Skip to content
AI Atlas
Research

Papers

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

790 total

Reset
Papers
TitleAuthorsPublishedCategoriesOrganization / venueQuality
Convex Optimization with Nested Evolving Feasible Sets (CONES) under Time-Varying Loss FunctionsarXiv:2609.11207Rahul Vaze11 Sept 2026cs.LG—
REVA: Reusable Evidence View Aggregation for Context-Efficient RAG ServingarXiv:2609.11209Tuan Nguyen, Qiran Hu, Banruo Liu +211 Sept 2026cs.LG—
Legible Failures: Detecting and Repairing In-Context Binding ErrorsarXiv:2609.11216Manas Venkata Sai Ravulapalli, Samrath Singh Chadha, Abhinav M. Hari11 Sept 2026cs.LG—
Polyhedral Geometry of Time-to-First-Spike Neural NetworksarXiv:2609.11227Manjot Singh, Guido Mont\'ufar, Gitta Kutyniok11 Sept 2026cs.LG—
Solving Few-Shot Multiobjective Multitask Optimization via Iterative Sequential TransferarXiv:2609.11228Tingyang Wei, Haofeng Wu, Ananda Phan Iman +211 Sept 2026cs.LG—
MUtE: A Dual Framework for Concept Erasure and Counterfactual InterventionsarXiv:2609.11253Antoine Saillenfest11 Sept 2026cs.LG—
A Dynamic Fusion Large Language Model for Traffic Flow PredictionarXiv:2609.11314Xue Qiu, Jianli Xiao11 Sept 2026cs.LG—
Estimating Inconsistency Response Surfaces under Uncertainty in Cyber-Physical System DevelopmentarXiv:2609.11331Johannes M\"akelburg, Tim Schwabe, Maribel Acosta11 Sept 2026cs.LG—
Reification as a Transferable Vocabulary: Zero-Shot Link Prediction with Vanilla GNNsarXiv:2609.11347Camille Pradel11 Sept 2026cs.LG—
Local Robustness Quantification for Naive Bayes Classifiers and Generative Forests: a General ApproacharXiv:2609.11366Adri\'an Detavernier, Jasper De Bock11 Sept 2026cs.LG—
Prevalence Determines Precision:Silent Contamination in Detector-Defined DatasetsarXiv:2609.11449Jia Huang, Yankai Wan, Yangjun Ou11 Sept 2026cs.LG—
Combining Synthetic and Real Data for Low-Resource Historical OCR: A Manchu Case StudyarXiv:2609.11495Yan Hon Michael Chung, Hanlin Wang11 Sept 2026cs.LG—
DeFiFlowBench: Benchmarking and Improving Safe Executability in Natural-Language DeFi Workflow SynthesisarXiv:2609.11504Abhinav Rajeev Kumar, Harshit Arora, Varun Singh +111 Sept 2026cs.LG—
Generalized Score Matching for Parameter Estimation on Convex DomainsarXiv:2609.11521Nishanth Shetty, Saisuchith Mahajan, Chandra Sekhar Seelamantula11 Sept 2026cs.LG—
Particle GFlowNets: Rethinking Generative Marginalization ModelsarXiv:2609.11538Tiago da Silva, Diego Mesquita, Salem Lahlou11 Sept 2026cs.LG—
A Dataset and Model for Imputing Water Surface Elevation on a Large and Extremely Sparse Spatiotemporal GrapharXiv:2609.11580Ruben Cartuyvels, Karim Douch, Gabriele Bertoli +211 Sept 2026cs.LG—
LoaDiff: Conditional Generation of Electricity Consumption Time Series for Energy AnalyticsarXiv:2609.11639Mariia Baranova, Adrien Petralia, Etienne Le Naour +211 Sept 2026cs.LG—
RDDMPI: Residual Denoising Diffusion Model for Probabilistic Multivariate Time Series ImputationarXiv:2609.11648Ramiro Valdes Jara, David Chapman, Adam Meyers11 Sept 2026cs.LG—
Musec: MomentUm SpEctral Clipping for Stable Muon-type TrainingarXiv:2609.11655Zhuanghua Liu, Menglian Wang, Luo Luo11 Sept 2026cs.LG—
Learnware and AI Model Management SystemarXiv:2609.11656Zhi-Hua Zhou11 Sept 2026cs.LG—
Why Does Post-Training Quantization Work?arXiv:2609.11716Yuxiang Chen, Michael Beyer, Jun Zhu +111 Sept 2026cs.LG—
Predicting Privacy Leakage from Weight Spectral DensityarXiv:2609.11780Richard J. Preen, Jim Smith11 Sept 2026cs.LG—
Dynamic language model representations for multi-objective reaction optimisationarXiv:2609.11790Joshua W. Sin, David Ming Segura, Bojana Rankovi\'c +211 Sept 2026cs.LG—
Thinking with Looped FlowsarXiv:2609.11801Ayhan Suleymanzade, Chanhyuk Lee, Floor Eijkelboom +211 Sept 2026cs.LG—
Model-Aware Schedules Improve Generation via Fiberwise Optimal TransportarXiv:2609.11842Luyi Jia, Boyan Zhang, Yilun Liu +111 Sept 2026cs.LG—
AdamX: Cosine similarity meets gradient descentarXiv:2609.11867Francisco Caldas, Ruben Belo, Cl\'audia Soares11 Sept 2026cs.LG—
The Last AI Built by Humans: Toward Genuine Recursive Self-ImprovementarXiv:2609.11873Yi Duan, Ying Liu, Zirui Tang +211 Sept 2026cs.LG—
CoRA-NAS: Coarse Ranking and Anchor-Residual Refinement for Neural Architecture SearcharXiv:2609.11884Yifan Yang, Zhaoyan Wang, Zheng Gao +211 Sept 2026cs.LG—
CausalArena: Benchmarking Causal Discovery in the Foundation Model EraarXiv:2609.11897Zi-Rong Li, Si-Yang Liu, Tian-Zuo Wang +111 Sept 2026cs.LG—
TART: A Modular Tool for Technique-Aware Audio-to-Tablature Guitar TranscriptionarXiv:2609.11904Akshaj Gupta, Hwi Joo Park, Andrea Guzman +211 Sept 2026cs.LG—
From Protocols to Evidence: Bounded Claims for AI in Service of the Common GoodarXiv:2609.11910Nitesh V. Chawla, Paulo Benanti11 Sept 2026cs.LG—
Data Scarcity and Model Sparsity: Mixtures-of-Experts Overfit More to Repeated DataarXiv:2609.11917Atindra Jha, Margaret Li, Jure Leskovec +211 Sept 2026cs.LG—
General Quantification of Covariate and Concept ShiftsarXiv:2609.11918Hongbo Chen, Li Charlie Xia11 Sept 2026cs.LG—
MUC-FL: Block-Wise Marginal Utility Contribution for Communication-Efficient Federated LearningarXiv:2609.10545Akshay Mhatre, Vikram Karthick, Deepti Gupta +111 Sept 2026cs.DC—
Optimizing AI Inference Across the Deployment StackarXiv:2609.10550Tejinder Singh, John Pflueger, Jeebak Mitra +211 Sept 2026cs.SE—
EVTradeMatch: A Mobility-Aware Multi-Objective Matching Framework for EV--EV Energy TradingarXiv:2609.10551Md. Mahfujur Rahman, Alistair Barros, Raja Jurdak +111 Sept 2026math.OC—
Supply Chain Analytics: A Data-Driven ApproacharXiv:2609.10563Elioth Sanabria11 Sept 2026math.OC—
A Station-Based Evaluation of Machine Learning-based Weather Forecasting Models in Northern NorwayarXiv:2609.10564Siyan Chen, Lars Uebbing, Eirik Mikal Samuelsen +211 Sept 2026physics.ao-ph—
An Empirical Measurement of Jailbreaking EvaluatorsarXiv:2609.10594Yujie Mu11 Sept 2026cs.CR—
Adaptive Diffusion Freezing: Privacy-preserving Diffusion Models Against Membership Inference AttacksarXiv:2609.10608Jialu Guo, Xiao Han, Junjie Wu11 Sept 2026cs.CR—

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.