Skip to content
AI Atlas
Research

Papers

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

378 total

Reset
Papers
TitleAuthorsPublishedCategoriesOrganization / venueQuality
The Truth Was Never Gone: Perfect Aliasing in Compliant-Context Truth ProbesarXiv:2609.10739Dylan Jayabahu11 Sept 2026cs.LG—89
Adaptive Margin Ordinal Loss: Penalizing Center-Class Hedging in Ordinal ClassificationarXiv:2609.10752Manisha Kandel11 Sept 2026cs.LG—89
Counterfactual Marginalisation: Framework for Evaluating Robustness to Nuisance VariablesarXiv:2609.10778Yasin Ibrahim, Hermione Warr, Robin J. Evans +111 Sept 2026cs.LG—89
Story Imprinting: AI Assistants Absorb Traits from Human Characters They ResemblearXiv:2609.10883Jorio Cocola, Lev McKinney, Harry Mayne +211 Sept 2026cs.LG—89
AUC Maximization from Biased Positive-unlabeled Data with ConfidencearXiv:2609.10928Atsutoshi Kumagai, Tomoharu Iwata, Hiroshi Takahashi +211 Sept 2026cs.LG—89
EGGROLL, Unrolled: Understanding and Improving Low-Rank Evolution Strategies at ScalearXiv:2609.10980Ege C. Kaya, Abolfazl Hashemi11 Sept 2026cs.LG—89
Importance Weighting for Unlabeled-unlabeled Learning under Distribution ShiftarXiv:2609.10994Atsutoshi Kumagai, Tomoharu Iwata, Hiroshi Takahashi +211 Sept 2026cs.LG—89
Topological Necessities: Mechanism-Invariant Strategic Subgoals for Cross-Embodiment Goal-Conditioned ControlarXiv:2609.11014Hao Shi, Xi Li11 Sept 2026cs.LG—89
T1: Terminal Agent Reinforcement Learning for Long-Horizon TasksarXiv:2609.11042Junyao Yang, Yucheng Shi, Zhongzhi Li +211 Sept 2026cs.LG—89
Solving Few-Shot Multiobjective Multitask Optimization via Iterative Sequential TransferarXiv:2609.11228Tingyang Wei, Haofeng Wu, Ananda Phan Iman +211 Sept 2026cs.LG—89
Reification as a Transferable Vocabulary: Zero-Shot Link Prediction with Vanilla GNNsarXiv:2609.11347Camille Pradel11 Sept 2026cs.LG—89
Prevalence Determines Precision:Silent Contamination in Detector-Defined DatasetsarXiv:2609.11449Jia Huang, Yankai Wan, Yangjun Ou11 Sept 2026cs.LG—89
LoaDiff: Conditional Generation of Electricity Consumption Time Series for Energy AnalyticsarXiv:2609.11639Mariia Baranova, Adrien Petralia, Etienne Le Naour +211 Sept 2026cs.LG—89
Thinking with Looped FlowsarXiv:2609.11801Ayhan Suleymanzade, Chanhyuk Lee, Floor Eijkelboom +211 Sept 2026cs.LG—89
Model-Aware Schedules Improve Generation via Fiberwise Optimal TransportarXiv:2609.11842Luyi Jia, Boyan Zhang, Yilun Liu +111 Sept 2026cs.LG—89
The Last AI Built by Humans: Toward Genuine Recursive Self-ImprovementarXiv:2609.11873Yi Duan, Ying Liu, Zirui Tang +211 Sept 2026cs.LG—89
General Quantification of Covariate and Concept ShiftsarXiv:2609.11918Hongbo Chen, Li Charlie Xia11 Sept 2026cs.LG—89
A Multi-Stage Rule-Chaining Framework for Compositional and Interpretable Cognitive ReasoningarXiv:2609.10654Deblina Kar11 Sept 2026cs.AI—89
Understanding LoRA Rank Trade-offs in Diffusion Model Fine-TuningarXiv:2609.10656Iman Khazrak, Narges Nejad, Mostafa M. Rezaee +111 Sept 2026cs.AI—89
Quantifying the Memorization-to-Generalization Transition: Scaling Laws and Phase Structure in GrokkingarXiv:2609.10657Anish Kataria11 Sept 2026cs.AI—89
CARTS: Contextual Autoregressive Rank Transcoding Steganography for Full-Capacity Keyed Text EncodingarXiv:2609.10744Wissam Ghantous, Alexander V. Mantzaris11 Sept 2026cs.CR—89
Temporal and Multimodal Deep Learning for Cyberattack Detection in LEO Satellite SystemsarXiv:2609.10746Kyle Stein, Guillermo Francia III, Eman El-Sheikh +111 Sept 2026cs.CR—89
When Synthetic Data Hurts: On Catastrophic Forgetting in Skill Retrieval for LLM AgentsarXiv:2609.10750Syed Shariyar Murtaza, Yifan Nie, Utkarsh Soni +211 Sept 2026cs.IR—89
Multilingual in Name Only? Cultural and Linguistic Weaknesses of LLMs in UrduarXiv:2609.10758Farah Adeeba, Abdul Rafae Khan, Rajesh Bhatt +111 Sept 2026cs.CL—89
Studying Without a Syllabus: Task-Agnostic Environment PreprocessingarXiv:2609.10824Vinay Samuel, Varun Ursekar, Vijay S. Kalmath +211 Sept 2026cs.AI—89
Are We Really Doing Few-Shot Learning? A Critical Examination of Pre-Training AssumptionsarXiv:2609.10851Alejandro Galan-Cuenca, Marcelo Saval-Calvo, Antonio Javier Gallego11 Sept 2026cs.CV—89
DriftNet: A Dual-Head Trajectory Transformer for Detecting and Localizing Prompt Injection in LLM AgentsarXiv:2609.10892Asif Pinjari, Mithun Paul Saint-Germain11 Sept 2026cs.CR—89
Robust Multimodal Sentiment Analysis with Incomplete Modalities via Semantic-aware Completeness based ReconstructionarXiv:2609.10950Han-Jun Choi, Byunggill Joe, Saim Shin +111 Sept 2026cs.CL—89
New Evidence, Same Choice: Testing Physical Experiment Selection in Vision Language ModelsarXiv:2609.11022Sourajit Saha, Shubhashis Roy Dipta, Nobin Sarwar +211 Sept 2026cs.CV—89
The Oligarch Barely Steers Model Collapse in Multi-Model EcosystemsarXiv:2609.11146Yangze Liu, Zhongyi Han11 Sept 2026cs.AI—89
A Fragility Spectrum for Recursive Language-Model TrainingarXiv:2609.11149Yangze Liu, Zhongyi Han11 Sept 2026cs.CL—89
CryptoL: Towards Scale Dominance and Physics Constraints Mitigation in Financial Multivariate Time Series ForecastingarXiv:2609.11206Yalda Taheri, Mohammad Hassan Heydari, Armon Rasooli +211 Sept 2026cs.AI—89
Generative Replay Mitigates Sample Starvation in Quantum Architecture SearcharXiv:2609.11248Akash Kundu, Amit Kumar Jaiswal, Sebastian Feld +111 Sept 2026quant-ph—89
Improving Faint Object Detection for Space Situational Awareness with Variational AutoencodersarXiv:2609.11269Angela Cratere, Luca Ghilardi, Vishnu Reddy +211 Sept 2026cs.CV—89
Predicting Train Delays in Finland Using Machine Learning and Weather DataarXiv:2609.11277Vinicius Pozzobon Borin, Jean Michel de Souza Sant'Ana, Nurul Huda Mahmood11 Sept 2026cs.AI—89
Bio-inspired Learning and Decision-Making with Probabilistic In-Memory Computing Hardware: Part 1arXiv:2609.11281Thomas Dalgaty, Eiji Kawasaki, Miguel de Prado +211 Sept 2026cs.AI—89
Your Model Already Knows Don't Teach It, Learn to Ask It: Soft Prompting for Few-Shot Adaptation of Vision-Language ModelsarXiv:2609.11310Gautam Rajendrakumar Gare, Siyi Li, Hewei Wang +211 Sept 2026cs.CV—89
E-CONAN (Entailment, CONtradition And Neutral) Benchmarks: Arabic Textual Entailment and Natural Inference DatasetsarXiv:2609.11334Khloud AL Jallad, Nada Ghneim, Ghaida Rebdawi11 Sept 2026cs.CL—89
VikingRAG: Accurate and Token-efficient Retrieval-augmented Generation over Structured DocumentsarXiv:2609.11390Peiyuan Gao, Gaoyuan Zhang, Haojie Qin +211 Sept 2026cs.IR—89
Published Unlearning Numbers Move Per Checkpoint, and Not Because the Removed Data Survives: An Audit of 263 Released Batch-Normalized CheckpointsarXiv:2609.11490Junlong Shen Xingyu Li11 Sept 2026cs.AI—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.