Skip to content
AI Atlas
Research

Papers

Publications linked to models, labs and benchmarks. Authors, venues and abstracts come from arXiv and publisher pages.

191 total

Reset
Papers
TitleAuthorsPublishedCategoriesOrganization / venueQuality
Reconstruction of a 3D wireframe from a single line drawing via generative depth estimationarXiv:2604.13549Elton Cao, Hod Lipson11 Sept 2026cs.CV—89
TextAlign: Preference Alignment for Text Rendering with Hierarchical RewardsarXiv:2605.19320Mingxuan Cui, Jingpu Yang, Fengxian Ji +211 Sept 2026cs.CV—89
Artic-O: End-to-End Articulated Object Reconstruction via Latent Geometry LearningarXiv:2606.21938Xuyang Wang, Zhenyu Li, Jian Ding +211 Sept 2026cs.CV—89
ABACUS: Adapting Unified Foundation Model for Bridging Image Count Understanding and GenerationarXiv:2606.23835Anindya Mondal, Sauradip Nag, Anjan Dutta11 Sept 2026cs.CV—89
Does YOLO26 Truly Offer Advantages Over Its Predecessors for Edge Deployment? A Benchmark Study in AquaculturearXiv:2607.09835Rakesh Ranjan, Gajanan S. Kothawade, Kata Sharrer +211 Sept 2026cs.CV—89
HeteroPROMPT: A Real-time and Privacy-Preserving Heterogeneous Collaborative Perception FrameworkarXiv:2607.26283Armin Maleki, Hayder Radha11 Sept 2026cs.CV—89
SparSTAR: Sparse Attention for SpaceTime AutoRegressive Video SynthesisarXiv:2608.10519Jongbeom Lee, Hyunwoo Yu, Jincheol Yang +211 Sept 2026cs.CV—89
StreamTTT: Reconciling Real-Time Perception and Long-Term Memory in Streaming VLMsarXiv:2608.13416Joya Chen, Zeyun Zhong, Mike Zheng Shou11 Sept 2026cs.CV—89
Routing Before Looking: Query-Adaptive Evidence Acquisition for Long-form Video UnderstandingarXiv:2608.20805Tianyue Wang, Xuying Wu, Yuxiang Ma +211 Sept 2026cs.CV—89
MRI-based Deep Radiomic Phenotyping of Neuromuscular Disorders: A Topology-driven CharacterizationarXiv:2608.24415Martyna \.Zur, {\L}ukasz Pi\'orecki, Marek Socha +211 Sept 2026cs.CV—89
Differentiable Jitter Correction using Deep Learning-based Image Quality Metric for Phase-Contrast Micro-CTarXiv:2608.27034Junan Chen, Yiting Jia, Joscha Maier +211 Sept 2026cs.CV—89
Streaming4D: Accelerate 4D World Models via Block-wise Video Generation and Incremental ReconstructionarXiv:2609.00610Xiaoyan Liu, Jiaxin Liu, Kangrui Li +111 Sept 2026cs.CV—89
Design and Implementation of a Kalman Filter-Infused Algorithm for Tilt EstimationarXiv:2609.00730Yuehan Ma, Hongji Dai11 Sept 2026cs.CV—89
Persistent Identity Preservation in Generative Image Models: A Benchmark and Evaluation SystemarXiv:2609.04151Mengwei Ren, Xuaner Zhang, Zhihao Xia11 Sept 2026cs.CV—89
FreeTransformSR: Efficient Lightweight Image Super-Resolution via Free Low-Rank Learnable TransformarXiv:2609.05912Hongji Li, Yunhui Li11 Sept 2026cs.CV—89
FujinSplat: Seeing Through Smoke with RAW-Domain Gaussian SplattingarXiv:2609.06017Gengjia Chang, Ziteng Cui, Shuhong Liu11 Sept 2026cs.CV—89
RAIDAL: Redundancy-Aware Information Density Active Learning for CTC-Based Continuous Sign Language RecognitionarXiv:2609.06843Rafael A. Diniz Augusto, Gabriel L. Oliveira, Erickson R. Nascimento11 Sept 2026cs.CV—89
CGSM: Concept-Guided Segmentation Model for Precise Pulmonary Lesion DelineationarXiv:2609.07004Changheng Lin, Wenjie Zhang, Yushan Lu +211 Sept 2026cs.CV—89
Ambient @ EgoLongQA 2026: Distilling Long-Video perception into a Sub-2B ModelarXiv:2609.07154Logesh Kumar Umapathi11 Sept 2026cs.CV—89
From Few-Shot Segmentation to Clinician-in-the-Loop Medical Image AnalysisarXiv:2609.10001Yazhou Zhu11 Sept 2026cs.CV—89
3rd Place Solution to Human Motion Challenges in Real-World and Clinical Settings (MoCha) @ECCV2026: Language-Aligned Motion Representations for Domain-Generalizable UPDRS-Gait Severity EstimationarXiv:2609.10187Soojie Kim, Muhammad Munsif, Minkyung Kim +111 Sept 2026cs.CV—89
SegKAN: High-Resolution Medical Image Segmentation with Long-Distance DependenciesarXiv:2412.19990Shengbo Tan, Rundong Xue, Shipeng Luo +211 Sept 2026eess.IV—89
PathoHR: Breast Cancer Survival Prediction on High-Resolution Pathological ImagesarXiv:2503.17970Yang Luo, Shiru Wang, Jun Liu +211 Sept 2026eess.IV—89
FastMap: Real-Time Semantic Map Completion via Bitwise Masked ModelingarXiv:2506.07350Yijie Deng, Shuaihang Yuan, Congcong Wen +211 Sept 2026cs.RO—89
Prompting with Sign Parameters for Low-resource Sign Language Instruction GenerationarXiv:2508.16076Md Tariquzzaman, Md Farhan Ishmam, Saiyma Sittul Muna +211 Sept 2026cs.HC—89
DCReg: Decoupled Characterization for Efficient Degenerate LiDAR RegistrationarXiv:2509.06285Xiangcheng Hu, Xieyuanli Chen, Mingkai Jia +211 Sept 2026cs.RO—89
DefVINS: Visual-Inertial Odometry for Deformable ScenesarXiv:2601.00702Samuel Cerezo, Javier Civera11 Sept 2026cs.RO—89
Measuring Browser Webcam Gaze Honestly: A Capture-Clock Methodology and Open Reference ImplementationarXiv:2608.11566Chi-Sheng Chen, Gabriel A. Brat11 Sept 2026cs.HC—89
Diagnosing and Dynamically Filtering Occupancy World Models for Active MappingarXiv:2609.06820Jiahui Zhang, Gongbo Liang, Yu Zhang11 Sept 2026cs.RO—89
TBR: Transport-Based Rendering with Deposition Strokes for Inverse GraphicsarXiv:2609.08722Tianqi Liu, Yushan Han, Hang Liu11 Sept 2026cs.GR—89
Data-Driven Risk Fields for Safer End-to-End Autonomous DrivingarXiv:2609.10377Yuanxin Tian, Zhiyuan Liu, Jinhao Li +211 Sept 2026cs.RO—89

Author lists and categories are copied from the paper's own metadata (arXiv, publisher). Each paper page shows the abstract, related models and every source snapshot.