{"total":94,"rows":[{"id":"2506.01844","title":"SmolVLA: A Vision-Language-Action Model for Affordable and Efficient Robotics","created":"2025-06-02","cited_by_count":530,"area":"mllm"},{"id":"2512.10942","title":"VL-JEPA: Joint Embedding Predictive Architecture for Vision-language","created":"2025-12-11","cited_by_count":68,"area":"mllm"},{"id":"2510.17269","title":"FineVision: Open Data Is All You Need","created":"2025-10-20","cited_by_count":53,"area":"mllm"},{"id":"2508.18264","title":"MMTok: Multimodal Coverage Maximization for Efficient Inference of VLMs","created":"2025-08-25","cited_by_count":33,"area":"mllm"},{"id":"2505.01481","title":"VideoHallu: Evaluating and Mitigating Multi-modal Hallucinations on Synthetic Video Understanding","created":"2025-05-02","cited_by_count":32,"area":"mllm"},{"id":"2510.17111","title":"Efficient Vision-Language-Action Models for Embodied Manipulation: A Systematic Survey","created":"2025-10-20","cited_by_count":26,"area":"mllm"},{"id":"2512.00903","title":"SwiftVLA: Unlocking Spatiotemporal Dynamics for Lightweight VLA Models at Minimal Overhead","created":"2025-11-30","cited_by_count":26,"area":"mllm"},{"id":"2510.10991","title":"A Survey on Agentic Multimodal Large Language Models","created":"2025-10-13","cited_by_count":23,"area":"mllm"},{"id":"2602.15397","title":"ActionCodec: What Makes for Good Action Tokenizers","created":"2026-02-17","cited_by_count":18,"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":"2510.16292","title":"QSVD: Efficient Low-rank Approximation for Unified Query-Key-Value Weight Compression in Low-Precision Vision-Language Models","created":"2025-10-18","cited_by_count":16,"area":"mllm"},{"id":"2505.19201","title":"DREAM: Drafting with Refined Target Features and Entropy-Adaptive Cross-Attention Fusion for Multimodal Speculative Decoding","created":"2025-05-25","cited_by_count":14,"area":"mllm"},{"id":"2509.23050","title":"Understanding Language Prior of LVLMs by Contrasting Chain-of-Embedding","created":"2025-09-27","cited_by_count":14,"area":"mllm"},{"id":"2508.21496","title":"ELV-Halluc: Benchmarking Semantic Aggregation Hallucinations in Long Video Understanding","created":"2025-08-29","cited_by_count":10,"area":"mllm"},{"id":"2509.10345","title":"Towards Understanding Visual Grounding in Visual Language Models","created":"2025-09-12","cited_by_count":10,"area":"mllm"},{"id":"2512.08829","title":"InfiniteVL: Synergizing Linear and Sparse Attention for Highly-Efficient, Unlimited-Input Vision-Language Models","created":"2025-12-09","cited_by_count":10,"area":"mllm"},{"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":"2512.23562","title":"VL-RouterBench: A Benchmark for Vision-Language Model Routing","created":"2025-12-29","cited_by_count":8,"area":"mllm"},{"id":"2601.09954","title":"The Spatial Blindspot of Vision-Language Models","created":"2026-01-15","cited_by_count":8,"area":"mllm"},{"id":"2603.27064","title":"ChartNet: A Million-Scale, High-Quality Multimodal Dataset for Robust Chart Understanding","created":"2026-03-28","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":"2603.14882","title":"LLMind: Bio-inspired Training-free Adaptive Visual Representations for Vision-Language Models","created":"2026-03-16","cited_by_count":7,"area":"mllm"},{"id":"2509.14769","title":"Frame Sampling Strategies Matter: A Benchmark for small vision language models","created":"2025-09-18","cited_by_count":6,"area":"mllm"},{"id":"2510.19496","title":"CARES: Context-Aware Resolution Selector for VLMs","created":"2025-10-22","cited_by_count":6,"area":"mllm"},{"id":"2512.22238","title":"Masking Teacher and Reinforcing Student for Distilling Vision-Language Models","created":"2025-12-23","cited_by_count":6,"area":"mllm"},{"id":"2511.04479","title":"ThaiOCRBench: A Task-Diverse Benchmark for Vision-Language Understanding in Thai","created":"2025-11-06","cited_by_count":5,"area":"mllm"},{"id":"2512.23592","title":"Same or Not? Enhancing Visual Perception in Vision-Language Models","created":"2025-12-29","cited_by_count":5,"area":"mllm"},{"id":"2602.07038","title":"UNIKIE-BENCH: Benchmarking Large Multimodal Models for Key Information Extraction in Visual Documents","created":"2026-02-03","cited_by_count":5,"area":"mllm"},{"id":"2505.12884","title":"TinyAlign: Boosting Lightweight Vision-Language Models by Mitigating Modal Alignment Bottlenecks","created":"2025-05-19","cited_by_count":4,"area":"mllm"},{"id":"2509.18174","title":"Baseer: A Vision-Language Model for Arabic Document-to-Markdown OCR","created":"2025-09-17","cited_by_count":4,"area":"mllm"},{"id":"2510.11496","title":"AndesVL Technical Report: An Efficient Mobile-side Multimodal Large Language Model","created":"2025-10-13","cited_by_count":4,"area":"mllm"},{"id":"2510.14896","title":"Leveraging Multimodal LLM Descriptions of Activity for Explainable Semi-Supervised Video Anomaly Detection","created":"2025-10-16","cited_by_count":4,"area":"mllm"},{"id":"2605.19846","title":"FineBench: Benchmarking and Enhancing Vision-Language Models for Fine-grained Human Activity Understanding","created":"2026-05-19","cited_by_count":4,"area":"mllm"},{"id":"2510.16333","title":"RL makes MLLMs see better than SFT","created":"2025-10-18","cited_by_count":3,"area":"mllm"},{"id":"2601.05739","title":"PII-VisBench: Evaluating Personally Identifiable Information Safety in Vision Language Models Along a Continuum of Visibility","created":"2026-01-09","cited_by_count":3,"area":"mllm"},{"id":"2604.01002","title":"Query-Conditioned Evidential Keyframe Sampling for MLLM-Based Long-Form Video Understanding","created":"2026-04-01","cited_by_count":3,"area":"mllm"},{"id":"2604.02570","title":"WSVD: Weighted Low-Rank Approximation for Fast and Efficient Execution of Low-Precision Vision-Language Models","created":"2026-04-02","cited_by_count":3,"area":"mllm"},{"id":"2508.11616","title":"Controlling Multimodal LLMs via Reward-guided Decoding","created":"2025-08-15","cited_by_count":2,"area":"mllm"},{"id":"2508.17334","title":"Mind the (Language) Gap: Towards Probing Numerical and Cross-Lingual Limits of LVLMs","created":"2025-08-24","cited_by_count":2,"area":"mllm"},{"id":"2509.10129","title":"Towards Reliable and Interpretable Document Question Answering via VLMs","created":"2025-09-12","cited_by_count":2,"area":"mllm"},{"id":"2509.15695","title":"ORIC: Benchmarking Object Recognition under Contextual Incongruity in Large Vision-Language Models","created":"2025-09-19","cited_by_count":2,"area":"mllm"},{"id":"2510.00040","title":"Uncovering Intrinsic Capabilities: A Paradigm for Data Curation in Vision-Language Models","created":"2025-09-27","cited_by_count":2,"area":"mllm"},{"id":"2511.22928","title":"Seeing before Observable: Potential Risk Reasoning in Autonomous Driving via Vision Language Models","created":"2025-11-28","cited_by_count":2,"area":"mllm"},{"id":"2512.11899","title":"Read or Ignore? A Unified Benchmark for Typographic-Attack Robustness and Text Recognition in Vision-Language Models","created":"2025-12-10","cited_by_count":2,"area":"mllm"},{"id":"2602.18884","title":"TPRU: Advancing Temporal and Procedural Understanding in Large Multimodal Models","created":"2026-02-21","cited_by_count":2,"area":"mllm"},{"id":"2603.06084","title":"Multimodal Behavior Tree Generation: A Small Vision-Language Model for Robot Task Planning","created":"2026-03-06","cited_by_count":2,"area":"mllm"},{"id":"2603.19466","title":"ProactiveBench: Benchmarking Proactiveness in Multimodal Large Language Models","created":"2026-03-19","cited_by_count":2,"area":"mllm"},{"id":"2606.24335","title":"Ill-Posed by Design: Probing Evidence Use in VLMs","created":"2026-06-23","cited_by_count":2,"area":"mllm"},{"id":"2606.28551","title":"DataComp-VLM: Improved Open Datasets for Vision-Language Models","created":"2026-06-26","cited_by_count":2,"area":"mllm"},{"id":"2607.09520","title":"Seeing is Free, Speaking is Not: Uncovering the True Energy Bottleneck in Edge VLM Inference","created":"2026-07-10","cited_by_count":2,"area":"mllm"},{"id":"2510.05109","title":"Tiny but Mighty: A Software-Hardware Co-Design Approach for Efficient Multimodal Inference on Battery-Powered Small Devices","created":"2025-09-25","cited_by_count":1,"area":"mllm"},{"id":"2510.12931","title":"Unifying Vision-Language Latents for Zero-label Image Caption Enhancement","created":"2025-10-14","cited_by_count":1,"area":"mllm"},{"id":"2511.15552","title":"Multimodal Evaluation of Russian-language Architectures","created":"2025-11-19","cited_by_count":1,"area":"mllm"},{"id":"2512.04032","title":"jina-vlm: Small Multilingual Vision Language Model","created":"2025-12-03","cited_by_count":1,"area":"mllm"},{"id":"2512.19535","title":"CASA: Cross-Attention over Self-Attention for Efficient Vision-Language Fusion","created":"2025-12-22","cited_by_count":1,"area":"mllm"},{"id":"2604.04579","title":"Firebolt-VL: Efficient Vision-Language Understanding with Cross-Modality Modulation","created":"2026-04-06","cited_by_count":1,"area":"mllm"},{"id":"2604.07634","title":"VSAS-Bench: Real-Time Evaluation of Visual Streaming Assistant Models","created":"2026-04-08","cited_by_count":1,"area":"mllm"},{"id":"2604.26508","title":"Progressive Semantic Communication for Efficient Edge-Cloud Vision-Language Models","created":"2026-04-29","cited_by_count":1,"area":"mllm"},{"id":"2605.02130","title":"From Where Things Are to What They Are For: Benchmarking Spatial-Functional Intelligence in Multimodal LLMs","created":"2026-05-04","cited_by_count":1,"area":"mllm"},{"id":"2605.10408","title":"VISOR: A Vision-Language Model-based Test Oracle for Testing Robots","created":"2026-05-11","cited_by_count":1,"area":"mllm"},{"id":"2605.27737","title":"Bounded-Compute Multimodal Regression for Product-Rating Prediction","created":"2026-05-26","cited_by_count":1,"area":"mllm"},{"id":"2606.00535","title":"DREAM-S: Speculative Decoding with Searchable Drafting and Target-Aware Refinement for Multimodal Generation","created":"2026-05-30","cited_by_count":1,"area":"mllm"},{"id":"2508.01540","title":"MagicVL-2B: Empowering Vision-Language Models on Mobile Devices with Lightweight Visual Encoders via Curriculum Learning","created":"2025-08-03","cited_by_count":0,"area":"mllm"},{"id":"2511.11177","title":"Viper-F1: Fast and Fine-Grained Multimodal Understanding with Cross-Modal State-Space Modulation","created":"2025-11-14","cited_by_count":0,"area":"mllm"},{"id":"2602.14989","title":"ThermEval: A Structured Benchmark for Evaluation of Vision-Language Models on Thermal Imagery","created":"2026-02-16","cited_by_count":0,"area":"mllm"},{"id":"2603.04453","title":"Induced Numerical Instability: Hidden Costs in Multimodal Large Language Models","created":"2026-02-27","cited_by_count":0,"area":"mllm"},{"id":"2603.16987","title":"Empirical Recipes for Efficient and Compact Vision-Language Models","created":"2026-03-17","cited_by_count":0,"area":"mllm"},{"id":"2603.26769","title":"Edge Reliability Gap in Vision-Language Models: Quantifying Failure Modes of Compressed VLMs Under Visual Corruption","created":"2026-03-24","cited_by_count":0,"area":"mllm"},{"id":"2603.27522","title":"Hidden Ads: Behavior Triggered Semantic Backdoors for Advertisement Injection in Vision Language Models","created":"2026-03-29","cited_by_count":0,"area":"mllm"},{"id":"2604.06247","title":"SALLIE: Generation-Free Hidden-State Detection of Jailbreaks and Prompt Injections Across Text and Vision","created":"2026-04-06","cited_by_count":0,"area":"mllm"},{"id":"2604.10528","title":"BareBones: Benchmarking Zero-Shot Geometric Comprehension in VLMs","created":"2026-04-12","cited_by_count":0,"area":"mllm"},{"id":"2605.08145","title":"Self-Captioning Multimodal Interaction Tuning: Amplifying Exploitable Redundancies for Robust Vision Language Models","created":"2026-05-03","cited_by_count":0,"area":"mllm"},{"id":"2605.09384","title":"LiteMedCoT-VL: Parameter-Efficient Adaptation for Medical Visual Question Answering","created":"2026-05-10","cited_by_count":0,"area":"mllm"},{"id":"2605.12789","title":"Lifelong Learning in Vision-Language Models: Enhanced EWC with Cross-Modal Knowledge Retention","created":"2026-05-12","cited_by_count":0,"area":"mllm"},{"id":"2605.18029","title":"What Matters for Grocery Product Retrieval with Open Source Vision Language Models","created":"2026-05-18","cited_by_count":0,"area":"mllm"},{"id":"2605.19866","title":"Structured Layout Priors for Robust Out-of-Distribution Visual Document Understanding","created":"2026-05-19","cited_by_count":0,"area":"mllm"},{"id":"2605.29299","title":"Pocket-Dentist: On-Device Dental Image Understanding via Efficient Multimodal Large Language Models","created":"2026-05-28","cited_by_count":0,"area":"mllm"},{"id":"2606.04351","title":"Frames2LoRA: Parametric Video Internalization for Vision-Language Models","created":"2026-06-03","cited_by_count":0,"area":"mllm"},{"id":"2607.03365","title":"Brand-as-Memory: Vision-Language Models Encode Causal, Mechanistically Localizable Credibility Priors for News Sources","created":"2026-07-03","cited_by_count":0,"area":"mllm"},{"id":"2607.09029","title":"MOSAIC: Adaptive Inter-layer Composition for Efficient Heterogeneous Vision-Language Models","created":"2026-07-10","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":"2608.06154","title":"Visual Grounding in Zero-Shot Vision-Language Control","created":"2026-08-06","cited_by_count":0,"area":"mllm"},{"id":"2608.10758","title":"Where To Look? : Causal Tracing of Vision Encoders in VLM","created":"2026-08-11","cited_by_count":0,"area":"mllm"},{"id":"2608.16263","title":"Seeing Before Answering: Training-Free Visual Layer Profiling for Vision-Language Models","created":"2026-08-17","cited_by_count":0,"area":"mllm"},{"id":"2608.20763","title":"CARD: Diagnosing Belief to Action Routing Failures in Vision Language Models","created":"2026-08-21","cited_by_count":0,"area":"mllm"},{"id":"2609.02187","title":"Lightweight Adaptation of General-Purpose VLMs for Multispectral and SAR Image Understanding","created":"2026-09-02","cited_by_count":0,"area":"mllm"},{"id":"2609.11022","title":"New Evidence, Same Choice: Testing Physical Experiment Selection in Vision Language Models","created":"2026-09-10","cited_by_count":0,"area":"mllm"},{"id":"2609.15706","title":"Beyond Accuracy: Robustness, Cost, and Governance Trade-offs for Vision-Language Models in Templated Document Extraction","created":"2026-09-14","cited_by_count":0,"area":"mllm"},{"id":"2609.27395","title":"PRISM-VLM: A Multi-Axis Discriminative Benchmark for Compact Vision-Language Models","created":"2026-09-23","cited_by_count":0,"area":"mllm"},{"id":"2609.28757","title":"Small yet Assistive: Spatially-Aware Post-Training for Low Vision","created":"2026-09-23","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":"2609.37515","title":"Hierarchical Compression of Vision-Language Model Benchmarks","created":"2026-09-29","cited_by_count":0,"area":"mllm"},{"id":"2610.08401","title":"GeoPID: Decomposing and Steering Visual Information in Vision-Language Models","created":"2026-10-06","cited_by_count":0,"area":"mllm"},{"id":"2610.11818","title":"From Pixels to Structure: Lightweight Vision-Language Models for Document OCR and Structured JSON Extraction","created":"2026-10-08","cited_by_count":0,"area":"mllm"}],"next_cursor":null}