{"total":452,"rows":[{"id":"2504.13181","title":"Perception Encoder: The best visual embeddings are not at the output of the network","created":"2025-04-17","cited_by_count":326,"area":null},{"id":"2510.18234","title":"DeepSeek-OCR: Contexts Optical Compression","created":"2025-10-21","cited_by_count":183,"area":null},{"id":"2507.13334","title":"A Survey of Context Engineering for Large Language Models","created":"2025-07-17","cited_by_count":126,"area":null},{"id":"2511.05491","title":"Visual Spatial Tuning","created":"2025-11-07","cited_by_count":89,"area":null},{"id":"2511.13719","title":"Scaling Spatial Intelligence with Multimodal Foundation Models","created":"2025-11-17","cited_by_count":82,"area":null},{"id":"2601.20552","title":"DeepSeek-OCR 2: Visual Causal Flow","created":"2026-01-28","cited_by_count":74,"area":null},{"id":"2510.12798","title":"Detect Anything via Next Point Prediction","created":"2025-10-14","cited_by_count":73,"area":null},{"id":"2507.07999","title":"Traceable Evidence Enhanced Visual Grounded Reasoning: Evaluation and Methodology","created":"2025-07-10","cited_by_count":69,"area":null},{"id":"2506.23044","title":"Ovis-U1 Technical Report","created":"2025-06-29","cited_by_count":67,"area":null},{"id":"2510.15870","title":"OmniVinci: Enhancing Architecture and Data for Omni-Modal Understanding LLM","created":"2025-10-17","cited_by_count":59,"area":null},{"id":"2601.21957","title":"PaddleOCR-VL-1.5: Towards a Multi-Task 0.9B VLM for Robust In-the-Wild Document Parsing","created":"2026-01-29","cited_by_count":57,"area":null},{"id":"2509.07295","title":"Reconstruction Alignment Improves Unified Multimodal Models","created":"2025-09-08","cited_by_count":49,"area":null},{"id":"2505.23661","title":"OpenUni: A Simple Baseline for Unified Multimodal Understanding and Generation","created":"2025-05-29","cited_by_count":46,"area":null},{"id":"2507.23278","title":"UniLiP: Adapting CLIP for Unified Multimodal Understanding, Generation and Editing","created":"2025-07-31","cited_by_count":44,"area":null},{"id":"2506.08010","title":"Vision Transformers Don't Need Trained Registers","created":"2025-06-09","cited_by_count":41,"area":null},{"id":"2507.14533","title":"ArtiMuse: Fine-Grained Image Aesthetics Assessment with Joint Scoring and Expert-Level Understanding","created":"2025-07-19","cited_by_count":41,"area":null},{"id":"2509.04548","title":"Skywork UniPic 2.0: Building Kontext Model with Online RL for Unified Multimodal Model","created":"2025-09-04","cited_by_count":41,"area":null},{"id":"2512.10863","title":"MMSI-Video-Bench: A Holistic Benchmark for Video-Based Spatial Intelligence","created":"2025-12-11","cited_by_count":38,"area":null},{"id":"2509.03516","title":"Easier Painting Than Thinking: Can Text-to-Image Models Set the Stage, but Not Direct the Play?","created":"2025-09-03","cited_by_count":34,"area":null},{"id":"2507.14632","title":"BusterX++: Towards Unified Cross-Modal AI-Generated Content Detection and Explanation with MLLM","created":"2025-07-19","cited_by_count":29,"area":null},{"id":"2509.12886","title":"The LLM Already Knows: Estimating LLM-Perceived Question Difficulty via Hidden Representations","created":"2025-09-16","cited_by_count":29,"area":null},{"id":"2510.13747","title":"InteractiveOmni: A Unified Omni-modal Model for Audio-Visual Multi-turn Dialogue","created":"2025-10-15","cited_by_count":29,"area":null},{"id":"2505.17399","title":"FullFront: Benchmarking MLLMs Across the Full Front-End Engineering Workflow","created":"2025-05-23","cited_by_count":28,"area":null},{"id":"2505.19650","title":"Modality Curation: Building Universal Embeddings for Advanced Multimodal Information Retrieval","created":"2025-05-26","cited_by_count":26,"area":null},{"id":"2512.21334","title":"Streaming Video Instruction Tuning","created":"2025-12-24","cited_by_count":26,"area":null},{"id":"2603.10910","title":"GLM-OCR Technical Report","created":"2026-03-11","cited_by_count":26,"area":null},{"id":"2505.15145","title":"CineTechBench: A Benchmark for Cinematographic Technique Understanding and Generation","created":"2025-05-21","cited_by_count":23,"area":null},{"id":"2507.18342","title":"EgoExoBench: A Benchmark for First- and Third-person View Video Understanding in MLLMs","created":"2025-07-24","cited_by_count":23,"area":null},{"id":"2509.26625","title":"Learning to See Before Seeing: Demystifying LLM Visual Priors from Language Pre-training","created":"2025-09-30","cited_by_count":23,"area":null},{"id":"2510.10575","title":"UniFlow: A Unified Pixel Flow Tokenizer for Visual Understanding and Generation","created":"2025-10-12","cited_by_count":23,"area":null},{"id":"2510.12422","title":"VideoLucy: Deep Memory Backtracking for Long Video Understanding","created":"2025-10-14","cited_by_count":22,"area":null},{"id":"2511.00391","title":"VinciCoder: Unifying Multimodal Code Generation via Coarse-to-fine Visual Reinforcement Learning","created":"2025-11-01","cited_by_count":21,"area":null},{"id":"2507.09815","title":"VRU-Accident: A Vision-Language Benchmark for Video Question Answering and Dense Captioning for Accident Scene Understanding","created":"2025-07-13","cited_by_count":20,"area":null},{"id":"2601.21406","title":"Generation Enhances Understanding in Unified Multimodal Models via Multi-Representation Generation","created":"2026-01-29","cited_by_count":20,"area":null},{"id":"2507.11336","title":"UGC-VideoCaptioner: An Omni UGC Video Detail Caption Model and New Benchmarks","created":"2025-07-15","cited_by_count":19,"area":null},{"id":"2510.08673","title":"Thinking with Camera: A Unified Multimodal Model for Camera-Centric Understanding and Generation","created":"2025-10-09","cited_by_count":19,"area":null},{"id":"2512.23333","title":"CME-CAD: Heterogeneous Collaborative Multi-Expert Reinforcement Learning for CAD Code Generation","created":"2025-12-29","cited_by_count":19,"area":null},{"id":"2510.21307","title":"Towards Physically Executable 3D Gaussian for Embodied Navigation","created":"2025-10-24","cited_by_count":17,"area":null},{"id":"2511.21087","title":"MIRA: Multimodal Iterative Reasoning Agent for Image Editing","created":"2025-11-26","cited_by_count":17,"area":null},{"id":"2601.04498","title":"IGenBench: Benchmarking the Reliability of Text-to-Infographic Generation","created":"2026-01-08","cited_by_count":17,"area":null},{"id":"2511.02778","title":"VCode: a Multimodal Coding Benchmark with SVG as Symbolic Visual Representation","created":"2025-11-04","cited_by_count":16,"area":null},{"id":"2511.08195","title":"UI2Code^N: UI-to-Code Generation as Interactive Visual Optimization","created":"2025-11-11","cited_by_count":15,"area":null},{"id":"2511.21025","title":"CaptionQA: Is Your Caption as Useful as the Image Itself?","created":"2025-11-26","cited_by_count":15,"area":null},{"id":"2601.11035","title":"Your One-Stop Solution for AI-Generated Video Detection","created":"2026-01-16","cited_by_count":15,"area":null},{"id":"2602.20903","title":"TextPecker: Rewarding Structural Anomaly Quantification for Enhancing Visual Text Rendering","created":"2026-02-24","cited_by_count":15,"area":null},{"id":"2505.23522","title":"OmniEarth-Bench: Towards Holistic Evaluation of Earth's Six Spheres and Cross-Spheres Interactions with Multimodal Observational Earth Data","created":"2025-05-29","cited_by_count":14,"area":null},{"id":"2506.05336","title":"VideoMolmo: Spatio-Temporal Grounding Meets Pointing","created":"2025-06-05","cited_by_count":14,"area":null},{"id":"2509.01907","title":"RSCC: A Large-Scale Remote Sensing Change Caption Dataset for Disaster Events","created":"2025-09-02","cited_by_count":14,"area":null},{"id":"2509.22820","title":"MMPB: It's Time for Multi-Modal Personalization","created":"2025-09-26","cited_by_count":14,"area":null},{"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":"2510.14630","title":"Adapting Self-Supervised Representations as a Latent Space for Efficient Generation","created":"2025-10-16","cited_by_count":13,"area":null},{"id":"2512.21095","title":"UniRec-0.1B: Unified Text and Formula Recognition with 0.1B Parameters","created":"2025-12-24","cited_by_count":13,"area":null},{"id":"2603.01840","title":"FireRed-OCR Technical Report","created":"2026-03-02","cited_by_count":13,"area":null},{"id":"2510.11549","title":"ODI-Bench: Can MLLMs Understand Immersive Omnidirectional Environments?","created":"2025-10-13","cited_by_count":12,"area":null},{"id":"2512.04451","title":"StreamEQA: Towards Streaming Video Understanding for Embodied Scenarios","created":"2025-12-04","cited_by_count":12,"area":null},{"id":"2604.26283","title":"MedSynapse-V: Bridging Visual Perception and Clinical Intuition via Latent Memory Evolution","created":"2026-04-29","cited_by_count":12,"area":null},{"id":"2605.04128","title":"JoyAI-Image: Awaking Spatial Intelligence in Unified Multimodal Understanding and Generation","created":"2026-05-05","cited_by_count":12,"area":null},{"id":"2505.23179","title":"DIP-R1: Deep Inspection and Perception with RL Looking Through and Understanding Complex Scenes","created":"2025-05-29","cited_by_count":11,"area":null},{"id":"2506.17202","title":"UniFork: Exploring Modality Alignment for Unified Multimodal Understanding and Generation","created":"2025-06-20","cited_by_count":11,"area":null},{"id":"2601.16093","title":"SAMTok: Representing Any Mask with Two Words","created":"2026-01-22","cited_by_count":11,"area":null},{"id":"2603.12255","title":"Spatial-TTT: Streaming Visual-based Spatial Intelligence with Test-Time Training","created":"2026-03-12","cited_by_count":11,"area":null},{"id":"2507.14902","title":"U-MARVEL: Unveiling Key Factors for Universal Multimodal Retrieval via Embedding Learning with MLLMs","created":"2025-07-20","cited_by_count":10,"area":null},{"id":"2509.23563","title":"RAVEN: Resilient Aerial Navigation via Open-Set Semantic Memory and Behavior Adaptation","created":"2025-09-28","cited_by_count":10,"area":null},{"id":"2510.02423","title":"RefineShot: Rethinking Cinematography Understanding with Foundational Skill Evaluation","created":"2025-10-02","cited_by_count":10,"area":null},{"id":"2511.23332","title":"UniGeoSeg: Towards Unified Open-World Segmentation for Geospatial Scenes","created":"2025-11-28","cited_by_count":10,"area":null},{"id":"2511.23386","title":"VQRAE: Representation Quantization Autoencoders for Multimodal Understanding, Generation and Reconstruction","created":"2025-11-28","cited_by_count":10,"area":null},{"id":"2601.20430","title":"Youtu-Parsing: Perception, Structuring and Recognition via High-Parallelism Decoding","created":"2026-01-28","cited_by_count":10,"area":null},{"id":"2602.16110","title":"OmniCT: Towards a Unified Slice-Volume LVLM for Comprehensive CT Analysis","created":"2026-02-18","cited_by_count":10,"area":null},{"id":"2602.19549","title":"Sculpting the Vector Space: Towards Efficient Multi-Vector Visual Document Retrieval via Prune-then-Merge Framework","created":"2026-02-23","cited_by_count":10,"area":null},{"id":"2506.21980","title":"R1-Track: Direct Application of MLLMs to Visual Object Tracking via Reinforcement Learning","created":"2025-06-27","cited_by_count":9,"area":null},{"id":"2510.09507","title":"PhysToolBench: Benchmarking Physical Tool Understanding for MLLMs","created":"2025-10-10","cited_by_count":9,"area":null},{"id":"2511.17952","title":"Multi-speaker Attention Alignment for Multimodal Social Interaction","created":"2025-11-22","cited_by_count":9,"area":null},{"id":"2512.00993","title":"PhotoFramer: Multi-modal Image Composition Instruction","created":"2025-11-30","cited_by_count":9,"area":null},{"id":"2602.04279","title":"ECG-R1: Protocol-Guided and Modality-Agnostic MLLM for Reliable ECG Interpretation","created":"2026-02-04","cited_by_count":9,"area":null},{"id":"2505.15818","title":"InstructSAM: A Training-Free Framework for Instruction-Oriented Remote Sensing Object Recognition","created":"2025-05-21","cited_by_count":8,"area":null},{"id":"2505.16175","title":"QuickVideo: Real-Time Long Video Understanding with System Algorithm Co-Design","created":"2025-05-22","cited_by_count":8,"area":null},{"id":"2505.23922","title":"ScaleLong: A Multi-Timescale Benchmark for Long Video Understanding","created":"2025-05-29","cited_by_count":8,"area":null},{"id":"2506.21742","title":"VRR-QA: Visual Relational Reasoning in Videos Beyond Explicit Cues","created":"2025-06-26","cited_by_count":8,"area":null},{"id":"2507.03541","title":"Foundation versus Domain-specific Models: Performance Comparison, Fusion, and Explainability in Face Recognition","created":"2025-07-04","cited_by_count":8,"area":null},{"id":"2509.19090","title":"Citrus-V: Advancing Medical Foundation Models with Unified Medical Image Grounding for Clinical Reasoning","created":"2025-09-23","cited_by_count":8,"area":null},{"id":"2510.10231","title":"Semantic Visual Anomaly Detection and Reasoning in AI-Generated Images","created":"2025-10-11","cited_by_count":8,"area":null},{"id":"2512.03666","title":"ToG-Bench: Task-Oriented Spatio-Temporal Grounding in Egocentric Videos","created":"2025-12-03","cited_by_count":8,"area":null},{"id":"2603.25072","title":"GIFT: Global Irreplaceability Frame Targeting for Efficient Video Understanding","created":"2026-03-26","cited_by_count":8,"area":null},{"id":"2605.24496","title":"EgoAction: Egocentric Action Composition with Reliability-Aware Temporal Fusion for the EPIC-KITCHENS Action Detection Challenge at CVPR 2026","created":"2026-05-23","cited_by_count":8,"area":null},{"id":"2505.24840","title":"The LLM Bottleneck: Why Open-Source Vision LLMs Struggle with Hierarchical Visual Recognition","created":"2025-05-30","cited_by_count":7,"area":null},{"id":"2507.18531","title":"IntentVCNet: Bridging Spatio-Temporal Gaps for Intention-Oriented Controllable Video Captioning","created":"2025-07-24","cited_by_count":7,"area":null},{"id":"2508.04062","title":"PET2Rep: Towards Vision-Language Model-Drived Automated Radiology Report Generation for Positron Emission Tomography","created":"2025-08-06","cited_by_count":7,"area":null},{"id":"2509.13939","title":"Can Current AI Models Count What We Mean, Not What They See? A Benchmark and Systematic Evaluation","created":"2025-09-17","cited_by_count":7,"area":null},{"id":"2509.16972","title":"The 1st Solution for 7th LSVOS RVOS Track: SaSaSa2VA","created":"2025-09-21","cited_by_count":7,"area":null},{"id":"2509.22228","title":"UrbanFeel: A Comprehensive Benchmark for Temporal and Perceptual Understanding of City Scenes through Human Perspective","created":"2025-09-26","cited_by_count":7,"area":null},{"id":"2510.09201","title":"Multimodal Prompt Optimization: Why Not Leverage Multiple Modalities for MLLMs","created":"2025-10-10","cited_by_count":7,"area":null},{"id":"2510.10982","title":"Catch-Only-One: Non-Transferable Examples for Model-Specific Authorization","created":"2025-10-13","cited_by_count":7,"area":null},{"id":"2510.26412","title":"LoCoT2V-Bench: Benchmarking Long-Form and Complex Text-to-Video Generation","created":"2025-10-30","cited_by_count":7,"area":null},{"id":"2511.03325","title":"SurgViVQA: Temporally-Grounded Video Question Answering for Surgical Scene Understanding","created":"2025-11-05","cited_by_count":7,"area":null},{"id":"2512.04763","title":"MemLoRA: Distilling Expert Adapters for On-Device Memory Systems","created":"2025-12-04","cited_by_count":7,"area":null},{"id":"2602.09823","title":"Covo-Audio Technical Report","created":"2026-02-10","cited_by_count":7,"area":null},{"id":"2505.16915","title":"DetailMaster: Can Your Text-to-Image Model Handle Long Prompts?","created":"2025-05-22","cited_by_count":6,"area":null},{"id":"2508.06072","title":"Can Large Models Fool the Eye? A New Turing Test for Biological Animation","created":"2025-08-08","cited_by_count":6,"area":null},{"id":"2508.19650","title":"Video-LevelGauge: Investigating Contextual Positional Bias in Large Video Language Models","created":"2025-08-27","cited_by_count":6,"area":null},{"id":"2508.21675","title":"Is this chart lying to me? Automating the detection of misleading visualizations","created":"2025-08-29","cited_by_count":6,"area":null}],"next_cursor":"100"}