04802","title":"VISTA-Bench: Do Vision-Language Models Really Understand Visualized Text as Well as Pure Text?","created":"2026-02-04","cited_by_count":8,"area":"mllm"},{"id":"2603.06569","title":"Penguin-VL: Exploring the Efficiency Limits of VLM with LLM-based Vision Encoders","created":"2026-03-06","cited_by_count":7,"area":"mllm"},{"id":"2604.01966","title":"Ego-Grounding for Personalized Question-Answering in Egocentric Videos","created":"2026-04-02","cited_by_count":7,"area":"mllm"},{"id":"2512.05391","title":"LoC-Path: Learning to Compress for Pathology Multimodal Large Language Models","created":"2025-12-05","cited_by_count":6,"area":"mllm"},{"id":"2604.11102","title":"OmniScript: Towards Audio-Visual Script Generation for Long-Form Cinematic Video","created":"2026-04-13","cited_by_count":6,"area":"mllm"},{"id":"2603.22756","title":"MVPBench: A Multi-Video Perception Evaluation Benchmark for Multi-Modal Video Understanding","created":"2026-03-24","cited_by_count":4,"area":"mllm"},{"id":"2512.18563","title":"OpenView: Empowering MLLMs with Out-of-view VQA","created":"2025-12-21","cited_by_count":3,"area":"mllm"},{"id":"2605.03903","title":"CC-OCR V2: Fine-Grained Attribution of LMM Failures in Real-World Visual Document Understanding","created":"2026-05-05","cited_by_count":3,"area":"mllm"},{"id":"2608.13113","title":"EgoMonth: A Month-Level Egocentric Video Benchmark for Long-Term Spatiotemporal Memory","created":"2026-08-13","cited_by_count":3,"area":"mllm"},{"id":"2509.22524","title":"Color Names in Vision-Language Models","created":"2025-09-26","cited_by_count":2,"area":"mllm"},{"id":"2601.22737","title":"Lingua-SafetyBench: A Benchmark for Safety Evaluation of Multilingual Vision-Language Models","created":"2026-01-30","cited_by_count":2,"area":"mllm"},{"id":"2602.22716","title":"SoPE: Spherical Coordinate-Based Positional Embedding for Enhancing Spatial Perception of 3D LVLMs","created":"2026-02-26","cited_by_count":2,"area":"mllm"},{"id":"2604.04372","title":"Graph-to-Frame RAG: Visual-Space Knowledge Fusion for Training-Free and Auditable Video Reasoning","created":"2026-04-06","cited_by_count":2,"area":"mllm"},{"id":"2608.03782","title":"KnowHal: A Knowledge-Driven Benchmark for Comprehensive Multimodal Hallucination Evaluation","created":"2026-08-04","cited_by_count":2,"area":"mllm"},{"id":"2608.24138","title":"Rubrics as Visual-Repair Context for Self-Evolving UI-to-Code Generation","created":"2026-08-25","cited_by_count":2,"area":"mllm"},{"id":"2512.18735","title":"$M^3-Verse$: A \"Spot the Difference\" Challenge for Large Multimodal Models","created":"2025-12-21","cited_by_count":1,"area":"mllm"},{"id":"2601.10378","title":"Global Context Compression with Interleaved Vision-Text Transformation","created":"2026-01-15","cited_by_count":1,"area":"mllm"},{"id":"2601.19222","title":"UniPCB: A Unified Vision-Language Benchmark for Open-Ended PCB Quality Inspection","created":"2026-01-27","cited_by_count":1,"area":"mllm"},{"id":"2601.21915","title":"VideoAesBench: Benchmarking the Video Aesthetics Perception Capabilities of Large Multimodal Models","created":"2026-01-29","cited_by_count":1,"area":"mllm"},{"id":"2602.00559","title":"Learning to Decode Against Compositional Hallucination in Video Multimodal Large Language Models","created":"2026-01-31","cited_by_count":1,"area":"mllm"},{"id":"2603.10863","title":"Beyond Sequential Distance: Inter-Modal Distance Invariant Position Encoding","created":"2026-03-11","cited_by_count":1,"area":"mllm"},{"id":"2604.03231","title":"CoME-VL: Scaling Complementary Multi-Encoder Vision-Language Learning","created":"2026-04-03","cited_by_count":1,"area":"mllm"},{"id":"2604.13073","title":"OmniTrace: A Unified Framework for Generation-Time Attribution in Omni-Modal LLMs","created":"2026-03-20","cited_by_count":1,"area":"mllm"},{"id":"2605.00326","title":"Prompt-Induced Score Variance in Zero-Shot Binary Vision-Language Safety Classification","created":"2026-05-01","cited_by_count":1,"area":"mllm"},{"id":"2607.02991","title":"GuideMe: Multi-Domain Task Guidance and Intervention in Streaming Video","created":"2026-07-03","cited_by_count":1,"area":"mllm"},{"id":"2607.22708","title":"StepX-Edge: An On-Device UI Vision-Language Model via Architecture-Training-Deployment Co-Design","created":"2026-07-20","cited_by_count":1,"area":"mllm"},{"id":"2608.02039","title":"RSVideo: Are Your Vision-Language Models Ready for Remote Sensing Videos?","created":"2026-08-03","cited_by_count":1,"area":"mllm"},{"id":"2601.04824","title":"SOVABench: A Vehicle Surveillance Action Retrieval Benchmark for Multimodal Large Language Models","created":"2026-01-08","cited_by_count":0,"area":"mllm"},{"id":"2604.22884","title":"Can Multimodal Large Language Models Truly Understand Small Objects?","created":"2026-04-24","cited_by_count":0,"area":"mllm"},{"id":"2605.15300","title":"Deep Pre-Alignment for VLMs","created":"2026-05-14","cited_by_count":0,"area":"mllm"},{"id":"2605.17093","title":"HEED: Density-Weighted Residual Alignment for Hybrid Vision-Language Model Distillation","created":"2026-05-16","cited_by_count":0,"area":"mllm"},{"id":"2605.22185","title":"Enhancing Multimodal Large Language Models for Safety-Critical Driving Video Analysis","created":"2026-05-21","cited_by_count":0,"area":"mllm"},{"id":"2606.19965","title":"ROSE: Benchmarking the Perception-to-Action Gap in Multimodal Models","created":"2026-06-18","cited_by_count":0,"area":"mllm"},{"id":"2607.03817","title":"Global Logic and Local Search: Dual-Stream Multimodal In-Context Learning for Verifiable Industrial Anomaly Detection","created":"2026-07-04","cited_by_count":0,"area":"mllm"},{"id":"2607.26913","title":"Prior Directions: Why GUI Grounding Gets Locked in the Past","created":"2026-07-29","cited_by_count":0,"area":"mllm"},{"id":"2608.06154","title":"Visual Grounding in Zero-Shot Vision-Language Control","created":"2026-08-06","cited_by_count":0,"area":"mllm"},{"id":"2608.20975","title":"Belief Without Behavior: Measuring the Translation of Theory of Mind into Coordinated Social Action in Vision-Language Models","created":"2026-08-21","cited_by_count":0,"area":"mllm"},{"id":"2608.24325","title":"SonarLLM: A Native Sonar--Optical Multimodal Large Language Model for Underwater Perception","created":"2026-08-25","cited_by_count":0,"area":"mllm"},{"id":"2608.28784","title":"ClearText-Video: A Large-Scale Text-Centric Video Dataset Bridging Video Restoration and Scene-Text Enhancement","created":"2026-08-28","cited_by_count":0,"area":"mllm"},{"id":"2609.08300","title":"Human-Centric Image Captioning with Subject-Centered Spatial Understanding","created":"2026-09-08","cited_by_count":0,"area":"mllm"},{"id":"2609.25770","title":"Reading Right, Answering Wrong: How Visual Configuration Changes Affect Evidence Use in VLMs","created":"2026-09-22","cited_by_count":0,"area":"mllm"},{"id":"2609.31746","title":"VisionPsy-Nano: Improving Accuracy, Efficiency, and Reliability in On-Device Vision-Language Models","created":"2026-09-23","cited_by_count":0,"area":"mllm"},{"id":"2609.33694","title":"Seeing and Solving Are Not Enough for Vision-Language Models","created":"2026-09-27","cited_by_count":0,"area":"mllm"},{"id":"2609.36136","title":"Xiaomi-OCR-0 Technical Report","created":"2026-09-28","cited_by_count":0,"area":"mllm"},{"id":"2609.37515","title":"Hierarchical Compression of Vision-Language Model Benchmarks","created":"2026-09-29","cited_by_count":0,"area":"mllm"},{"id":"2609.37576","title":"Evaluating the Evaluators: Diagnosing Large Multimodal Models for AI-Generated Image Assessment","created":"2026-09-29","cited_by_count":0,"area":"mllm"},{"id":"2610.05940","title":"ReMem: Streaming Video Understanding With Long Context Retention","created":"2026-10-05","cited_by_count":0,"area":"mllm"},{"id":"2610.11410","title":"Cognition-Oriented Emotion Tracing from Causes to Consequences in Real-World Social Scenes","created":"2026-10-08","cited_by_count":0,"area":"mllm"},{"id":"2610.14094","title":"Scenes as an Attack Surface: Uncovering Scene-Grounded Safety Failures in MLLMs","created":"2026-10-08","cited_by_count":0,"area":"mllm"}],"next_cursor":null}