{"total":605,"rows":[{"id":"2604.20329","title":"Image Generators are Generalist Vision Learners","created":"2026-04-22","cited_by_count":43,"area":null},{"id":"2603.02175","title":"Kiwi-Edit: Versatile Video Editing via Instruction and Reference Guidance","created":"2026-03-02","cited_by_count":36,"area":null},{"id":"2601.19887","title":"VGGT-SLAM 2.0: Real-time Dense Feed-forward Scene Reconstruction","created":"2026-01-27","cited_by_count":28,"area":null},{"id":"2603.24458","title":"OmniWeaving: Towards Unified Video Generation with Free-form Composition and Reasoning","created":"2026-03-25","cited_by_count":27,"area":null},{"id":"2511.19046","title":"MedSAM3: Delving into Segment Anything with Medical Concepts","created":"2025-11-24","cited_by_count":26,"area":null},{"id":"2601.10880","title":"Medical SAM3: A Foundation Model for Universal Prompt-Driven Medical Image Segmentation","created":"2026-01-15","cited_by_count":25,"area":null},{"id":"2512.08730","title":"SegEarth-OV3: Exploring SAM 3 for Open-Vocabulary Semantic Segmentation in Remote Sensing Images","created":"2025-12-09","cited_by_count":16,"area":null},{"id":"2604.01001","title":"EgoSim: Egocentric World Simulator for Embodied Interaction Generation","created":"2026-04-01","cited_by_count":14,"area":null},{"id":"2607.09024","title":"Video Generation Models are General-Purpose Vision Learners","created":"2026-07-10","cited_by_count":14,"area":null},{"id":"2604.11998","title":"The Second Challenge on Cross-Domain Few-Shot Object Detection at NTIRE 2026: Methods and Results","created":"2026-04-13","cited_by_count":13,"area":null},{"id":"2603.28480","title":"INSID3: Training-Free In-Context Segmentation with DINOv3","created":"2026-03-30","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":"2602.16356","title":"Articulated 3D Scene Graphs for Open-World Mobile Manipulation","created":"2026-02-18","cited_by_count":11,"area":null},{"id":"2603.16869","title":"SegviGen: Repurposing 3D Generative Model for Part Segmentation","created":"2026-03-17","cited_by_count":10,"area":null},{"id":"2603.22387","title":"Efficient Universal Perception Encoder","created":"2026-03-23","cited_by_count":10,"area":null},{"id":"2604.04911","title":"SpatialEdit: Benchmarking Fine-Grained Image Spatial Editing","created":"2026-04-06","cited_by_count":10,"area":null},{"id":"2606.18363","title":"Guava: Distilling Frontier VLMs into a Compact Agent through a Robotic Manipulation Harness","created":"2026-06-16","cited_by_count":10,"area":null},{"id":"2512.04585","title":"SAM3-I: Segment Anything with Instructions","created":"2025-12-04","cited_by_count":9,"area":null},{"id":"2604.02296","title":"VOID: Video Object and Interaction Deletion","created":"2026-04-02","cited_by_count":9,"area":null},{"id":"2602.20119","title":"NovaPlan: Zero-Shot Long-Horizon Manipulation via Closed-Loop Video Language Planning","created":"2026-02-23","cited_by_count":8,"area":null},{"id":"2606.01399","title":"PAI-Studio: Cinematic Video Background Replacement with Camera-Aware Motion","created":"2026-05-31","cited_by_count":8,"area":null},{"id":"2606.10804","title":"SCAIL-2: Unifying Controlled Character Animation with End-to-End In-Context Conditioning","created":"2026-06-09","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":"2602.13444","title":"FlowHOI: Flow-based Semantics-Grounded Generation of Hand-Object Interactions for Dexterous Robot Manipulation","created":"2026-02-13","cited_by_count":7,"area":null},{"id":"2604.05212","title":"Boxer: Robust Lifting of Open-World 2D Bounding Boxes to 3D","created":"2026-04-06","cited_by_count":7,"area":null},{"id":"2603.07660","title":"Holi-Spatial: Evolving Video Streams into Holistic 3D Spatial Intelligence","created":"2026-03-08","cited_by_count":6,"area":null},{"id":"2603.23502","title":"OccAny: Generalized Unconstrained Urban 3D Occupancy","created":"2026-03-24","cited_by_count":6,"area":null},{"id":"2605.26102","title":"InstructSAM: Segment Any Instance with Any Instructions","created":"2026-05-25","cited_by_count":6,"area":null},{"id":"2605.30338","title":"REST3D: Reconstructing Physically Stable 3D Scenes from a Single Image","created":"2026-05-28","cited_by_count":6,"area":null},{"id":"2606.31388","title":"One Video, One World: Turning Monocular Video into Physical 4D Scenes","created":"2026-06-30","cited_by_count":6,"area":null},{"id":"2603.09283","title":"From Ideal to Real: Stable Video Object Removal under Imperfect Conditions","created":"2026-03-10","cited_by_count":5,"area":null},{"id":"2603.17840","title":"Video Understanding: From Geometry and Semantics to Unified Models","created":"2026-03-18","cited_by_count":5,"area":null},{"id":"2604.06870","title":"RefineAnything: Multimodal Region-Specific Refinement for Perfect Local Details","created":"2026-04-08","cited_by_count":5,"area":null},{"id":"2604.27621","title":"Robot Learning from Human Videos: A Survey","created":"2026-04-30","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":"2606.03994","title":"SimuScene: Simulation-Ready Compositional 3D Scene Reconstruction from a Single Image","created":"2026-06-02","cited_by_count":5,"area":null},{"id":"2606.11628","title":"LUCID: Learning Embodiment-Agnostic Intent Models from Unstructured Human Videos for Scalable Dexterous Robot Skill Acquisition","created":"2026-06-10","cited_by_count":5,"area":null},{"id":"2606.18558","title":"MolmoMotion: Forecasting Point Trajectories in 3D with Language Instruction","created":"2026-06-17","cited_by_count":5,"area":null},{"id":"2608.12122","title":"HandEdit: A Unified Benchmark for Egocentric Human-to-Robot Dexterous Hand Image Editing","created":"2026-08-12","cited_by_count":5,"area":null},{"id":"2512.01789","title":"SAM3-UNet: Simplified Adaptation of Segment Anything Model 3","created":"2025-12-01","cited_by_count":4,"area":null},{"id":"2512.16908","title":"SceneDiff: A Benchmark and Method for Multiview Object Change Detection","created":"2025-12-18","cited_by_count":4,"area":null},{"id":"2512.24702","title":"Evolving, Not Training: Zero-Shot Reasoning Segmentation via Evolutionary Prompting","created":"2025-12-31","cited_by_count":4,"area":null},{"id":"2601.07447","title":"PanoSAMic: Panoramic Image Segmentation from SAM Feature Encoding and Dual View Fusion","created":"2026-01-12","cited_by_count":4,"area":null},{"id":"2601.13895","title":"OmniOVCD: Streamlining Open-Vocabulary Change Detection with SAM 3","created":"2026-01-20","cited_by_count":4,"area":null},{"id":"2602.06333","title":"Taming SAM3 in the Wild: A Concept Bank for Open-Vocabulary Segmentation","created":"2026-02-06","cited_by_count":4,"area":null},{"id":"2603.15847","title":"FEEL (Force-Enhanced Egocentric Learning): A Dataset for Physical Action Understanding","created":"2026-03-16","cited_by_count":4,"area":null},{"id":"2604.14944","title":"HRDexDB: A 4D Dexterous Grasping Dataset Across Human and Multiple Robot Embodiments","created":"2026-04-16","cited_by_count":4,"area":null},{"id":"2604.19609","title":"Volume Transformer: Revisiting Vanilla Transformers for 3D Scene Understanding","created":"2026-04-21","cited_by_count":4,"area":null},{"id":"2605.00663","title":"Affordance Agent Harness: Verification-Gated Skill Orchestration","created":"2026-05-01","cited_by_count":4,"area":null},{"id":"2605.20290","title":"PhysOmni: Physics-Grounded Multi-Object Scene Generation from a Single Image with Real-Time Interaction","created":"2026-05-19","cited_by_count":4,"area":null},{"id":"2607.21881","title":"Farmland Extent and Visible Boundary Mapping from 1 m NAIP Imagery Using Residual U-Net and Text-Prompted SAM 3 Refinement","created":"2026-07-24","cited_by_count":4,"area":null},{"id":"2512.15564","title":"On the Effectiveness of Textual Prompting with Lightweight Fine-Tuning for SAM3 Remote Sensing Segmentation","created":"2025-12-17","cited_by_count":3,"area":null},{"id":"2601.00537","title":"Boosting Segment Anything Model to Generalize Visually Non-Salient Scenarios","created":"2026-01-02","cited_by_count":3,"area":null},{"id":"2602.13195","title":"Conversational Image Segmentation: Grounding Abstract Concepts with Scalable Supervision","created":"2026-02-13","cited_by_count":3,"area":null},{"id":"2602.23543","title":"Synthetic Visual Genome 2: Extracting Large-scale Spatio-Temporal Scene Graphs from Videos","created":"2026-02-26","cited_by_count":3,"area":null},{"id":"2603.05377","title":"OpenFrontier: General Navigation with Visual-Language Grounded Frontiers","created":"2026-03-05","cited_by_count":3,"area":null},{"id":"2603.09740","title":"Let's Reward Step-by-Step: Step-Aware Contrastive Alignment for Vision-Language Navigation in Continuous Environments","created":"2026-03-10","cited_by_count":3,"area":null},{"id":"2603.11606","title":"Articulat3D: Reconstructing Articulated Digital Twins From Monocular Videos with Geometric and Motion Constraints","created":"2026-03-12","cited_by_count":3,"area":null},{"id":"2603.28757","title":"SonoWorld: From One Image to a 3D Audio-Visual Scene","created":"2026-03-30","cited_by_count":3,"area":null},{"id":"2604.05433","title":"Few-Shot Semantic Segmentation Meets SAM3","created":"2026-04-07","cited_by_count":3,"area":null},{"id":"2604.10789","title":"ReplicateAnyScene: Zero-Shot Video-to-3D Composition via Textual-Visual-Spatial Alignment","created":"2026-04-12","cited_by_count":3,"area":null},{"id":"2604.12929","title":"Grasp in Gaussians: Fast Monocular Reconstruction of Dynamic Hand-Object Interactions","created":"2026-04-14","cited_by_count":3,"area":null},{"id":"2605.07191","title":"Attention Transfer Is Not Universally Effective for Vision Transformers","created":"2026-05-08","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":"2606.06601","title":"Direct 3D-Aware Object Insertion via Decomposed Visual Proxies","created":"2026-06-04","cited_by_count":3,"area":null},{"id":"2606.14188","title":"Robustness without Wrinkles: Parallel Simulation and Robust MPC for Certified Deformable Manipulation","created":"2026-06-12","cited_by_count":3,"area":null},{"id":"2607.01015","title":"SuperFlex: Deformable Superquadrics for Point Cloud Decomposition","created":"2026-07-01","cited_by_count":3,"area":null},{"id":"2607.01166","title":"Structured 4D Latent Predictive Model for Robot Planning","created":"2026-07-01","cited_by_count":3,"area":null},{"id":"2607.20002","title":"Post-Training in Time Series Foundation Models: A Unifying Framework","created":"2026-07-22","cited_by_count":3,"area":null},{"id":"2607.22832","title":"MEMENTO: Memory-Guided Memetic Code-as-Policy Evolution","created":"2026-07-24","cited_by_count":3,"area":null},{"id":"2511.21926","title":"Comparing SAM 2 and SAM 3 for Zero-Shot Segmentation of 3D Medical Data","created":"2025-11-26","cited_by_count":2,"area":null},{"id":"2512.06032","title":"The SAM2-to-SAM3 Gap in the Segment Anything Model Family: Why Prompt-Based Expertise Fails in Concept-Driven Image Segmentation","created":"2025-12-04","cited_by_count":2,"area":null},{"id":"2601.13404","title":"Local-to-Global Logical Explanations for Deep Vision Models","created":"2026-01-19","cited_by_count":2,"area":null},{"id":"2602.03253","title":"LaVPR: Benchmarking Language and Vision for Place Recognition","created":"2026-02-03","cited_by_count":2,"area":null},{"id":"2602.05577","title":"LocateEdit-Bench: A Benchmark for Instruction-Based Editing Localization","created":"2026-02-05","cited_by_count":2,"area":null},{"id":"2602.08224","title":"Efficient-SAM2: Accelerating SAM2 with Object-Aware Visual Encoding and Memory Retrieval","created":"2026-02-09","cited_by_count":2,"area":null},{"id":"2603.02419","title":"DINOv3 Visual Representations for Blueberry Perception Toward Robotic Harvesting","created":"2026-03-02","cited_by_count":2,"area":null},{"id":"2603.06699","title":"Multi-label Instance-level Generalised Visual Grounding in Agriculture","created":"2026-03-05","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":"2603.14301","title":"4D Synchronized Fields: Motion-Language Gaussian Splatting for Temporal Scene Understanding","created":"2026-03-15","cited_by_count":2,"area":null},{"id":"2603.14382","title":"StAR: Segment Anything Reasoner","created":"2026-03-15","cited_by_count":2,"area":null},{"id":"2603.17845","title":"Revisiting foundation models for cell instance segmentation","created":"2026-03-18","cited_by_count":2,"area":null},{"id":"2603.22972","title":"WorldMesh: Generating Navigable Multi-Room 3D Scenes via Mesh-Conditioned Image Diffusion","created":"2026-03-24","cited_by_count":2,"area":null},{"id":"2603.27344","title":"TerraSeg: Self-Supervised Ground Segmentation for Any LiDAR","created":"2026-03-28","cited_by_count":2,"area":null},{"id":"2603.28182","title":"A Closer Look at Cross-Domain Few-Shot Object Detection: Fine-Tuning Matters and Parallel Decoder Helps","created":"2026-03-30","cited_by_count":2,"area":null},{"id":"2604.22390","title":"Region Matters: Efficient and Reliable Region-Aware Visual Place Recognition","created":"2026-04-24","cited_by_count":2,"area":null},{"id":"2605.02638","title":"ViewSAM: Learning View-aware Cross-modal Semantics for Weakly Supervised Cross-view Referring Multi-Object Tracking","created":"2026-05-04","cited_by_count":2,"area":null},{"id":"2605.04045","title":"Audio-Visual Intelligence in Large Foundation Models","created":"2026-05-05","cited_by_count":2,"area":null},{"id":"2605.11756","title":"Focusable Monocular Depth Estimation","created":"2026-05-12","cited_by_count":2,"area":null},{"id":"2605.14534","title":"PROVE: A Perceptual RemOVal cohErence Benchmark for Visual Media","created":"2026-05-14","cited_by_count":2,"area":null},{"id":"2605.17286","title":"HyperVision: A Channel-Adaptive Ground-Based Hyperspectral Vision Pre-trained Backbone","created":"2026-05-17","cited_by_count":2,"area":null},{"id":"2605.20110","title":"SetCon: Towards Open-Ended Referring Segmentation via Set-Level Concept Prediction","created":"2026-05-19","cited_by_count":2,"area":null},{"id":"2605.22272","title":"Imagine2Real: Towards Zero-shot Humanoid-Object Interaction via Video Generative Priors","created":"2026-05-21","cited_by_count":2,"area":null},{"id":"2605.22538","title":"Segment Anything with Motion, Geometry, and Semantic Adaptation for Complex Nonlinear Visual Object Tracking","created":"2026-05-21","cited_by_count":2,"area":null},{"id":"2605.26137","title":"AssetGen: Deployable 3D Asset Generation at Interactive Speed","created":"2026-05-22","cited_by_count":2,"area":null},{"id":"2605.26316","title":"E$^3$C: Video Generation with 3D Environmental Memory and Ego-Exo Human Pose Control","created":"2026-05-25","cited_by_count":2,"area":null},{"id":"2606.03168","title":"JAVEDIT: Joint Audio-Visual Instruction-Guided Video Editing with Agentic Data Curation","created":"2026-06-02","cited_by_count":2,"area":null},{"id":"2606.08057","title":"EgoAERO: Learning Dexterous Manipulation from a Single Egocentric Video without Object Assets","created":"2026-06-06","cited_by_count":2,"area":null},{"id":"2606.10614","title":"Dexterous Point Policy: Learning Point-based Dexterous Hand Policies from Human Demonstrations","created":"2026-06-09","cited_by_count":2,"area":null},{"id":"2606.21863","title":"Prompt-Calibrated SAM 3 for Open-Vocabulary Remote Sensing Semantic Segmentation","created":"2026-06-20","cited_by_count":2,"area":null}],"next_cursor":"100"}