{"total":1510,"rows":[{"id":"2606.02800","title":"Cosmos 3: Omnimodal World Models for Physical AI","created":"2026-06-01","cited_by_count":165,"area":"wm"},{"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":"2509.22186","title":"MinerU2.5: A Decoupled Vision-Language Model for Efficient High-Resolution Document Parsing","created":"2025-09-26","cited_by_count":116,"area":"mllm"},{"id":"2509.24251","title":"Latent Visual Reasoning","created":"2025-09-29","cited_by_count":104,"area":"lr"},{"id":"2604.08995","title":"Matrix-Game 3.0: Real-Time and Streaming Interactive World Model with Long-Horizon Memory","created":"2026-04-10","cited_by_count":100,"area":"wm"},{"id":"2510.14528","title":"PaddleOCR-VL: Boosting Multilingual Document Parsing via a 0.9B Ultra-Compact Vision-Language Model","created":"2025-10-16","cited_by_count":89,"area":"mllm"},{"id":"2510.06308","title":"Lumina-DiMOO: An Omni Diffusion Large Language Model for Multi-Modal Generation and Understanding","created":"2025-10-07","cited_by_count":88,"area":"diffusion"},{"id":"2511.13719","title":"Scaling Spatial Intelligence with Multimodal Foundation Models","created":"2025-11-17","cited_by_count":82,"area":null},{"id":"2511.21395","title":"Monet: Reasoning in Latent Visual Space Beyond Images and Language","created":"2025-11-26","cited_by_count":82,"area":"lr"},{"id":"2604.27393","title":"MiniCPM-o 4.5: Towards Real-Time Full-Duplex Omni-Modal Interaction","created":"2026-04-30","cited_by_count":78,"area":"mllm"},{"id":"2605.00078","title":"Being-H0.7: A Latent World-Action Model from Egocentric Videos","created":"2026-04-30","cited_by_count":75,"area":"wm"},{"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":"2601.12993","title":"Being-H0.5: Scaling Human-Centric Robot Learning for Cross-Embodiment Generalization","created":"2026-01-19","cited_by_count":66,"area":"vla"},{"id":"2509.15221","title":"ScaleCUA: Scaling Open-Source Computer Use Agents with Cross-Platform Data","created":"2025-09-18","cited_by_count":60,"area":"mllm"},{"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":"2510.27492","title":"ThinkMorph: Emergent Properties in Multimodal Interleaved Chain-of-Thought Reasoning","created":"2025-10-30","cited_by_count":56,"area":"lr"},{"id":"2510.17771","title":"Seeing but Not Believing: Probing the Disconnect Between Visual Attention and Answer Correctness in VLMs","created":"2025-10-20","cited_by_count":55,"area":"mllm"},{"id":"2604.05015","title":"Video-MME-v2: Towards the Next Stage in Benchmarks for Comprehensive Video Understanding","created":"2026-04-06","cited_by_count":55,"area":"wm"},{"id":"2512.07826","title":"OpenVE-3M: A Large-Scale High-Quality Dataset for Instruction-Guided Video Editing","created":"2025-12-08","cited_by_count":53,"area":null},{"id":"2509.03498","title":"OneCAT: Decoder-Only Auto-Regressive Model for Unified Understanding and Generation","created":"2025-09-03","cited_by_count":50,"area":"moe"},{"id":"2605.02881","title":"MolmoAct2: Action Reasoning Models for Real-world Deployment","created":"2026-05-04","cited_by_count":50,"area":"lr"},{"id":"2601.06521","title":"BabyVision: Visual Reasoning Beyond Language","created":"2026-01-10","cited_by_count":49,"area":"lr"},{"id":"2509.23141","title":"Earth-Agent: Unlocking the Full Landscape of Earth Observation with Agents","created":"2025-09-27","cited_by_count":46,"area":"agents"},{"id":"2511.21688","title":"G$^2$VLM: Geometry Grounded Vision Language Model with Unified 3D Reconstruction and Spatial Reasoning","created":"2025-11-26","cited_by_count":44,"area":"lr"},{"id":"2509.18905","title":"How Far are VLMs from Visual Spatial Intelligence? A Benchmark-Driven Perspective","created":"2025-09-23","cited_by_count":43,"area":"lr"},{"id":"2510.18269","title":"StreamingTOM: Streaming Token Compression for Efficient Video Understanding","created":"2025-10-21","cited_by_count":43,"area":"mllm"},{"id":"2512.15431","title":"Step-GUI Technical Report","created":"2025-12-17","cited_by_count":39,"area":"agents"},{"id":"2601.03309","title":"VLM4VLA: Revisiting Vision-Language-Models in Vision-Language-Action Models","created":"2026-01-06","cited_by_count":39,"area":"mllm"},{"id":"2605.25979","title":"LLaVA-OneVision-2: Towards Next-Generation Perceptual Intelligence","created":"2026-05-25","cited_by_count":39,"area":"mllm"},{"id":"2511.11007","title":"VisMem: Latent Vision Memory Unlocks Potential of Vision-Language Models","created":"2025-11-14","cited_by_count":37,"area":"mllm"},{"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":"2512.01989","title":"PAI-Bench: A Comprehensive Benchmark For Physical AI","created":"2025-12-01","cited_by_count":34,"area":"mllm"},{"id":"2512.02014","title":"TUNA: Taming Unified Visual Representations for Native Unified Multimodal Models","created":"2025-12-01","cited_by_count":34,"area":null},{"id":"2512.24330","title":"SenseNova-MARS: Empowering Multimodal Agentic Reasoning and Search via Reinforcement Learning","created":"2025-12-30","cited_by_count":33,"area":"lr"},{"id":"2601.09668","title":"STEP3-VL-10B Technical Report","created":"2026-01-14","cited_by_count":32,"area":null},{"id":"2605.12500","title":"SenseNova-U1: Unifying Multimodal Understanding and Generation with NEO-unify Architecture","created":"2026-05-12","cited_by_count":32,"area":"mllm"},{"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":"2510.27350","title":"RzenEmbed: Towards Comprehensive Multimodal Retrieval","created":"2025-10-31","cited_by_count":29,"area":"mllm"},{"id":"2512.05774","title":"Active Video Perception: Iterative Evidence Seeking for Agentic Long Video Understanding","created":"2025-12-05","cited_by_count":29,"area":"agents"},{"id":"2512.12623","title":"Reasoning Within the Mind: Dynamic Multimodal Interleaving in Latent Space","created":"2025-12-14","cited_by_count":28,"area":"lr"},{"id":"2603.02096","title":"FluxMem: Adaptive Hierarchical Memory for Streaming Video Understanding","created":"2026-03-02","cited_by_count":28,"area":null},{"id":"2603.09877","title":"InternVL-U: Democratizing Unified Multimodal Models for Understanding, Reasoning, Generation and Editing","created":"2026-03-10","cited_by_count":28,"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":"2510.10395","title":"AVoCaDO: An Audiovisual Video Captioner Driven by Temporal Orchestration","created":"2025-10-12","cited_by_count":27,"area":null},{"id":"2509.23652","title":"ReWatch-R1: Boosting Complex Video Reasoning in Large Vision-Language Models through Agentic Data Synthesis","created":"2025-09-28","cited_by_count":26,"area":"lr"},{"id":"2511.04460","title":"V-Thinker: Interactive Thinking with Images","created":"2025-11-06","cited_by_count":26,"area":"lr"},{"id":"2601.02358","title":"VINO: A Unified Visual Generator with Interleaved OmniModal Context","created":"2026-01-05","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":"2512.15693","title":"Skyra: AI-Generated Video Detection via Grounded Artifact Reasoning","created":"2025-12-17","cited_by_count":25,"area":"lr"},{"id":"2512.16584","title":"Sketch-in-Latents: Eliciting Unified Reasoning in MLLMs","created":"2025-12-18","cited_by_count":25,"area":"lr"},{"id":"2601.09708","title":"Fast-ThinkAct: Efficient Vision-Language-Action Reasoning via Verbalizable Latent Planning","created":"2026-01-14","cited_by_count":24,"area":"vla"},{"id":"2510.10991","title":"A Survey on Agentic Multimodal Large Language Models","created":"2025-10-13","cited_by_count":23,"area":"mllm"},{"id":"2510.11718","title":"CodePlot-CoT: Mathematical Visual Reasoning by Thinking with Code-Driven Images","created":"2025-10-13","cited_by_count":23,"area":"lr"},{"id":"2510.18873","title":"DSI-Bench: A Benchmark for Dynamic Spatial Intelligence","created":"2025-10-21","cited_by_count":23,"area":null},{"id":"2512.15258","title":"VLA-AN: An Efficient and Onboard Vision-Language-Action Framework for Aerial Navigation in Complex Environments","created":"2025-12-17","cited_by_count":23,"area":"vla"},{"id":"2602.03828","title":"AutoFigure: Generating and Refining Publication-Ready Scientific Illustrations","created":"2026-02-03","cited_by_count":23,"area":null},{"id":"2509.14232","title":"GenExam: A Multidisciplinary Text-to-Image Exam","created":"2025-09-17","cited_by_count":22,"area":null},{"id":"2511.14582","title":"OmniZip: Audio-Guided Dynamic Token Compression for Fast Omnimodal Large Language Models","created":"2025-11-18","cited_by_count":22,"area":"inference"},{"id":"2512.04952","title":"FASTer: Toward Efficient Autoregressive Vision Language Action Modeling via Neural Action Tokenization","created":"2025-12-04","cited_by_count":22,"area":"vla"},{"id":"2605.06388","title":"Reconstruction or Semantics? What Makes a Latent Space Useful for Robotic World Models","created":"2026-05-07","cited_by_count":22,"area":"wm"},{"id":"2510.02240","title":"RewardMap: Tackling Sparse Rewards in Fine-grained Visual Reasoning via Multi-Stage Reinforcement Learning","created":"2025-10-02","cited_by_count":21,"area":"lr"},{"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":"2511.12609","title":"Uni-MoE-2.0-Omni: Scaling Language-Centric Omnimodal Large Model with Advanced MoE, Training and Data","created":"2025-11-16","cited_by_count":21,"area":"moe"},{"id":"2601.07779","title":"OS-Symphony: A Holistic Framework for Robust and Generalist Computer-Using Agent","created":"2026-01-12","cited_by_count":21,"area":"mllm"},{"id":"2606.03264","title":"PaddleOCR-VL-1.6: Expanding the Frontier of Document Parsing with Under-Optimized Region Refinement and Progressive Post-Training","created":"2026-06-02","cited_by_count":21,"area":null},{"id":"2511.19575","title":"HunyuanOCR Technical Report","created":"2025-11-24","cited_by_count":20,"area":"mllm"},{"id":"2510.09606","title":"SpaceVista: All-Scale Visual Spatial Reasoning from mm to km","created":"2025-10-10","cited_by_count":19,"area":"lr"},{"id":"2510.24411","title":"OS-Sentinel: Towards Safety-Enhanced Mobile GUI Agents via Hybrid Validation in Realistic Workflows","created":"2025-10-28","cited_by_count":19,"area":"agents"},{"id":"2512.04540","title":"VideoMem: Enhancing Ultra-Long Video Understanding via Adaptive Memory Management","created":"2025-12-04","cited_by_count":19,"area":"mllm"},{"id":"2602.07055","title":"Theory of Space: Can Foundation Models Construct Spatial Beliefs through Active Exploration?","created":"2026-02-04","cited_by_count":19,"area":null},{"id":"2604.02190","title":"UniDriveVLA: Unifying Understanding, Perception, and Action Planning for Autonomous Driving","created":"2026-04-02","cited_by_count":19,"area":"vla"},{"id":"2510.14979","title":"From Pixels to Words -- Towards Native Vision-Language Primitives at Scale","created":"2025-10-16","cited_by_count":18,"area":"mllm"},{"id":"2510.18876","title":"Grasp Any Region: Towards Precise, Contextual Pixel Understanding for Multimodal LLMs","created":"2025-10-21","cited_by_count":18,"area":"mllm"},{"id":"2511.22850","title":"Resolving Evidence Sparsity: Agentic Context Engineering for Long-Document Understanding","created":"2025-11-28","cited_by_count":18,"area":"agents"},{"id":"2601.06803","title":"Forest Before Trees: Latent Superposition for Efficient Visual Reasoning","created":"2026-01-11","cited_by_count":18,"area":"lr"},{"id":"2601.18744","title":"TSRBench: A Comprehensive Multi-task Multi-modal Time Series Reasoning Benchmark for Generalist Models","created":"2026-01-26","cited_by_count":18,"area":"lr"},{"id":"2602.08024","title":"FlashVID: Efficient Video Large Language Models via Training-free Tree-based Spatiotemporal Token Merging","created":"2026-02-08","cited_by_count":18,"area":"inference"},{"id":"2602.15397","title":"ActionCodec: What Makes for Good Action Tokenizers","created":"2026-02-17","cited_by_count":18,"area":"mllm"},{"id":"2604.24763","title":"Tuna-2: Pixel Embeddings Beat Vision Encoders for Multimodal Understanding and Generation","created":"2026-04-27","cited_by_count":18,"area":null},{"id":"2510.13804","title":"Generative Universal Verifier as Multimodal Meta-Reasoner","created":"2025-10-15","cited_by_count":17,"area":"lr"},{"id":"2509.22496","title":"Where MLLMs Attend and What They Rely On: Explaining Autoregressive Token Generation","created":"2025-09-26","cited_by_count":16,"area":"mllm"},{"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":"2604.04184","title":"AURA: Always-On Understanding and Real-Time Assistance via Video Streams","created":"2026-04-05","cited_by_count":16,"area":null},{"id":"2606.18974","title":"Visual-OPSD: Cross-Modal On-Policy Self-Distillation for Efficient Unified Multimodal Reasoning","created":"2026-06-17","cited_by_count":16,"area":"lr"},{"id":"2509.16197","title":"MANZANO: A Simple and Scalable Unified Multimodal Model with a Hybrid Vision Tokenizer","created":"2025-09-19","cited_by_count":15,"area":"mllm"},{"id":"2510.03255","title":"SciTS: Scientific Time Series Understanding and Generation with LLMs","created":"2025-09-26","cited_by_count":15,"area":"lr"},{"id":"2510.11026","title":"GIR-Bench: Versatile Benchmark for Generating Images with Reasoning","created":"2025-10-13","cited_by_count":15,"area":"lr"},{"id":"2510.17777","title":"SparseVILA: Decoupling Visual Sparsity for Efficient VLM Inference","created":"2025-10-20","cited_by_count":15,"area":"mllm"},{"id":"2511.18538","title":"From Code Foundation Models to Agents and Applications: A Comprehensive Survey and Practical Guide to Code Intelligence","created":"2025-11-23","cited_by_count":15,"area":"agents"},{"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":"2511.21025","title":"CaptionQA: Is Your Caption as Useful as the Image Itself?","created":"2025-11-26","cited_by_count":15,"area":null},{"id":"2511.21662","title":"Multi-Crit: Benchmarking Multimodal Judges on Pluralistic Criteria-Following","created":"2025-11-26","cited_by_count":15,"area":"mllm"},{"id":"2601.15224","title":"PROGRESSLM: Towards Progress Reasoning in Vision-Language Models","created":"2026-01-21","cited_by_count":15,"area":"lr"},{"id":"2602.22808","title":"MiroFlow: Towards High-Performance and Robust Open-Source Agent Framework for General Deep Research Tasks","created":"2026-02-26","cited_by_count":15,"area":"agents"},{"id":"2603.28069","title":"MolmoPoint: Better Pointing for VLMs with Grounding Tokens","created":"2026-03-30","cited_by_count":15,"area":"mllm"},{"id":"2604.24300","title":"ReVSI: Rebuilding Visual Spatial Intelligence Evaluation for Accurate Assessment of VLM 3D Reasoning","created":"2026-04-27","cited_by_count":15,"area":"lr"},{"id":"2509.14033","title":"SAIL-VL2 Technical Report","created":"2025-09-17","cited_by_count":14,"area":"mllm"},{"id":"2509.25390","title":"SpinBench: Perspective and Rotation as a Lens on Spatial Reasoning in VLMs","created":"2025-09-29","cited_by_count":14,"area":"lr"},{"id":"2510.20707","title":"Mixing Importance with Diversity: Joint Optimization for KV Cache Compression in Large Vision-Language Models","created":"2025-10-23","cited_by_count":14,"area":"mllm"}],"next_cursor":"100"}