{"total":223,"rows":[{"id":"2404.14219","title":"Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone","created":"2024-04-22","cited_by_count":1917,"area":null},{"id":"2504.17761","title":"Step1X-Edit: A Practical Framework for General Image Editing","created":"2025-04-24","cited_by_count":429,"area":null},{"id":"2409.10695","title":"Playground v3: Improving Text-to-Image Alignment with Deep-Fusion Large Language Models","created":"2024-09-16","cited_by_count":116,"area":null},{"id":"2502.12894","title":"CAST: Component-Aligned 3D Scene Reconstruction from an RGB Image","created":"2025-02-18","cited_by_count":106,"area":null},{"id":"2502.04144","title":"HD-EPIC: A Highly-Detailed Egocentric Video Dataset","created":"2025-02-06","cited_by_count":104,"area":null},{"id":"2503.21758","title":"Lumina-Image 2.0: A Unified and Efficient Image Generative Framework","created":"2025-03-27","cited_by_count":96,"area":null},{"id":"2505.04512","title":"HunyuanCustom: A Multimodal-Driven Architecture for Customized Video Generation","created":"2025-05-07","cited_by_count":87,"area":null},{"id":"2505.02567","title":"Unified Multimodal Understanding and Generation Models: Advances, Challenges, and Opportunities","created":"2025-05-05","cited_by_count":85,"area":null},{"id":"2312.09158","title":"General Object Foundation Model for Images and Videos at Scale","created":"2023-12-14","cited_by_count":71,"area":null},{"id":"2501.15891","title":"Any2AnyTryon: Leveraging Adaptive Position Embeddings for Versatile Virtual Clothing Tasks","created":"2025-01-27","cited_by_count":63,"area":null},{"id":"2504.21530","title":"RoboGround: Robotic Manipulation with Grounded Vision-Language Priors","created":"2025-04-30","cited_by_count":51,"area":null},{"id":"2504.14603","title":"UFO2: The Desktop AgentOS","created":"2025-04-20","cited_by_count":41,"area":null},{"id":"2505.20256","title":"Omni-R1: Reinforcement Learning for Omnimodal Reasoning via Two-System Collaboration","created":"2025-05-26","cited_by_count":41,"area":null},{"id":"2403.19596","title":"LocCa: Visual Pretraining with Location-aware Captioners","created":"2024-03-28","cited_by_count":35,"area":null},{"id":"2501.12931","title":"DynamicEarth: How Far are We from Open-Vocabulary Change Detection?","created":"2025-01-22","cited_by_count":21,"area":null},{"id":"2411.16198","title":"Interpreting Object-level Foundation Models via Visual Precision Search","created":"2024-11-25","cited_by_count":20,"area":null},{"id":"2506.09984","title":"InterActHuman: Multi-Concept Human Animation with Layout-Aligned Audio Conditions","created":"2025-06-11","cited_by_count":20,"area":null},{"id":"2504.01008","title":"IntrinsiX: High-Quality PBR Generation using Image Priors","created":"2025-04-01","cited_by_count":19,"area":null},{"id":"2506.07848","title":"PolyVivid: Vivid Multi-Subject Video Generation with Cross-Modal Interaction and Enhancement","created":"2025-06-09","cited_by_count":16,"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":"2407.16696","title":"PartGLEE: A Foundation Model for Recognizing and Parsing Any Objects","created":"2024-07-23","cited_by_count":15,"area":null},{"id":"2410.23144","title":"Public Domain 12M: A Highly Aesthetic Image-Text Dataset with Novel Governance Mechanisms","created":"2024-10-30","cited_by_count":15,"area":null},{"id":"2501.17635","title":"In-Context Meta LoRA Generation","created":"2025-01-29","cited_by_count":15,"area":null},{"id":"2503.21749","title":"LeX-Art: Rethinking Text Generation via Scalable High-Quality Data Synthesis","created":"2025-03-27","cited_by_count":15,"area":null},{"id":"2507.05427","title":"OpenWorldSAM: Extending SAM2 for Universal Image Segmentation with Language Prompts","created":"2025-07-07","cited_by_count":15,"area":null},{"id":"2410.17241","title":"Frontiers in Intelligent Colonoscopy","created":"2024-10-22","cited_by_count":14,"area":null},{"id":"2412.15588","title":"NeSyCoCo: A Neuro-Symbolic Concept Composer for Compositional Generalization","created":"2024-12-20","cited_by_count":13,"area":null},{"id":"2501.08505","title":"Yuan: Yielding Unblemished Aesthetics Through A Unified Network for Visual Imperfections Removal in Generated Images","created":"2025-01-15","cited_by_count":13,"area":null},{"id":"2503.16611","title":"A Recipe for Generating 3D Worlds From a Single Image","created":"2025-03-20","cited_by_count":13,"area":null},{"id":"2403.07478","title":"Towards Graph Foundation Models for Personalization","created":"2024-03-12","cited_by_count":12,"area":null},{"id":"2410.17883","title":"Lightweight Neural App Control","created":"2024-10-23","cited_by_count":12,"area":null},{"id":"2601.10592","title":"Action100M: A Large-scale Video Action Dataset","created":"2026-01-15","cited_by_count":12,"area":null},{"id":"2503.10596","title":"GroundingSuite: Measuring Complex Multi-Granular Pixel Grounding","created":"2025-03-13","cited_by_count":11,"area":null},{"id":"2504.12104","title":"Logits DeConfusion with CLIP for Few-Shot Learning","created":"2025-04-16","cited_by_count":11,"area":null},{"id":"2504.13987","title":"Entropy Rectifying Guidance for Diffusion and Flow Models","created":"2025-04-18","cited_by_count":11,"area":null},{"id":"2507.23734","title":"RAGNet: Large-scale Reasoning-based Affordance Segmentation Benchmark towards General Grasping","created":"2025-07-31","cited_by_count":11,"area":null},{"id":"2502.15392","title":"Chitrarth: Bridging Vision and Language for a Billion People","created":"2025-02-21","cited_by_count":10,"area":null},{"id":"2504.07836","title":"AerialVG: A Challenging Benchmark for Aerial Visual Grounding by Exploring Positional Relations","created":"2025-04-10","cited_by_count":10,"area":null},{"id":"2511.18416","title":"4D-VGGT: A General Foundation Model with SpatioTemporal Awareness for Dynamic Scene Geometry Estimation","created":"2025-11-23","cited_by_count":10,"area":null},{"id":"2506.21233","title":"ReME: A Data-Centric Framework for Training-Free Open-Vocabulary Segmentation","created":"2025-06-26","cited_by_count":9,"area":null},{"id":"2508.04153","title":"ICM-Fusion: In-Context Meta-Optimized LoRA Fusion for Multi-Task Adaptation","created":"2025-08-06","cited_by_count":9,"area":null},{"id":"2410.00231","title":"Helpful DoggyBot: Open-World Object Fetching using Legged Robots and Vision-Language Models","created":"2024-09-30","cited_by_count":8,"area":null},{"id":"2501.08303","title":"Advancing Semantic Future Prediction through Multimodal Visual Sequence Transformers","created":"2025-01-14","cited_by_count":8,"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":"2505.16314","title":"NTIRE 2025 challenge on Text to Image Generation Model Quality Assessment","created":"2025-05-22","cited_by_count":8,"area":null},{"id":"2505.17476","title":"The Coherence Trap: When MLLM-Crafted Narratives Exploit Manipulated Visual Contexts","created":"2025-05-23","cited_by_count":8,"area":null},{"id":"2506.17374","title":"From Drawings to Decisions: A Hybrid Vision-Language Framework for Parsing 2D Engineering Drawings into Structured Manufacturing Knowledge","created":"2025-06-20","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":"2511.20648","title":"LocateAnything3D: Vision-Language 3D Detection with Chain-of-Sight","created":"2025-11-25","cited_by_count":8,"area":null},{"id":"2512.13089","title":"UniVCD: A New Method for Unsupervised Change Detection in the Open-Vocabulary Era","created":"2025-12-15","cited_by_count":7,"area":null},{"id":"2607.06560","title":"Vision as Unified Multimodal Generation","created":"2026-07-07","cited_by_count":7,"area":null},{"id":"2312.03032","title":"ZeroReg: Zero-Shot Point Cloud Registration with Foundation Models","created":"2023-12-05","cited_by_count":6,"area":null},{"id":"2411.08127","title":"TIPO: Text to Image with Text Presampling for Prompt Optimization","created":"2024-11-12","cited_by_count":6,"area":null},{"id":"2412.10624","title":"CATALOG: A Camera Trap Language-guided Contrastive Learning Model","created":"2024-12-14","cited_by_count":6,"area":null},{"id":"2503.02910","title":"LangGas: Introducing Language in Selective Zero-Shot Background Subtraction for Semi-Transparent Gas Leak Detection with a New Dataset","created":"2025-03-04","cited_by_count":6,"area":null},{"id":"2511.21945","title":"GENA3D: Generative Amodal 3D Modeling by Bridging 2D Priors and 3D Coherence","created":"2025-11-26","cited_by_count":6,"area":null},{"id":"2601.05244","title":"GREx: Generalized Referring Expression Segmentation, Comprehension, and Generation","created":"2026-01-08","cited_by_count":6,"area":null},{"id":"2412.10604","title":"EvalGIM: A Library for Evaluating Generative Image Models","created":"2024-12-13","cited_by_count":5,"area":null},{"id":"2503.01936","title":"Decision-Focused Fine-Tuning of Time Series Foundation Models for Dispatchable Feeder Optimization","created":"2025-03-03","cited_by_count":5,"area":null},{"id":"2504.00844","title":"PRISM-0: A Predicate-Rich Scene Graph Generation Framework for Zero-Shot Open-Vocabulary Tasks","created":"2025-04-01","cited_by_count":5,"area":null},{"id":"2505.01322","title":"FreeInsert: Disentangled Text-Guided Object Insertion in 3D Gaussian Scene without Spatial Priors","created":"2025-05-02","cited_by_count":5,"area":null},{"id":"2505.21050","title":"Advancing high-fidelity 3D and Texture Generation with 2.5D latents","created":"2025-05-27","cited_by_count":5,"area":null},{"id":"2605.07141","title":"Qwen3-VL-Seg: Unlocking Open-World Referring Segmentation with Vision-Language Grounding","created":"2026-05-08","cited_by_count":5,"area":null},{"id":"2312.07532","title":"Interfacing Foundation Models' Embeddings","created":"2023-12-12","cited_by_count":4,"area":null},{"id":"2408.14756","title":"Training-Free Time-Series Anomaly Detection: Leveraging Image Foundation Models","created":"2024-08-27","cited_by_count":4,"area":null},{"id":"2501.05079","title":"Multimodal-to-Text Prompt Engineering in Large Language Models Using Feature Embeddings for GNSS Interference Characterization","created":"2025-01-09","cited_by_count":4,"area":null},{"id":"2502.13898","title":"GroundCap: A Visually Grounded Image Captioning Dataset","created":"2025-02-19","cited_by_count":4,"area":null},{"id":"2505.02867","title":"RESAnything: Attribute Prompting for Arbitrary Referring Segmentation","created":"2025-05-03","cited_by_count":4,"area":null},{"id":"2509.25991","title":"Towards Unified Multimodal Misinformation Detection in Social Media: A Benchmark Dataset and Baseline","created":"2025-09-30","cited_by_count":4,"area":null},{"id":"2510.26800","title":"OmniX: From Unified Panoramic Generation and Perception to Graphics-Ready 3D Scenes","created":"2025-10-30","cited_by_count":4,"area":null},{"id":"2602.03838","title":"PrevizWhiz: Combining Rough 3D Scenes and 2D Video to Guide Generative Video Previsualization","created":"2026-02-03","cited_by_count":4,"area":null},{"id":"2603.12265","title":"OmniStream: Mastering Perception, Reconstruction and Action in Continuous Streams","created":"2026-03-12","cited_by_count":4,"area":null},{"id":"2408.03340","title":"An Empirical Comparison of Video Frame Sampling Methods for Multi-Modal RAG Retrieval","created":"2024-07-22","cited_by_count":3,"area":null},{"id":"2409.16159","title":"ComiCap: A VLMs pipeline for dense captioning of Comic Panels","created":"2024-09-24","cited_by_count":3,"area":null},{"id":"2411.10639","title":"MTA: Multimodal Task Alignment for BEV Perception and Captioning","created":"2024-11-16","cited_by_count":3,"area":null},{"id":"2503.16413","title":"M3: 3D-Spatial MultiModal Memory","created":"2025-03-20","cited_by_count":3,"area":null},{"id":"2503.22869","title":"SIGHT: Synthesizing Image-Text Conditioned and Geometry-Guided 3D Hand-Object Trajectories","created":"2025-03-28","cited_by_count":3,"area":null},{"id":"2505.15765","title":"Constructing a 3D Scene from a Single Image","created":"2025-05-21","cited_by_count":3,"area":null},{"id":"2507.06972","title":"A multi-modal dataset for insect biodiversity with imagery and DNA at the trap and individual level","created":"2025-07-09","cited_by_count":3,"area":null},{"id":"2509.13484","title":"MINGLE: VLMs for Semantically Complex Region Detection in Urban Scenes","created":"2025-09-16","cited_by_count":3,"area":null},{"id":"2510.17866","title":"MUSE: Model-based Uncertainty-aware Similarity Estimation for zero-shot 2D Object Detection and Segmentation","created":"2025-10-15","cited_by_count":3,"area":null},{"id":"2511.22777","title":"Improving Robotic Manipulation Robustness via NICE Scene Surgery","created":"2025-11-27","cited_by_count":3,"area":null},{"id":"2604.05761","title":"Improving Controllable Generation: Faster Training and Better Performance via $x_0$-Supervision","created":"2026-04-07","cited_by_count":3,"area":null},{"id":"2605.17179","title":"iMiGUE-3K: A Large-Scale Benchmark for Micro-Gesture Analysis with Self-Supervised Learning","created":"2026-05-16","cited_by_count":3,"area":null},{"id":"2409.01109","title":"SOOD-ImageNet: a Large-Scale Dataset for Semantic Out-Of-Distribution Image Classification and Semantic Segmentation","created":"2024-09-02","cited_by_count":2,"area":null},{"id":"2410.04634","title":"Is What You Ask For What You Get? Investigating Concept Associations in Text-to-Image Models","created":"2024-10-06","cited_by_count":2,"area":null},{"id":"2410.11963","title":"CtrlSynth: Controllable Image Text Synthesis for Data-Efficient Multimodal Learning","created":"2024-10-15","cited_by_count":2,"area":null},{"id":"2411.15605","title":"GIFT: A Framework Towards Global Interpretable Faithful Textual Explanations of Vision Classifiers","created":"2024-11-23","cited_by_count":2,"area":null},{"id":"2501.08083","title":"Benchmarking Vision Foundation Models for Input Monitoring in Autonomous Driving","created":"2025-01-14","cited_by_count":2,"area":null},{"id":"2504.03621","title":"PILOT: A Promptable Interleaved Layout-aware OCR Transformer","created":"2025-04-04","cited_by_count":2,"area":null},{"id":"2506.08774","title":"Multimodal Representation Alignment for Cross-modal Information Retrieval","created":"2025-06-10","cited_by_count":2,"area":null},{"id":"2506.19331","title":"Segment Any 3D-Part in a Scene from a Sentence","created":"2025-06-24","cited_by_count":2,"area":null},{"id":"2509.26604","title":"Video Object Segmentation-Aware Audio Generation","created":"2025-09-30","cited_by_count":2,"area":null},{"id":"2510.13419","title":"Ultra High-Resolution Image Inpainting with Patch-Based Content Consistency Adapter","created":"2025-10-15","cited_by_count":2,"area":null},{"id":"2510.16051","title":"GUIrilla: A Scalable Framework for Automated Desktop UI Exploration","created":"2025-10-16","cited_by_count":2,"area":null},{"id":"2510.18083","title":"Chimera: Compositional Image Generation using Part-based Concepting","created":"2025-10-20","cited_by_count":2,"area":null},{"id":"2511.04384","title":"Multi-Task Learning for Visually Grounded Reasoning in Gastrointestinal VQA","created":"2025-11-06","cited_by_count":2,"area":null},{"id":"2512.08282","title":"PAVAS: Physics-Aware Video-to-Audio Synthesis","created":"2025-12-09","cited_by_count":2,"area":null},{"id":"2512.13953","title":"From Unlearning to UNBRANDING: A Benchmark for Trademark-Safe Text-to-Image Generation","created":"2025-12-15","cited_by_count":2,"area":null},{"id":"2512.19943","title":"SE360: Semantic Edit in 360$^\\circ$ Panoramas via Hierarchical Data Construction","created":"2025-12-23","cited_by_count":2,"area":null}],"next_cursor":"100"}