{"total":71,"rows":[{"id":"2505.14683","title":"Emerging Properties in Unified Multimodal Pretraining","created":"2025-05-20","cited_by_count":897,"area":null},{"id":"2506.09344","title":"Ming-Omni: A Unified Multimodal Model for Perception and Generation","created":"2025-06-11","cited_by_count":66,"area":null},{"id":"2603.27538","title":"LongCat-Next: Lexicalizing Modalities as Discrete Tokens","created":"2026-03-29","cited_by_count":36,"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":"2603.19217","title":"LVOmniBench: Pioneering Long Audio-Video Understanding Evaluation for Omnimodal LLMs","created":"2026-03-19","cited_by_count":24,"area":null},{"id":"2602.05384","title":"Dolphin-v2: Universal Document Parsing via Scalable Anchor Prompting","created":"2026-02-05","cited_by_count":22,"area":null},{"id":"2510.14359","title":"AI for Service: Proactive Assistance with AI Glasses","created":"2025-10-16","cited_by_count":20,"area":null},{"id":"2512.14856","title":"T5Gemma 2: Seeing, Reading, and Understanding Longer","created":"2025-12-16","cited_by_count":17,"area":null},{"id":"2505.24138","title":"AMSbench: A Comprehensive Benchmark for Evaluating MLLM Capabilities in AMS Circuits","created":"2025-05-30","cited_by_count":15,"area":null},{"id":"2506.03131","title":"Native-Resolution Image Synthesis","created":"2025-06-03","cited_by_count":15,"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":"2511.20351","title":"Thinking in 360{\\deg}: Humanoid Visual Search in the Wild","created":"2025-11-25","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":"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":"2512.20617","title":"SpatialTree: How Spatial Abilities Branch Out in MLLMs","created":"2025-12-23","cited_by_count":12,"area":null},{"id":"2510.09507","title":"PhysToolBench: Benchmarking Physical Tool Understanding for MLLMs","created":"2025-10-10","cited_by_count":9,"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":"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":"2605.08747","title":"Done, But Not Sure: Disentangling World Completion from Self-Termination in Embodied Agents","created":"2026-05-09","cited_by_count":7,"area":null},{"id":"2606.25041","title":"Wan-Streamer v0.1: End-to-end Real-time Interactive Foundation Models","created":"2026-06-23","cited_by_count":7,"area":null},{"id":"2601.23261","title":"TEON: Tensorized Orthonormalization Beyond Layer-Wise Muon for Large Language Model Pre-Training","created":"2026-01-30","cited_by_count":6,"area":null},{"id":"2602.21545","title":"MUON+: Towards More Effective Muon via One Additional Normalization Step for LLM Pre-training","created":"2026-02-25","cited_by_count":6,"area":null},{"id":"2603.16590","title":"BATQuant: Outlier-resilient MXFP4 Quantization via Learnable Block-wise Optimization","created":"2026-03-17","cited_by_count":6,"area":null},{"id":"2604.07296","title":"OpenSpatial: A Principled Data Engine for Empowering Spatial Intelligence","created":"2026-04-08","cited_by_count":6,"area":null},{"id":"2606.14502","title":"From Chatbot to Digital Colleague: The Paradigm Shift Toward Persistent Autonomous AI","created":"2026-06-12","cited_by_count":6,"area":null},{"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":"2506.00893","title":"Affordance Benchmark for MLLMs","created":"2025-06-01","cited_by_count":5,"area":null},{"id":"2602.12617","title":"GeoAgent: Learning to Geolocate Everywhere with Reinforced Geographic Characteristics","created":"2026-02-13","cited_by_count":5,"area":null},{"id":"2602.15772","title":"Understanding vs. Generation: Navigating Optimization Dilemma in Multimodal Models","created":"2026-02-17","cited_by_count":5,"area":null},{"id":"2605.10343","title":"EvoStreaming: Your Offline Video Model Is a Natively Streaming Assistant","created":"2026-05-11","cited_by_count":5,"area":null},{"id":"2605.15735","title":"UAM: A Dual-Stream Perspective on Forgetting in VLA Training","created":"2026-05-15","cited_by_count":5,"area":null},{"id":"2602.06391","title":"POINTS-GUI-G: GUI-Grounding Journey","created":"2026-02-06","cited_by_count":4,"area":null},{"id":"2606.18249","title":"Unified Multimodal Autoregressive Modeling with Shared Context-Visual Tokenizer is Key to Unification","created":"2026-06-16","cited_by_count":4,"area":null},{"id":"2602.01623","title":"Omni-Judge: Can Omni-LLMs Serve as Human-Aligned Judges for Text-Conditioned Audio-Video Generation?","created":"2026-02-02","cited_by_count":3,"area":null},{"id":"2602.06442","title":"ChatUMM: Robust Context Tracking for Conversational Interleaved Generation","created":"2026-02-06","cited_by_count":3,"area":null},{"id":"2606.00750","title":"I-WebGenBench : Evaluating Interactivity in LLM-Generated Scientific Web Applications","created":"2026-05-30","cited_by_count":3,"area":null},{"id":"2606.20521","title":"HumanScale: Egocentric Human Video Can Outperform Real-Robot Data for Embodied Pretraining","created":"2026-06-18","cited_by_count":3,"area":null},{"id":"2506.10912","title":"Breaking Bad Molecules: Are MLLMs Ready for Structure-Level Molecular Detoxification?","created":"2025-06-12","cited_by_count":2,"area":null},{"id":"2507.12463","title":"MMHU: A Massive-Scale Multimodal Benchmark for Human Behavior Understanding","created":"2025-07-16","cited_by_count":2,"area":null},{"id":"2512.17196","title":"UmniBench: Unified Understand and Generation Model Oriented Omni-dimensional Benchmark","created":"2025-12-19","cited_by_count":2,"area":null},{"id":"2602.21042","title":"OmniOCR: Generalist OCR for Ethnic Minority Languages","created":"2026-02-24","cited_by_count":2,"area":null},{"id":"2603.09896","title":"Stepping VLMs onto the Court: Benchmarking Spatial Intelligence in Sports","created":"2026-03-10","cited_by_count":2,"area":null},{"id":"2603.29846","title":"SNEAK: Evaluating Strategic Communication and Information Leakage in Large Language Models","created":"2026-03-31","cited_by_count":2,"area":null},{"id":"2605.13045","title":"Large Language Models Lack Temporal Awareness of Medical Knowledge","created":"2026-05-13","cited_by_count":2,"area":null},{"id":"2601.00561","title":"AEGIS: Exploring the Limit of World Knowledge Capabilities for Unified Mulitmodal Models","created":"2026-01-02","cited_by_count":1,"area":null},{"id":"2602.09843","title":"Kelix Technical Report","created":"2026-02-10","cited_by_count":1,"area":null},{"id":"2603.12147","title":"EgoIntent: A Pre-Outcome Micro-Step Benchmark for Understanding What, Why, and Next","created":"2026-03-12","cited_by_count":1,"area":null},{"id":"2603.13397","title":"TennisExpert: Towards Expert-Level Analytical Sports Video Understanding","created":"2026-03-11","cited_by_count":1,"area":null},{"id":"2604.02505","title":"Optimal Projection-Free Adaptive SGD for Matrix Optimization","created":"2026-04-02","cited_by_count":1,"area":null},{"id":"2604.04475","title":"Discrete Prototypical Memories for Federated Time Series Foundation Models","created":"2026-04-06","cited_by_count":1,"area":null},{"id":"2604.20878","title":"AITP: Traffic Accident Responsibility Allocation via Multimodal Large Language Models","created":"2026-04-11","cited_by_count":1,"area":null},{"id":"2605.07593","title":"TraceAV-Bench: Benchmarking Multi-Hop Trajectory Reasoning over Long Audio-Visual Videos","created":"2026-05-08","cited_by_count":1,"area":null},{"id":"2605.22907","title":"VideoOdyssey: A Benchmark for Ultra-Long-Context and Omni-Modal Video Understanding","created":"2026-05-21","cited_by_count":1,"area":null},{"id":"2606.27313","title":"ViQ: Text-Aligned Visual Quantized Representations at Any Resolution","created":"2026-06-25","cited_by_count":1,"area":null},{"id":"2607.13558","title":"Multi-Agent Collaborative Reasoning with Tool-Augmented Evidence for Urban Region Profiling","created":"2026-07-15","cited_by_count":1,"area":null},{"id":"2607.18789","title":"Moving Alphabet: A Controlled Study of Training Data for Text-to-Video Generation","created":"2026-07-21","cited_by_count":1,"area":null},{"id":"2608.07570","title":"COMEX: A Composition-Grounded Benchmark and Learning Framework for Explainable Aesthetic Image Cropping","created":"2026-08-04","cited_by_count":1,"area":null},{"id":"2509.14886","title":"A Multi-To-One Interview Paradigm for Efficient MLLM Evaluation","created":"2025-09-18","cited_by_count":0,"area":null},{"id":"2512.04580","title":"CryptoTensors: A Light-Weight Large Language Model File Format for Highly-Secure Model Distribution","created":"2025-12-04","cited_by_count":0,"area":null},{"id":"2603.04980","title":"A Simple Baseline for Unifying Understanding, Generation, and Editing via Vanilla Next-token Prediction","created":"2026-03-05","cited_by_count":0,"area":null},{"id":"2603.17761","title":"Evidence Packing for Cross-Domain Image Deepfake Detection with LVLMs","created":"2026-03-18","cited_by_count":0,"area":null},{"id":"2603.27259","title":"Seeing the Scene Matters: Revealing Forgetting in Video Understanding Models with a Scene-Aware Long-Video Benchmark","created":"2026-03-28","cited_by_count":0,"area":null},{"id":"2603.28474","title":"CiQi-Agent: Aligning Vision, Tools and Aesthetics in Multimodal Agent for Cultural Reasoning on Chinese Porcelains","created":"2026-03-30","cited_by_count":0,"area":null},{"id":"2604.10666","title":"Omnimodal Dataset Distillation via High-order Proxy Alignment","created":"2026-04-12","cited_by_count":0,"area":null},{"id":"2604.25186","title":"FCMBench-Video: Benchmarking Document Video Intelligence","created":"2026-04-28","cited_by_count":0,"area":null},{"id":"2605.17288","title":"When Efficiency Backfires: Cascading LLMs Trigger Cascade Failure under Adversarial Attack","created":"2026-05-17","cited_by_count":0,"area":null},{"id":"2606.27382","title":"AI-Model Network: Concept, Current State and Future","created":"2026-05-25","cited_by_count":0,"area":null},{"id":"2607.14660","title":"VIABench: A Comprehensive Video Benchmark Collected from Blind Individuals for Visual Impairment Assistance","created":"2026-07-16","cited_by_count":0,"area":null},{"id":"2607.20389","title":"PercepCap: Video Captioner with Structured Spatio-Temporal Perception","created":"2026-07-22","cited_by_count":0,"area":null},{"id":"2608.06549","title":"TradeVerse: A Longitudinal Benchmark of Political Negotiation in International Trade","created":"2026-08-06","cited_by_count":0,"area":null},{"id":"2609.33212","title":"CoLMbo-SV: A Grounded Language Model for Explainable Speaker Verification","created":"2026-09-27","cited_by_count":0,"area":null}],"next_cursor":null}