{"total":52,"rows":[{"id":"2607.02770","title":"Gemma 4 Technical Report","created":"2026-07-02","cited_by_count":259,"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":"2607.04884","title":"HunyuanOCR-1.5: Making Lightweight OCR VLMs Faster and Better","created":"2026-07-06","cited_by_count":14,"area":"mllm"},{"id":"2603.16289","title":"VisBrowse-Bench: Benchmarking Visual-Native Search for Multimodal Browsing Agents","created":"2026-03-17","cited_by_count":13,"area":"mllm"},{"id":"2603.13391","title":"WebVR: Benchmarking Multimodal LLMs for WebPage Recreation from Videos via Human-Aligned Visual Rubrics","created":"2026-03-11","cited_by_count":8,"area":"mllm"},{"id":"2604.01569","title":"VideoZeroBench: Probing the Limits of Video MLLMs with Spatio-Temporal Evidence Verification","created":"2026-04-02","cited_by_count":7,"area":"mllm"},{"id":"2605.14906","title":"MemLens: Benchmarking Multimodal Long-Term Memory in Large Vision-Language Models","created":"2026-05-14","cited_by_count":7,"area":"mllm"},{"id":"2604.03016","title":"Agentic-MME: What Agentic Capability Really Brings to Multimodal Intelligence?","created":"2026-04-03","cited_by_count":5,"area":"mllm"},{"id":"2605.12684","title":"Visual Aesthetic Benchmark: Can Frontier Models Judge Beauty?","created":"2026-05-12","cited_by_count":4,"area":"mllm"},{"id":"2607.23125","title":"Self-Boosting Vision-Language Models with Noisy Student On-Policy Self-Distillation","created":"2026-07-25","cited_by_count":4,"area":"mllm"},{"id":"2603.08436","title":"Can Vision-Language Models Solve the Shell Game?","created":"2026-03-09","cited_by_count":3,"area":"mllm"},{"id":"2605.16079","title":"VideoSeeker: Incentivizing Instance-level Video Understanding via Native Agentic Tool Invocation","created":"2026-05-15","cited_by_count":3,"area":"mllm"},{"id":"2605.26781","title":"LiveK12Bench: Have Large Multimodal Models Truly Conquered High School-level Examinations?","created":"2026-05-26","cited_by_count":3,"area":"mllm"},{"id":"2606.00579","title":"Sandboxed Coding Agents are Competitive Omni-modal Task Solvers","created":"2026-05-30","cited_by_count":3,"area":"mllm"},{"id":"2607.17423","title":"TimeLens2: Generalist Video Temporal Grounding with Multimodal LLMs","created":"2026-07-19","cited_by_count":3,"area":"mllm"},{"id":"2605.00809","title":"Let ViT Speak: Generative Language-Image Pre-training","created":"2026-05-01","cited_by_count":2,"area":"mllm"},{"id":"2605.08985","title":"LLaVA-UHD v4: What Makes Efficient Visual Encoding in MLLMs?","created":"2026-05-09","cited_by_count":2,"area":"mllm"},{"id":"2605.21541","title":"Frequency-Domain Regularized Adversarial Alignment for Transferable Attacks against Closed-Source MLLMs","created":"2026-05-20","cited_by_count":2,"area":"mllm"},{"id":"2606.06076","title":"Learning Visual Spatial Planning from Symbolic State via Modality-Gap-Aware Self-Distillation","created":"2026-06-04","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":"2608.12262","title":"Diagram-MMU: A Multi-Modal Benchmark for Scientific Diagrams","created":"2026-08-12","cited_by_count":2,"area":"mllm"},{"id":"2604.00161","title":"Q-Mask: Query-driven Causal Masks for Text Anchoring in OCR-Oriented Vision-Language Models","created":"2026-03-31","cited_by_count":1,"area":"mllm"},{"id":"2605.29615","title":"DiffSpot: Can VLMs Spot Fine-Grained Visual Differences in Web Interfaces?","created":"2026-05-28","cited_by_count":1,"area":"mllm"},{"id":"2606.29805","title":"Clearer Sight, Fewer Lies: Oriented Pickup Preference Optimization for Multimodal Hallucination Mitigation","created":"2026-06-29","cited_by_count":1,"area":"mllm"},{"id":"2608.17402","title":"MoE-ViE: Mixture of Experts Vision Encoder for Efficient Image and Video Understanding","created":"2026-08-18","cited_by_count":1,"area":"mllm"},{"id":"2603.00842","title":"MedGPT-oss: Training a General-Purpose Vision-Language Model for Biomedicine","created":"2026-03-01","cited_by_count":0,"area":"mllm"},{"id":"2603.19274","title":"CURE: A Multimodal Benchmark for Clinical Understanding and Retrieval Evaluation","created":"2026-02-28","cited_by_count":0,"area":"mllm"},{"id":"2603.28662","title":"AMIGO: Agentic Multi-Image Grounding Oracle Benchmark","created":"2026-03-30","cited_by_count":0,"area":"mllm"},{"id":"2604.01181","title":"True (VIS) Lies: Analyzing How Generative AI Recognizes Intentionality, Rhetoric, and Misleadingness in Visualization Lies","created":"2026-04-01","cited_by_count":0,"area":"mllm"},{"id":"2604.02048","title":"Jagle: Building a Large-Scale Japanese Multimodal Post-Training Dataset for Vision-Language Models","created":"2026-04-02","cited_by_count":0,"area":"mllm"},{"id":"2604.10297","title":"FashionMV: Product-Level Composed Image Retrieval with Multi-View Fashion Data","created":"2026-04-11","cited_by_count":0,"area":"mllm"},{"id":"2604.27389","title":"COHERENCE: Benchmarking Fine-Grained Image-Text Alignment in Interleaved Multimodal Contexts","created":"2026-04-30","cited_by_count":0,"area":"mllm"},{"id":"2605.05709","title":"Conceal, Reconstruct, Jailbreak: Exploiting the Reconstruction-Concealment Tradeoff in MLLMs","created":"2026-05-07","cited_by_count":0,"area":"mllm"},{"id":"2605.21852","title":"Seizure-Semiology-Suite (S3): A Clinically Multimodal Dataset, Benchmark, and Models for Seizure Semiology Understanding","created":"2026-05-21","cited_by_count":0,"area":"mllm"},{"id":"2605.26380","title":"VisualNeedle: Benchmarking Active Visual Search in Information-Dense Scenes","created":"2026-05-25","cited_by_count":0,"area":"mllm"},{"id":"2606.05874","title":"Evaluating Stochastic Collapse and Implicit Bias in Multimodal Large Language Models","created":"2026-06-04","cited_by_count":0,"area":"mllm"},{"id":"2606.16586","title":"LOCUS: Local Visual Cue Search for Enhancing Fine-Grained Perception in Multimodal Large Language Models","created":"2026-06-15","cited_by_count":0,"area":"mllm"},{"id":"2606.27187","title":"HarmVideoBench: Benchmarking Harmful Video Understanding in Large Multimodal Models","created":"2026-06-25","cited_by_count":0,"area":"mllm"},{"id":"2607.04694","title":"Solve the Missing First Step: Can VLMs Standardize Raw Heterogeneous Medical Data?","created":"2026-07-06","cited_by_count":0,"area":"mllm"},{"id":"2607.18673","title":"MissingBench-Verified: Probing Vision-Language Models' Inability to Detect Missing Object Parts","created":"2026-07-21","cited_by_count":0,"area":"mllm"},{"id":"2607.19857","title":"Memory-Augmented Multimodal Large Language Models for Small Object Understanding in Streaming Aerial Videos","created":"2026-07-22","cited_by_count":0,"area":"mllm"},{"id":"2607.19910","title":"MV-Bench: Benchmarking Multimodal Large Language Models for Coordinated Multi-View Interface Construction","created":"2026-07-22","cited_by_count":0,"area":"mllm"},{"id":"2608.03474","title":"MT-Web2Code: Benchmarking Coding Agents on Multi-Turn Regional Reconstruction and Localized Modification","created":"2026-08-04","cited_by_count":0,"area":"mllm"},{"id":"2608.11074","title":"CapProbe: Evaluating Detailed Image Captions via Full-Scene Dense Question Answering","created":"2026-08-11","cited_by_count":0,"area":"mllm"},{"id":"2608.14718","title":"VideoGAIA: A Benchmark for General AI Assistants on Agentic Video Understanding","created":"2026-08-12","cited_by_count":0,"area":"mllm"},{"id":"2608.27154","title":"ReViCo: Unveiling the Limitations of VLMs in Visual Text Understanding via Error Correction","created":"2026-08-27","cited_by_count":0,"area":"mllm"},{"id":"2609.06245","title":"VDiff-Bench: A Challenging Benchmark for Fine-Grained Image Difference Identification","created":"2026-09-05","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":"2609.35457","title":"How Far Are We from Removing the Visual Encoder? Scaling Laws for Encoder-Free Multimodal Pretraining","created":"2026-09-28","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":"2610.12266","title":"DVD: Dynamic Vector Decoding for Efficient MLLM-based Perception","created":"2026-10-08","cited_by_count":0,"area":"mllm"}],"next_cursor":null}