{"total":108,"rows":[{"id":"2509.18154","title":"MiniCPM-V 4.5: Cooking Efficient MLLMs via Architecture, Data, and Training Recipe","created":"2025-09-16","cited_by_count":186,"area":"mllm"},{"id":"2510.12798","title":"Detect Anything via Next Point Prediction","created":"2025-10-14","cited_by_count":73,"area":null},{"id":"2510.25616","title":"Don't Blind Your VLA: Aligning Visual Representations for OOD Generalization","created":"2025-10-29","cited_by_count":35,"area":"mllm"},{"id":"2512.08228","title":"MM-CoT:A Benchmark for Probing Visual Chain-of-Thought Reasoning in Multimodal Models","created":"2025-12-09","cited_by_count":34,"area":"lr"},{"id":"2605.27365","title":"LocateAnything: Fast and High-Quality Vision-Language Grounding with Parallel Box Decoding","created":"2026-05-26","cited_by_count":28,"area":"mllm"},{"id":"2509.25373","title":"From Perception to Cognition: A Survey of Vision-Language Interactive Reasoning in Multimodal Large Language Models","created":"2025-09-29","cited_by_count":26,"area":"lr"},{"id":"2511.20937","title":"ENACT: Evaluating Embodied Cognition with World Modeling of Egocentric Interaction","created":"2025-11-26","cited_by_count":15,"area":"wm"},{"id":"2509.14033","title":"SAIL-VL2 Technical Report","created":"2025-09-17","cited_by_count":14,"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":"2509.21789","title":"Visual Multi-Agent System: Mitigating Hallucination Snowballing via Visual Flow","created":"2025-09-26","cited_by_count":13,"area":"mllm"},{"id":"2510.10921","title":"FG-CLIP 2: A Bilingual Fine-grained Vision-Language Alignment Model","created":"2025-10-13","cited_by_count":13,"area":null},{"id":"2601.17814","title":"MMR-Bench: A Comprehensive Benchmark for Multimodal LLM Routing","created":"2026-01-25","cited_by_count":13,"area":"mllm"},{"id":"2510.03574","title":"Efficient Test-Time Scaling for Small Vision-Language Models","created":"2025-10-03","cited_by_count":12,"area":"lr"},{"id":"2511.22055","title":"OralGPT-Omni: A Versatile Dental Multimodal Large Language Model","created":"2025-11-27","cited_by_count":11,"area":"mllm"},{"id":"2510.09507","title":"PhysToolBench: Benchmarking Physical Tool Understanding for MLLMs","created":"2025-10-10","cited_by_count":9,"area":null},{"id":"2601.08198","title":"Triplets Better Than Pairs: Towards Stable and Effective Self-Play Fine-Tuning for LLMs","created":"2026-01-13","cited_by_count":9,"area":"synth"},{"id":"2602.03595","title":"Refer-Agent: A Collaborative Multi-Agent System with Reasoning and Reflection for Referring Video Object Segmentation","created":"2026-02-03","cited_by_count":9,"area":"lr"},{"id":"2509.25160","title":"GSM8K-V: Can Vision Language Models Solve Grade School Math Word Problems in Visual Contexts","created":"2025-09-29","cited_by_count":8,"area":"lr"},{"id":"2510.05034","title":"Video-LMM Post-Training: A Deep Dive into Video Reasoning with Large Multimodal Models","created":"2025-10-06","cited_by_count":8,"area":"lr"},{"id":"2510.20812","title":"Small Drafts, Big Verdict: Information-Intensive Visual Reasoning via Speculation","created":"2025-10-23","cited_by_count":8,"area":"lr"},{"id":"2511.22982","title":"Ovis-Image Technical Report","created":"2025-11-28","cited_by_count":8,"area":null},{"id":"2512.17306","title":"Deep But Reliable: Advancing Multi-turn Reasoning for Thinking with Images","created":"2025-12-19","cited_by_count":8,"area":"lr"},{"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":"2512.07175","title":"SPACE: Noise Contrastive Estimation Stabilizes Self-Play Fine-Tuning for Large Language Models","created":"2025-12-08","cited_by_count":7,"area":"synth"},{"id":"2512.05094","title":"From Generated Human Videos to Physically Plausible Robot Trajectories","created":"2025-12-04","cited_by_count":6,"area":null},{"id":"2512.14989","title":"Evaluating Large Language Models on Multimodal Chemistry Olympiad Exams","created":"2025-12-17","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":"2607.12477","title":"Self in Space: Benchmarking Self-Awareness and Spatial Cognition in UAV Embodied Intelligence","created":"2026-07-14","cited_by_count":6,"area":null},{"id":"2511.14259","title":"ManipShield: A Unified Framework for Image Manipulation Detection, Localization and Explanation","created":"2025-11-18","cited_by_count":5,"area":null},{"id":"2512.08374","title":"The Unseen Bias: How Norm Discrepancy in Pre-Norm MLLMs Leads to Visual Information Loss","created":"2025-12-09","cited_by_count":5,"area":"mllm"},{"id":"2512.12756","title":"FysicsWorld: A Unified Full-Modality Benchmark for Any-to-Any Understanding, Generation, and Reasoning","created":"2025-12-14","cited_by_count":5,"area":"lr"},{"id":"2512.16978","title":"A Benchmark for Omni-Modal Reasoning in Long Videos","created":"2025-12-18","cited_by_count":5,"area":"lr"},{"id":"2602.07064","title":"OmniFysics: Towards Physical Intelligence Evolution via Omni-Modal Signal Processing and Network Optimization","created":"2026-02-05","cited_by_count":5,"area":null},{"id":"2603.25706","title":"Wan-Weaver: Interleaved Multi-modal Generation via Decoupled Training","created":"2026-03-26","cited_by_count":5,"area":null},{"id":"2604.06777","title":"Walk the Talk: Bridging the Reasoning-Action Gap for Thinking with Images via Multimodal Agentic Policy Optimization","created":"2026-04-08","cited_by_count":5,"area":"lr"},{"id":"2510.16505","title":"PRISMM-Bench: A Benchmark of Peer-Review Grounded Multimodal Inconsistencies","created":"2025-10-18","cited_by_count":4,"area":"mllm"},{"id":"2512.14870","title":"HERBench: A Benchmark for Multi-Evidence Integration in Video Question Answering","created":"2025-12-16","cited_by_count":4,"area":null},{"id":"2603.14916","title":"EditHF-1M: A Million-Scale Rich Human Preference Feedback for Image Editing","created":"2026-03-16","cited_by_count":4,"area":"alignment"},{"id":"2606.08464","title":"TVI-CoT: Text-Visual Interleaved Chain-of-Thought Reasoning for Multimodal Understanding","created":"2026-06-07","cited_by_count":4,"area":"lr"},{"id":"2512.08016","title":"FRIEDA: Benchmarking Multi-Step Cartographic Reasoning in Vision-Language Models","created":"2025-12-08","cited_by_count":3,"area":"lr"},{"id":"2602.18600","title":"MapTab: A Diagnostic Benchmark for Long-Horizon Multi-Criteria Multimodal Reasoning on Heterogeneous Topological Graphs","created":"2026-02-20","cited_by_count":3,"area":"lr"},{"id":"2603.06054","title":"Probing Visual Concepts in Lightweight Vision-Language Models for Automated Driving","created":"2026-03-06","cited_by_count":3,"area":"mllm"},{"id":"2603.10757","title":"CodePercept: Code-Grounded Visual STEM Perception for MLLMs","created":"2026-03-11","cited_by_count":3,"area":"lr"},{"id":"2604.03318","title":"EgoMind: Activating Spatial Cognition through Linguistic Reasoning in MLLMs","created":"2026-04-01","cited_by_count":3,"area":"lr"},{"id":"2605.10286","title":"AgentRx: A Benchmark Study of LLM Agents for Multimodal Clinical Prediction Tasks","created":"2026-05-11","cited_by_count":3,"area":"agents"},{"id":"2605.23898","title":"SPACENUM: Revisiting Spatial Numerical Understanding in VLMs","created":"2026-05-22","cited_by_count":3,"area":"mllm"},{"id":"2605.27378","title":"OralAgent: Integrating Reasoning, Tools, and Knowledge for Interactive Dental Image Analysis","created":"2026-04-09","cited_by_count":3,"area":null},{"id":"2606.18216","title":"Zone of Proximal Policy Optimization: Teacher in Prompts, Not Gradients","created":"2026-06-16","cited_by_count":3,"area":"lr"},{"id":"2510.12974","title":"Scope: Selective Cross-modal Orchestration of Visual Perception Experts","created":"2025-10-14","cited_by_count":2,"area":"mllm"},{"id":"2512.15560","title":"GRAN-TED: Generating Robust, Aligned, and Nuanced Text Embedding for Diffusion Models","created":"2025-12-17","cited_by_count":2,"area":"diffusion"},{"id":"2601.22725","title":"OpenVTON-Bench: A Large-Scale High-Resolution Benchmark for Controllable Virtual Try-On Evaluation","created":"2026-01-30","cited_by_count":2,"area":"diffusion"},{"id":"2604.16331","title":"BrainMem: Brain-Inspired Evolving Memory for Embodied Agent Task Planning","created":"2026-03-12","cited_by_count":2,"area":"agents"},{"id":"2604.28076","title":"TopBench: A Benchmark for Implicit Predictive Reasoning in Tabular Question Answering","created":"2026-04-30","cited_by_count":2,"area":"lr"},{"id":"2605.14465","title":"From Table to Cell: Attention for Better Reasoning with TABALIGN","created":"2026-05-14","cited_by_count":2,"area":"lr"},{"id":"2511.16600","title":"You Only Forward Once: An Efficient Compositional Judging Paradigm","created":"2025-11-20","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":"2601.10369","title":"Fine-Grained Human Pose Editing Assessment via Layer-Selective MLLMs","created":"2026-01-15","cited_by_count":1,"area":null},{"id":"2601.16419","title":"Learning Domain Knowledge in Multimodal Large Language Models through Reinforcement Fine-Tuning","created":"2026-01-23","cited_by_count":1,"area":"mllm"},{"id":"2602.13653","title":"Building Autonomous GUI Navigation via Agentic-Q Estimation and Step-Wise Policy Optimization","created":"2026-02-14","cited_by_count":1,"area":"agents"},{"id":"2602.20197","title":"Controllable Exploration in Hybrid-Policy RLVR for Multi-Modal Reasoning","created":"2026-02-22","cited_by_count":1,"area":"lr"},{"id":"2602.21706","title":"SurGo-R1: Benchmarking and Modeling Contextual Reasoning for Operative Zone in Surgical Video","created":"2026-02-25","cited_by_count":1,"area":"lr"},{"id":"2603.00938","title":"Seeing Beyond 8bits: Subjective and Objective Quality Assessment of HDR-UGC Videos","created":"2026-03-01","cited_by_count":1,"area":null},{"id":"2603.09731","title":"EXPLORE-Bench: Egocentric Scene Prediction with Long-Horizon Reasoning","created":"2026-03-10","cited_by_count":1,"area":"lr"},{"id":"2603.10978","title":"GroundCount: Grounding Vision-Language Models with Object Detection for Mitigating Counting Hallucinations","created":"2026-03-11","cited_by_count":1,"area":"lr"},{"id":"2603.13397","title":"TennisExpert: Towards Expert-Level Analytical Sports Video Understanding","created":"2026-03-11","cited_by_count":1,"area":null},{"id":"2604.00404","title":"The 1st Winner for 5th PVUW MeViS-Text Challenge: Strong MLLMs Meet SAM3 for Referring Video Object Segmentation","created":"2026-04-01","cited_by_count":1,"area":null},{"id":"2604.22226","title":"Towards Temporal Compositional Reasoning in Long-Form Sports Videos","created":"2026-04-24","cited_by_count":1,"area":"lr"},{"id":"2605.07457","title":"EditRefiner: A Human-Aligned Agentic Framework for Image Editing Refinement","created":"2026-05-08","cited_by_count":1,"area":"agents"},{"id":"2605.07477","title":"ReasonEdit: Towards Interpretable Image Editing Evaluation via Reinforcement Learning","created":"2026-05-08","cited_by_count":1,"area":"lr"},{"id":"2605.13667","title":"SceneGraphVLM: Dynamic Scene Graph Generation from Video with Vision-Language Models","created":"2026-05-13","cited_by_count":1,"area":"mllm"},{"id":"2608.28701","title":"TopoAgent: A Structure-Aware Perception-to-Reasoning Framework for Diagram-to-Graph Topology Extraction with Large Vision-Language Models","created":"2026-08-27","cited_by_count":1,"area":"lr"},{"id":"2609.19745","title":"Region-Level Policy Optimization for Fine-grained MLLM Perception","created":"2026-09-17","cited_by_count":1,"area":null},{"id":"2510.27033","title":"A Multi-Modal Neuro-Symbolic Approach for Spatial Reasoning-Based Visual Grounding in Robotics","created":"2025-10-30","cited_by_count":0,"area":"lr"},{"id":"2512.06276","title":"RefBench-PRO: Perceptual and Reasoning Oriented Benchmark for Referring Expression Comprehension","created":"2025-12-06","cited_by_count":0,"area":"lr"},{"id":"2512.12424","title":"ViInfographicVQA: A Benchmark for Single and Multi-image Visual Question Answering on Vietnamese Infographics","created":"2025-12-13","cited_by_count":0,"area":null},{"id":"2601.10165","title":"Advancing Adaptive Multi-Stage Video Anomaly Reasoning: A Benchmark Dataset and Method","created":"2026-01-15","cited_by_count":0,"area":"lr"},{"id":"2602.10771","title":"From Steering to Pedalling: Do Autonomous Driving VLMs Generalize to Cyclist-Assistive Spatial Perception and Planning?","created":"2026-02-11","cited_by_count":0,"area":"driving"},{"id":"2602.15539","title":"Dynamic Training-Free Fusion of Subject and Style LoRAs","created":"2026-02-17","cited_by_count":0,"area":null},{"id":"2603.29759","title":"TSHA: A Benchmark for Visual Language Models in Trustworthy Safety Hazard Assessment Scenarios","created":"2026-03-31","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":"2604.25186","title":"FCMBench-Video: Benchmarking Document Video Intelligence","created":"2026-04-28","cited_by_count":0,"area":null},{"id":"2605.07544","title":"From Pixels to Prompts: Vision-Language Models","created":"2026-05-08","cited_by_count":0,"area":"mllm"},{"id":"2605.09270","title":"Memorize Theorems, Not Instances: Probing SFT Generalization through Mathematical Reasoning","created":"2026-05-10","cited_by_count":0,"area":"lr"},{"id":"2605.10576","title":"SenseBench: A Benchmark for Remote Sensing Low-Level Visual Perception and Description in Large Vision-Language Models","created":"2026-05-11","cited_by_count":0,"area":"mllm"},{"id":"2605.17823","title":"Why We Look Where We Look: Emergent Human-like Fixations of a Foveated Visual Language Model Maximizing Scene Understanding","created":"2026-05-18","cited_by_count":0,"area":"mllm"},{"id":"2605.19522","title":"iDiff: Interpretable Difference-aware Framework for Pairwise Image Quality Assessment","created":"2026-05-19","cited_by_count":0,"area":null},{"id":"2605.31174","title":"Detect in Any Scene: An Agentic Framework for Object Detection with Experience-Aware Reasoning","created":"2026-05-29","cited_by_count":0,"area":"lr"},{"id":"2606.07161","title":"TraRA: Trajectory-level Recognition Aggregation for Video Text Spotting in Urban Surveillance","created":"2026-06-05","cited_by_count":0,"area":null},{"id":"2606.30217","title":"Before Thinking, Learn to Decide: Proactive Routing for Efficient Visual Reasoning","created":"2026-06-29","cited_by_count":0,"area":"lr"},{"id":"2606.31187","title":"Learning to Deny: Action Denial in Multimodal Large Language Models","created":"2026-06-30","cited_by_count":0,"area":"mllm"},{"id":"2607.18839","title":"HPD-Parsing: Hierarchical Parallel Document Parsing","created":"2026-07-21","cited_by_count":0,"area":"inference"},{"id":"2608.11692","title":"HUGIN: Enhancing Vision-Language Planning for Autonomous Logistics Sorting","created":"2026-08-12","cited_by_count":0,"area":null},{"id":"2608.24430","title":"Vision Language Model Fusion for Explainable Face Recognition","created":"2026-08-25","cited_by_count":0,"area":"mllm"},{"id":"2608.30653","title":"Fine-Grained Multi Image Object Hallucination Benchmark","created":"2026-08-31","cited_by_count":0,"area":"mllm"},{"id":"2609.01691","title":"FairLens: Benchmarking Fairness in Vision-Language Models for High-Stakes Decision-Making","created":"2026-09-01","cited_by_count":0,"area":"mllm"},{"id":"2609.05539","title":"Dual-Latent Memory Routing for Vision-Language Reasoning","created":"2026-09-02","cited_by_count":0,"area":"lr"},{"id":"2609.06704","title":"Counterfactual Tests for Measuring Chain-of-Thought Faithfulness in Visual Language Models","created":"2026-09-06","cited_by_count":0,"area":"lr"},{"id":"2609.07258","title":"MV-STRIDE: Enabling MLLMs to Master Multi-View Spatial Reasoning via Hierarchical Capability Modeling","created":"2026-09-07","cited_by_count":0,"area":"lr"},{"id":"2609.20423","title":"WeVisDoc: From Coverage to Capability for Robust End-to-End Document Parsing","created":"2026-09-17","cited_by_count":0,"area":null},{"id":"2609.25738","title":"OmniFysics-Nano-V2 Technical Report: Understanding the Physical World Across Modalities","created":"2026-09-22","cited_by_count":0,"area":null}],"next_cursor":"100"}