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.

10 papers

Papers
TitleAuthorsOrganizationPublishedIntroduces Models (and artifacts) whose model card or documentation cites this paper — inbound described_by relations.DatasetsBenchmarksCode
When Does Text Inform? Benchmarking Information-Theoretic Metrics for Multimodal Time-Series ForecastingarXiv:2609.11282cs.AIEmma Andrews, Gianmarco Mengaldo12 Sept 2026
A machine-checked proof of the Dong-Yang classification of optimal (n,4) binary codes for BSCsarXiv:2609.10579math.HOShenghao Yang, Yanyan Dong12 Sept 2026
A Mathematical Theory of Pragmatic InformationarXiv:2609.10986cs.ITKai Niu, Ping Zhang12 Sept 2026
Risk-Averse Decision Making with Multi-Level Reliability GuaranteesarXiv:2609.11524stat.MLAmirmohammad Farzaneh, Osvaldo Simeone11 Sept 2026
Prediction--Loss Alignment for Sampler--Robust Flow Matching TrainingarXiv:2602.10420cs.LGJiadong Hong, Lei Liu, Xinyu Bian +211 Sept 2026
Statistically Valid Post-Training Hyperparameter Selection: From Tuning to GuaranteesarXiv:2606.25601stat.MLAmirmohammad Farzaneh, Osvaldo Simeone11 Sept 2026
Formalizing building-up constructions of self-dual codes through isotropic lines in LeanarXiv:2604.08485cs.ITJae-Hyun Baek, Jon-Lark Kim11 Sept 2026
Quantifying Logical Consistency in Transformers via Query-Key AlignmentarXiv:2502.17017cs.CLEduard Tulchinskii, Anastasia Voznyuk, Laida Kushnareva +211 Sept 2026
Reliable Near-Field Multi-User Positioning Informed by Two-Stage MUSICarXiv:2609.09409eess.SPJiaying Li, Haifeng Wen, Changsheng You +211 Sept 2026
Non-Stationarity Breaks Permutation Surrogates in Multi-Agent Reinforcement Learning: Diagnosis and RemediesarXiv:2604.23716cs.AINikolaos Al. Papadopoulos, Konstantinos E. Psannis11 Sept 2026

10 results

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.