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.

341 papers

Papers
TitleAuthorsOrganizationPublishedIntroduces Models (and artifacts) whose model card or documentation cites this paper — inbound described_by relations.DatasetsBenchmarksCode
Why Does Post-Training Quantization Work?arXiv:2609.11716cs.LGYuxiang Chen, Michael Beyer, Jun Zhu +111 Sept 2026
Predicting Privacy Leakage from Weight Spectral DensityarXiv:2609.11780cs.LGRichard J. Preen, Jim Smith11 Sept 2026
Dynamic language model representations for multi-objective reaction optimisationarXiv:2609.11790cs.LGJoshua W. Sin, David Ming Segura, Bojana Rankovi\'c +211 Sept 2026
AdamX: Cosine similarity meets gradient descentarXiv:2609.11867cs.LGFrancisco Caldas, Ruben Belo, Cl\'audia Soares11 Sept 2026
CoRA-NAS: Coarse Ranking and Anchor-Residual Refinement for Neural Architecture SearcharXiv:2609.11884cs.LGYifan Yang, Zhaoyan Wang, Zheng Gao +211 Sept 2026
CausalArena: Benchmarking Causal Discovery in the Foundation Model EraarXiv:2609.11897cs.LGZi-Rong Li, Si-Yang Liu, Tian-Zuo Wang +111 Sept 2026
TART: A Modular Tool for Technique-Aware Audio-to-Tablature Guitar TranscriptionarXiv:2609.11904cs.LGAkshaj Gupta, Hwi Joo Park, Andrea Guzman +211 Sept 2026
From Protocols to Evidence: Bounded Claims for AI in Service of the Common GoodarXiv:2609.11910cs.LGNitesh V. Chawla, Paulo Benanti11 Sept 2026
Data Scarcity and Model Sparsity: Mixtures-of-Experts Overfit More to Repeated DataarXiv:2609.11917cs.LGAtindra Jha, Margaret Li, Jure Leskovec +211 Sept 2026
MUC-FL: Block-Wise Marginal Utility Contribution for Communication-Efficient Federated LearningarXiv:2609.10545cs.DCAkshay Mhatre, Vikram Karthick, Deepti Gupta +111 Sept 2026
Optimizing AI Inference Across the Deployment StackarXiv:2609.10550cs.SETejinder Singh, John Pflueger, Jeebak Mitra +211 Sept 2026
EVTradeMatch: A Mobility-Aware Multi-Objective Matching Framework for EV--EV Energy TradingarXiv:2609.10551math.OCMd. Mahfujur Rahman, Alistair Barros, Raja Jurdak +111 Sept 2026
Supply Chain Analytics: A Data-Driven ApproacharXiv:2609.10563math.OCElioth Sanabria11 Sept 2026
A Station-Based Evaluation of Machine Learning-based Weather Forecasting Models in Northern NorwayarXiv:2609.10564physics.ao-phSiyan Chen, Lars Uebbing, Eirik Mikal Samuelsen +211 Sept 2026
An Empirical Measurement of Jailbreaking EvaluatorsarXiv:2609.10594cs.CRYujie Mu11 Sept 2026
Adaptive Diffusion Freezing: Privacy-preserving Diffusion Models Against Membership Inference AttacksarXiv:2609.10608cs.CRJialu Guo, Xiao Han, Junjie Wu11 Sept 2026
On the Relation between Code Quality and Machine Learning Performance: A Large-scale Empirical StudyarXiv:2609.10610cs.SEMarius Mignard (CRIStAL), Steven Costiou (CRIStAL), Anne Etien (CRIStAL +111 Sept 2026
Black-Box Membership Inference via Word-Level Probability EstimationarXiv:2609.10611cs.CRShengjie Niu, Yeheng Ge, Jian Huang11 Sept 2026
PEARL: A Task-Aware Framework for Evaluating Differentially Private Synthetic Educational DataarXiv:2609.10612cs.CRXianghui Meng, Yujing Zhang, Jionghao Lin11 Sept 2026
Understanding In-Context Multimodal Jailbreaks via Posterior ReweightingarXiv:2609.10613cs.CRXu Zhang, Dev Mistry, Xiang Xu +111 Sept 2026
SoK: Privacy Attacks on Machine Learning via Explainable AIarXiv:2609.10627cs.CRAbdullah Caglar Oksuz, Anisa Halimi, Erman Ayday11 Sept 2026
From Cycle Space to Cycle Manifold: Limits and Achievability of Blind False Data Injection AttacksarXiv:2609.10631cs.CRXin Li, Chenhan Xiao, Jonathan Cohen +211 Sept 2026
Numbat: Building and Verifying a Self-Contained Machine-Learning StackarXiv:2609.10632cs.SEThang Tran (CloudKites AI Lab, New South Wales, Australia) +211 Sept 2026
Sequence-Informed Geometric Evaluation of RNA 3D StructuresarXiv:2609.10644q-bio.BMAndrea Zerio, Yighua Yao, Alessandro Micheli +211 Sept 2026
HuRo: Robotizing Human Videos for Scalable VLA PretrainingarXiv:2609.10706cs.ROJinho Jeong, Se June Joo, Jaehyun Kang +211 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.