- 1 UniCustom: Unified Visual Conditioning for Multi-Reference Image Generation ↗
- 2 ReLIC-SGG: Relation Lattice Completion for Open-Vocabulary Scene Graph Generation ↗
- 3 Distill, Diffuse, and Semanticize (DDS): Annotation-Free 3D Scene Understanding Based on Multi-Granularity Distillation and Graph-Diffusion-Based Segmentation ↗
- 4 STORM: Segment, Track, and Object Re-Localization from a Single Image ↗
- 5 GraphThinker: Reinforcing Temporally Grounded Video Reasoning with Event Graph Thinking ↗
- 6 LoREnc: Low-Rank Encryption for Securing Foundation Models and LoRA Adapters ↗
- 7 Compact 3D Gaussian Splatting For Dense Visual SLAM ↗
- 8 M3Net: A Macro-to-Meso-to-Micro Clinical-inspired Hierarchical 3D Network for Pulmonary Nodule Classification ↗
- 9 VideoSEAL: Mitigating Evidence Misalignment in Agentic Long Video Understanding by Decoupling Answer Authority ↗
- 10 M2Retinexformer: Multi-Modal Retinexformer for Low-Light Image Enhancement ↗
- 11 Pyramid Self-contrastive Learning Framework for Test-time Ultrasound Image Denoising ↗
- 12 SSDA: Bridging Spectral and Structural Gaps via Dual Adaptation for Vision-Based Time Series Forecasting ↗
- 13 What Happens Before Decoding? Prefill Determines GUI Grounding in VLMs ↗
- 14 CROP: Expert-Aligned Image Cropping via Compositional Reasoning and Optimizing Preference ↗
- 15 GUIGuard-Bench: Toward a General Evaluation for Privacy-Preserving GUI Agents ↗
- 16 Improving Diffusion Posterior Samplers with Lagged Temporal Corrections for Image Restoration ↗
- 17 Gradient-Free Noise Optimization for Reward Alignment in Generative Models ↗
- 18 DistractMIA: Black-Box Membership Inference on Vision-Language Models via Semantic Distraction ↗
- 19 Robust and Explainable Bicuspid Aortic Valve Diagnosis Using Stacked Ensembles on Echocardiography ↗
- 20 3D Primitives are a Spatial Language for VLMs ↗
- 21 Reasoning to Edit: Hypothetical Instruction-Based Image Editing with Visual Reasoning ↗
- 22 TrackCraft3R: Repurposing Video Diffusion Transformers for Dense 3D Tracking ↗
- 23 SymbolSight: Minimizing Inter-Symbol Interference for Reading with Prosthetic Vision ↗
- 24 A Data Efficiency Study of Synthetic Fog for Object Detection Using the Clear2Fog Pipeline ↗
- 25 DeCo-DETR: Decoupled Cognition DETR for efficient Open-Vocabulary Object Detection ↗
- 26 MambaPanoptic: A Vision Mamba-based Structured State Space Framework for Panoptic Segmentation ↗
- 27 Does it Really Count? Assessing Semantic Grounding in Text-Guided Class-Agnostic Counting ↗
- 28 DIVER:Diving Deeper into Distilled Data via Expressive Semantic Recovery ↗
- 29 CoWorld-VLA: Thinking in a Multi-Expert World Model for Autonomous Driving ↗
- 30 CRAFT: Clinical Reward-Aligned Finetuning for Medical Image Synthesis ↗
- 31 Breaking Down and Building Up: Mixture of Skill-Based Vision-and-Language Navigation Agents ↗
- 32 No One Knows the State of the Art in Geospatial Foundation Models ↗
- 33 Data Agent: Learning to Select Data via End-to-End Dynamic Optimization ↗
- 34 Visual Aesthetic Benchmark: Can Frontier Models Judge Beauty? ↗
- 35 Towards Long-horizon Embodied Agents with Tool-Aligned Vision-Language-Action Models ↗
- 36 MMCL-Bench: Multimodal Context Learning from Visual Rules, Procedures, and Evidence ↗
- 37 Taming the Long Tail: Rebalancing Adversarial Training via Adaptive Perturbation ↗
- 38 Inline Critic Steers Image Editing ↗
- 39 Realtime-VLA FLASH: Speculative Inference Framework for Diffusion-based VLAs ↗
- 40 Is Video Anomaly Detection Misframed? Evidence from LLM-Based and Multi-Scene Models ↗
- 41 LENS: Multi-level Evaluation of Multimodal Reasoning with Large Language Models ↗
- 42 Just Ask for a Table: A Thirty-Token User Prompt Defeats Sponsored Recommendations in Twelve LLMs ↗
- 43 UNIV: Unified Foundation Model for Infrared and Visible Modalities ↗
- 44 WildPose: A Unified Framework for Robust Pose Estimation in the Wild ↗
- 45 When Diffusion Breaks Constraints: Sequential Autoregressive Generation with RL and MCTS ↗
- 46 FRAME: Forensic Routing and Adaptive Multi-path Evidence Fusion for Image Manipulation Detection ↗
- 47 Aligning Forest and Trees in Images & Long Captions for Visually Grounded Understanding ↗
- 48 AssemblyBench: Physics-Aware Assembly of Complex Industrial Objects ↗
- 49 Kiwi-Edit: Versatile Video Editing via Instruction and Reference Guidance ↗
- 50 PRISM: Perinuclear Ring-based Image Segmentation Method for Acute Lymphoblastic Leukemia Classification ↗
- 51 NTIRE 2026 The Second Challenge on Day and Night Raindrop Removal for Dual-Focused Images: Methods and Results ↗
- 52 Prediction of Rectal Cancer Regrowth from Longitudinal Endoscopy ↗
- 53 COHERENCE: Benchmarking Fine-Grained Image-Text Alignment in Interleaved Multimodal Contexts ↗
- 54 Adaptive Conformal Prediction for Reliable and Explainable Medical Image Classification ↗
- 55 PicoEyes: Unified Gaze Estimation Framework for Mixed Reality with a Large-Scale Multi-View Dataset ↗
- 56 GuardMarkGS: Unified Ownership Tracing and Edit Deterrence for 3D Gaussian Splatting ↗
- 57 Evidence-based Decision Modeling for Synthetic Face Detection with Uncertainty-driven Active Learning ↗
- 58 Anatomy-Slot: Unsupervised Anatomical Factorization for Homologous Bilateral Reasoning in Retinal Diagnosis ↗
- 59 A Mimetic Detector for Adversarial Image Perturbations ↗
- 60 AuraMask: An Extensible Pipeline for Developing Aesthetic Anti-Facial Recognition Image Filters ↗
- 61 VIP: Visual-guided Prompt Evolution for Efficient Dense Vision-Language Inference ↗
- 62 CRePE: Curved Ray Expectation Positional Encoding for Unified-Camera-Controlled Video Generation ↗
- 63 Energy Scaling Laws for Diffusion Models: Quantifying Compute in Image Generation ↗
- 64 DirectTryOn: One-Step Virtual Try-On via Straightened Conditional Transport ↗
- 65 Test-Time Training with KV Binding Is Secretly Linear Attention ↗
- 66 Debunking Grad-ECLIP: A Comprehensive Study on Its Incorrectness and Fundamental Principles for Model Interpretation ↗
- 67 (Sparse) Attention to the Details: Preserving Spectral Fidelity in ML-based Weather Forecasting Models ↗
- 68 Seg-Agent: Test-Time Multimodal Reasoning for Training-Free Language-Guided Segmentation ↗
- 69 ThermalTap: Passive Application Fingerprinting in VR Headsets via Thermal Side Channels ↗
- 70 AdaFocus: Adaptive Relevance-Diversity Sampling with Zero-Cache Look-back for Efficient Long Video Understanding ↗
- 71 On Hallucinations in Inverse Problems: Fundamental Limits and Provable Assessment Methods ↗
- 72 GTA: Advancing Image-to-3D World Generation via Geometry Then Appearance Video Diffusion ↗
- 73 What Limits Vision-and-Language Navigation ? ↗
- 74 Reducing Bias and Variance: Generative Semantic Guidance and Bi-Layer Ensemble for Image Clustering ↗
- 75 DeepFilters: Scattering-Aware Pupil Engineering with Learned Digital Filter Reconstruction for Extended Depth of Field Microscopy ↗
- 76 Asymmetric Flow Models ↗
- 77 Min Generalized Sliced Gromov Wasserstein: A Scalable Path to Gromov Wasserstein ↗
- 78 ImageAttributionBench: How Far Are We from Generalizable Attribution? ↗
- 79 History Anchors: How Prior Behavior Steers LLM Decisions Toward Unsafe Actions ↗
- 80 Amortized Guidance for Image Inpainting with Pretrained Diffusion Models ↗
- 81 PVLM: Parsing-Aware Vision Language Model with Dynamic Contrastive Learning for Zero-Shot Deepfake Attribution ↗
- 82 OCH3R: Object-Centric Holistic 3D Reconstruction ↗
- 83 NFR: Neural Feature-Guided Non-Rigid Shape Registration ↗
- 84 PRISM: Prior Rectification and Uncertainty-Aware Structure Modeling for Diffusion-Based Text Image Super-Resolution ↗
- 85 Scalable Object Detection in the Car Interior With Vision Foundation Models ↗
- 86 ViDR: Grounding Multimodal Deep Research Reports in Source Visual Evidence ↗
- 87 Unmasking Puppeteers: Leveraging Biometric Leakage to Expose Impersonation in AI-Based Videoconferencing ↗
- 88 CoGE: Sim-to-Real Online Geometric Estimation for Monocular Colonoscopy ↗
- 89 The Joint Gromov Wasserstein Objective for Multiple Object Matching ↗
- 90 EgoForce: Robust Online Egocentric Motion Reconstruction via Diffusion Forcing ↗
- 91 Make-It-Poseable: Feed-forward Latent Posing Model for 3D Characters ↗
- 92 Revealing the Gap in Human and VLM Scene Perception through Counterfactual Semantic Saliency ↗
- 93 Inference-Time Dynamic Modality Selection for Incomplete Multimodal Classification ↗
- 94 Uncertainty-aware Spatial-Frequency Registration and Fusion for Infrared and Visible Images ↗
- 95 Perception with Guarantees: Certified Pose Estimation via Reachability Analysis ↗
- 96 BrainAnytime: Anatomy-Aware Cross-Modal Pretraining for Brain Image Analysis with Arbitrary Modality Availability ↗
- 97 Exploring Multimodal LMMs for Online Episodic Memory Question Answering on the Edge ↗
- 98 Edit-Compass & EditReward-Compass: A Unified Benchmark for Image Editing and Reward Modeling ↗
- 99 MedOpenClaw and MedFlowBench: Auditing Medical Agents in Full-Study Workflows ↗
- 100 HarmoGS: Robust 3D Gaussian Splatting in the Wild via Conflict-Aware Gradient Harmonization ↗