Skip to content
AI Atlas
Research

Papers

Publications linked to models, labs and benchmarks. Authors, venues and abstracts come from arXiv and publisher pages; model links come from model cards citing the paper.

510 papers

Papers
TitleAuthorsOrganizationPublishedIntroduces Models (and artifacts) whose model card or documentation cites this paper — inbound described_by relations.DatasetsBenchmarksCode
Arbitrary Cipher Attacks Against Large Language Models Do Not Require Fine-TuningarXiv:2609.09553cs.CRThomas Rivasseau11 Sept 2026
High-probability guarantees for linear accessibility in feature superpositionarXiv:2609.09556stat.MLEnrico Vompa11 Sept 2026
The Vibe Shift in Software Engineering: Evaluating AI-Led Conversational Programming for Performance, Cognition, and Responsible AdoptionarXiv:2609.09560cs.SESales G. Aribe Jr., Louie Jay S. Labastida11 Sept 2026
Learning with Synthetic Data via SGD in High-Dimensional Linear RegressionarXiv:2609.09572stat.MLJichu li, Difan Zou11 Sept 2026
Myocardial Strain Drift Correction in Deep Learning Based Ultrasound TrackingarXiv:2609.09577eess.IVThierry Judge, Nicolas Duchateau, Andreas {\O}stvik +211 Sept 2026
Modality-Decoupled Federated Learning for Privacy-Preserving Embodied Intelligence in 6GarXiv:2609.09591eess.SPZhuodong Liu, Xiangyu Li, Chunhong Yuan +211 Sept 2026
Teacher Geometry Shapes Learnability in Teacher-Student NetworksarXiv:2609.09595cs.LGKai J. Sandbrink, Flavio Martinelli, Alexander van Meegen +211 Sept 2026
Watermarks Without Verification: AI Text Watermarking After the EU AI ActarXiv:2609.09604cs.CYAlexander Nemecek, Vipin Chaudhary, Erman Ayday11 Sept 2026
RouteBridge: Reliability-Routed Bidirectional Distillation Between Neural Radiance Fields and 3D Gaussian SplattingarXiv:2609.09606cs.CVYuanHang Wang, Xin Cao11 Sept 2026
Hyperbolic Geometry for Open-World Object Detection in Remote Sensing ImageryarXiv:2609.09626cs.CVWuzhou Li, Jiawei Zhou, Shenghang Wang +111 Sept 2026
Cascading Gradient Inversion via LT-Code Inspired Peeling in Federated LearningarXiv:2609.09659cs.LGSaeed Shariati, Mohsen Alambardar Meybodi11 Sept 2026
Introducing Consort: A Spec-First Agent Framework for Enforced, Test-Driven Development on Live Database BranchesarXiv:2609.09671cs.SEKevin Hartman11 Sept 2026
Which Medical Questions Deserve Rationales? Perturbation-Sensitive Selection for Robust QAarXiv:2609.09684cs.CLYuexin Wu, Dayou Yu, Vasile Rus11 Sept 2026
Looped GPT-BERT: Trading Parameters for Computation in Small Language ModelingarXiv:2609.09691cs.CLTingshuo Fan, Hongtao Mu, Tianyu Zhou +211 Sept 2026
CT-SAFR: Safe and Interpretable Chain-of-Thought Reasoning for Autonomous Robots: A Multi-Layered Verification Framework for Trustworthy AI-Driven Robotic Decision MakingarXiv:2609.09692cs.ROCagri Temel11 Sept 2026
When Auditors Fabricate: Batch-Size Degradation and Confident Hallucination in LLM Detection of Planted Document ContaminationarXiv:2609.09696cs.CLKaran Parekh, Sanjana Pendyala Ravinder, Sana Mhapsekar +111 Sept 2026
Kernel-Complexity Edge Sanitization for Training-Free Defense against Structural Graph AttacksarXiv:2609.09698cs.LGYaning Jia, Shenyang Deng, Yaoqing Yang +211 Sept 2026
Distilling Image Prototypes for Guided Test-Time AdaptationarXiv:2609.09737cs.CVLiwen Wang, Xingbo Dong, Iman Yi Liao +211 Sept 2026
HiRAD: A Flexible Large-Scale AGV Routing SystemarXiv:2609.09752cs.ROYunjie Huang, Ruizhong Wu, Mengxuan Zhang +211 Sept 2026
Fine-Tuning a KV Cache Concatenation-Aware Model or Recomputing KV Caches? Why Not Both?arXiv:2609.09768cs.LGFumihiko Tachibana, Daisuke Miyashita, Jun Deguchi11 Sept 2026
BRACE: Anchored Bellman-Residual Correction for Stale Critics in Asynchronous RLarXiv:2609.09783cs.LGGuanqun Zhao, Zijun Xie, Binbin Zheng +211 Sept 2026
Pairit: A Platform for Live Experiments on Human-AI CollaborationarXiv:2609.09789cs.HCHarang Ju, Sinan Aral11 Sept 2026
LogiScope-VQA: Benchmarking Vision-Language Models for Logistics Hazard Identification in Industrial ScenariosarXiv:2609.09790cs.CVHanjing Zhou, Mingze Yin, Ying Lian +211 Sept 2026
How Fragile Is Safety Alignment at Frontier Scale? A Single-Direction Attack on a 320B MoEarXiv:2609.09793cs.CRYi Shi, Tanyu Chen, Kai Shen11 Sept 2026
CS-Guard: Benchmarking LLM Guardrails for Code Generation SecurityarXiv:2609.09798cs.CRJinyang Li, Mingyu Guo, Hung X. Nguyen11 Sept 2026

Author lists and categories are copied from the paper's own metadata (arXiv, publisher). Linked models, datasets, benchmarks and code come from stated relations only; a dash means no source stated one.