📰 OFR 科研日报 — 2026-02-26

🎬 Restoration & Enhancement (6)
  📄 RGB-Event HyperGraph Prompt for Kilometer Marker Recognition based on Pre-trained Foundation Models
     https://arxiv.org/abs/2602.22026
  📄 RobustVisRAG: Causality-Aware Vision-Based Retrieval-Augmented Generation under Visual Degradations
     https://arxiv.org/abs/2602.22013
  📄 PatchDenoiser: Parameter-efficient multi-scale patch learning and fusion denoiser for medical images
     https://arxiv.org/abs/2602.21987
  📄 Geometry-as-context: Modulating Explicit 3D in Scene-consistent Video Generation to Geometry Context
     https://arxiv.org/abs/2602.21929
  📄 Scan Clusters, Not Pixels: A Cluster-Centric Paradigm for Efficient Ultra-high-definition Image Restoration
     https://arxiv.org/abs/2602.21917

🎞️ Video & Temporal (19)
  🤗 JavisDiT++: Unified Modeling and Optimization for Joint Audio-Video Generation
     ⬆️2 https://huggingface.co/papers/2602.19163
  📄 RGB-Event HyperGraph Prompt for Kilometer Marker Recognition based on Pre-trained Foundation Models
     https://arxiv.org/abs/2602.22026
  📄 PatchDenoiser: Parameter-efficient multi-scale patch learning and fusion denoiser for medical images
     https://arxiv.org/abs/2602.21987
  📄 Dream-SLAM: Dreaming the Unseen for Active SLAM in Dynamic Environments
     https://arxiv.org/abs/2602.21967
  📄 Global-Aware Edge Prioritization for Pose Graph Initialization
     https://arxiv.org/abs/2602.21963

⚡ Efficient Architecture (13)
  🤗 World Guidance: World Modeling in Condition Space for Action Generation
     https://huggingface.co/papers/2602.22010
  📄 PatchDenoiser: Parameter-efficient multi-scale patch learning and fusion denoiser for medical images
     https://arxiv.org/abs/2602.21987
  📄 When LoRA Betrays: Backdooring Text-to-Image Models by Masquerading as Benign Adapters
     https://arxiv.org/abs/2602.21977
  📄 Dream-SLAM: Dreaming the Unseen for Active SLAM in Dynamic Environments
     https://arxiv.org/abs/2602.21967
  📄 Global-Aware Edge Prioritization for Pose Graph Initialization
     https://arxiv.org/abs/2602.21963

🔭 Vision Backbone & Attention (17)
  📄 RT-RMOT: A Dataset and Framework for RGB-Thermal Referring Multi-Object Tracking
     https://arxiv.org/abs/2602.22033
  📄 RobustVisRAG: Causality-Aware Vision-Based Retrieval-Augmented Generation under Visual Degradations
     https://arxiv.org/abs/2602.22013
  📄 PatchDenoiser: Parameter-efficient multi-scale patch learning and fusion denoiser for medical images
     https://arxiv.org/abs/2602.21987
  📄 Mobile-Ready Automated Triage of Diabetic Retinopathy Using Digital Fundus Images
     https://arxiv.org/abs/2602.21943
  📄 A Framework for Cross-Domain Generalization in Coronary Artery Calcium Scoring Across Gated and Non-Gated Computed Tomog
     https://arxiv.org/abs/2602.21935

🌊 Frequency & Wavelet (1)
  📄 TIRAuxCloud: A Thermal Infrared Dataset for Day and Night Cloud Detection
     https://arxiv.org/abs/2602.21905

🎨 Diffusion & Generative Prior (19)
  🤗 JavisDiT++: Unified Modeling and Optimization for Joint Audio-Video Generation
     ⬆️2 https://huggingface.co/papers/2602.19163
  🤗 World Guidance: World Modeling in Condition Space for Action Generation
     https://huggingface.co/papers/2602.22010
  📄 RobustVisRAG: Causality-Aware Vision-Based Retrieval-Augmented Generation under Visual Degradations
     https://arxiv.org/abs/2602.22013
  📄 PatchDenoiser: Parameter-efficient multi-scale patch learning and fusion denoiser for medical images
     https://arxiv.org/abs/2602.21987
  📄 When LoRA Betrays: Backdooring Text-to-Image Models by Masquerading as Benign Adapters
     https://arxiv.org/abs/2602.21977

📋 其他热门
  📄 PanoEnv: Exploring 3D Spatial Intelligence in Panoramic Environments with Reinforcement Learning
     https://arxiv.org/abs/2602.21992
  📄 Global-Local Dual Perception for MLLMs in High-Resolution Text-Rich Image Translation
     https://arxiv.org/abs/2602.21956
  📄 MindDriver: Introducing Progressive Multimodal Reasoning for Autonomous Driving
     https://arxiv.org/abs/2602.21952
