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
OmniKVQuant: KV Cache Quantization for Omni-LLMsarXiv:2609.11582Suho Yoo, Hyunjong Ok, Jongmin Choi +211 Sept 2026cs.CV—89
MMGait: Benchmarking and Unifying Gait Recognition across Heterogeneous ModalitiesarXiv:2609.11601Saihui Hou, Chenye Wang, Qingyuan Cai +211 Sept 2026cs.CV—89
LangStreet: Persistent Language Fields for Anchor-Decoded Street GaussiansarXiv:2609.11616Runyi Yang, Deheng Zhang, Xiaoye Wang +211 Sept 2026cs.CV—89
Self-Supervised Cardiac Phase Detection via Single-Parameter Latent OrbitsarXiv:2609.11650John Bonnici, Matthew Baugh, Aleksandra Kulbaka +211 Sept 2026cs.CV—89
Single-Stream Multi-Feature Fusion with Temporal Robustness for Gait Emotion RecognitionarXiv:2609.11680Shirong Lyu, Silu Quan, Yixuan Ding +111 Sept 2026cs.CV—89
Spectral Adapters for Segment Anything Model-based Segmentation of Colorectal Liver Metastases in Computed TomographyarXiv:2609.11703Ramtin Mojtahedi, Mohammad Hamghalam, Jacob J. Peoples +211 Sept 2026cs.CV—89
Language-Augmented Semantic Priors for B-Spline Surface FittingarXiv:2609.11708Yunzhong Lou, Yusheng Luo, Jiahao Li +211 Sept 2026cs.CV—89
MC-DeTra: Motion-Consistent Joint Object Detection and Socially-Aware Trajectory Forecasting in Bird's-Eye-View ImagesarXiv:2609.11717Vladislav Diuzhev, Dmitry Yudin11 Sept 2026cs.CV—89
Revisiting Avatar-As-Image: High-Fidelity Registration is All You NeedarXiv:2609.11722Margaret Kostyrko, Yuxuan Xue, Garvita Tiwari +111 Sept 2026cs.CV—89
Guided Super-Resolution of Digital Elevation Models with Diffusion-Based Image GeneratorsarXiv:2609.11886Armand Mihai Nicolicioiu, Dominik Narnhofer, Nando Metzger +211 Sept 2026cs.CV—89
Caption-once, Frames-on-Demand: Visual-Need Routing for Budget-Aware Agentic Long Video UnderstandingarXiv:2609.11899Weitong Cai, Hang Zhang, Yukai Huang +211 Sept 2026cs.CV—89
SenseNova-U1.5: Towards Native Unified Visual IntelligencearXiv:2609.11929Haiwen Diao, Jiahao Wang, Chenjing Ding +211 Sept 2026cs.CV—74
Seamless Whole Slide Label-Free Virtual StainingarXiv:2609.10914Dou Hoon Kwark, Kianoush Falahkheirkhah, Ji-hun Oh +211 Sept 2026eess.IV—89
IMLE-VLA: Fast Single-Step Action Generation for Vision-Language-Action PoliciesarXiv:2609.10915Kian Hosseinkhani (Simon Fraser University), Qinhe Peng (University of Pennsylvania), George Shramko (Simon Fraser University) +211 Sept 2026cs.RO—89
Exponential Pixelating Integral transform with dual fractal features for enhanced chest X-ray abnormality detectionarXiv:2609.10988Naveenraj Kamalakannan, Sri Ram Macharla, M Kanimozhi +111 Sept 2026eess.IV—89
AI-Powered Flare Combustion Efficiency EstimationarXiv:2609.11262Afeefa Azam, Iyyakutti Iyappan Ganapathi, Fares Ossama Abdelhafez +211 Sept 2026cs.AI—89
SegCol Challenge: Semantic Segmentation for Tools and Fold Edges in Colonoscopy dataarXiv:2412.16078Xinwei Ju, Rema Daher, Razvan Caramalau +211 Sept 2026cs.CV—89
SSS: Semi-Supervised SAM-2 with Efficient Prompting for Medical Imaging SegmentationarXiv:2506.08949Hongjie Zhu, Xiwei Liu, Rundong Xue +211 Sept 2026cs.CV—89
Dream4D: Lifting Camera-Controlled I2V towards Spatiotemporally Consistent 4D GenerationarXiv:2508.07769Xiaoyan Liu, Kangrui Li, Jiaxin Liu +211 Sept 2026cs.CV—89
Adaptive Dual-Constrained Line Aggregation for Cross-Paradigm Line Segment DetectionarXiv:2508.19742Chenguang Liu, Chisheng Wang, Huilin Chen +211 Sept 2026cs.CV—89
Confidence-Calibrating Regularization for Robust Brain MRI Segmentation Under Domain ShiftarXiv:2509.23176Behraj Khan, Tahir Qasim Syed, Syed Ahmad Chan Bukhari11 Sept 2026cs.CV—89
MedGEN-Bench: A Contextually Entangled Benchmark for Open-ended Multimodal Medical GenerationarXiv:2511.13135Junjie Yang, Yuhao Yan, Gang Wu +211 Sept 2026cs.CV—89
DirectSwap: Paired, Mask-Free Video Head Swapping with Full-Reference EvaluationarXiv:2512.09417Yanan Wang, Shengcai Liao, Panwen Hu +211 Sept 2026cs.CV—89
Gaussian Belief Propagation Network for Depth CompletionarXiv:2601.21291Jie Tang, Pingping Xie, Jian Li +111 Sept 2026cs.CV—89
V-Retrver: Evidence-Driven Agentic Reasoning for Universal Multimodal RetrievalarXiv:2602.06034Dongyang Chen, Chaoyang Wang, Dezhao Su +211 Sept 2026cs.CV—89
InstantHDR: Single-forward Gaussian Splatting Initialization for HDR 3D ReconstructionarXiv:2603.11298Dingqiang Ye, Jiacong Xu, Jianglu Ping +211 Sept 2026cs.CV—89
CLIP-RD: Relational Distillation for Efficient CLIP Knowledge DistillationarXiv:2603.25383Jeannie Chung, Hanna Jang, Ingyeong Yang +211 Sept 2026cs.CV—89
Leveraging Avatar Fingerprinting: A Multi-Generator Photorealistic Talking-Head Public Database and BenchmarkarXiv:2603.26934Laura Pedrouzo-Rodriguez, Luis F. Gomez, Ruben Tolosana +211 Sept 2026cs.CV—89
Automated multi-class wound assessment using dedicated instance segmentation models for boundary detection and classificationarXiv:2603.27325Mehedi Hasan Tusar, Fateme Fayyazbakhsh, Igor Melnychuk +111 Sept 2026cs.CV—89
Towards Automated Solar Panel Integrity: Hybrid Deep Feature Extraction for Advanced Surface Defect IdentificationarXiv:2604.10969Muhammad Junaid Asif, Muhammad Saad Rafaqat, Usman Nazakat +211 Sept 2026cs.CV—89
Task Alignment: A Simple Proxy for Practical Model Merging Across Diverse Vision TasksarXiv:2604.12935Pau de Jorge, C\'esar Roberto de Souza, Bj\"orn Michele +211 Sept 2026cs.CV—89
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
ScaleResfusion: Residual Rectified Flow based on Residual Vector FieldarXiv:2607.25275Zhenning Shi, Chen Xu, Junhao Zhang +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
SciFigQual-Bench: A Benchmark for Scientific Figure Quality Assessment with Full-Manuscript ContextarXiv:2607.27084Zihan Deng, Chuanzhi Xu, Huiqi Liang +211 Sept 2026cs.CV—89
SPECTRA: Band-Routed Embedding and Stage-Wise LoRA for Cross-Sensor Fine-Tuning of Geospatial Foundation ModelsarXiv:2608.01751Xingyan Li, Jordan A. Caraballo-Vega, Jie Gong +211 Sept 2026cs.CV—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.