Skip to content
AI Atlas
Research

Papers

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

341 total

Reset
Papers
TitleAuthorsPublishedCategoriesOrganization / venueQuality
Test time training enhances in-context learning of nonlinear functionsarXiv:2509.25741Kento Kuwataka, Taiji Suzuki11 Sept 2026stat.ML—89
Configuration-Dependent Lower Bounds for Approximation by Shallow ReLU$^k$ Networks on the SpherearXiv:2510.04060Tong Mao, Jinchao Xu11 Sept 2026math.NA—89
PitchFlower: A flow-based neural audio codec with pitch controllabilityarXiv:2510.25566Diego Torres, Axel Roebel, Nicolas Obin11 Sept 2026eess.AS—89
Addressing A Posteriori Performance Degradation in Neural Network Subgrid Stress ModelsarXiv:2511.17475Andy Wu, Sanjiva K. Lele11 Sept 2026physics.flu-dyn—89
Statistical analysis of Inverse Entropy-regularized Reinforcement LearningarXiv:2512.06956Denis Belomestny, Alexey Naumov, Artemy Rubtsov +111 Sept 2026stat.ML—89
Narrative Consolidation: Formulating a New Task for Unifying Multi-Perspective AccountsarXiv:2512.18041Roger A. Finger, Eduardo G. Cortes, Sandro J. Rigo +111 Sept 2026cs.CL—89
Building Supervision into Hebbian Plasticity through Spike AgreementarXiv:2601.08526Gouri Lakshmi S, Athira Chandrasekharan, Harshit Kumar +211 Sept 2026cs.NE—89
Bayesian quantum sensing using graybox machine learningarXiv:2601.17465Akram Youssry, Stefan Todd, Patrick Murton +211 Sept 2026quant-ph—89
Single Microphone Own Voice Detection based on Simulated Transfer Functions for Hearing AidsarXiv:2603.02724Mathuranathan Mayuravaani, W. Bastiaan Kleijn, Andrew Lensen +111 Sept 2026cs.SD—89
Bilateral Trade Under Heavy-Tailed Valuations: Minimax Regret without a Variance BoundarXiv:2603.06851Hangyi Zhao11 Sept 2026stat.ML—89
mmFHE: mmWave Sensing with End-to-End Fully Homomorphic EncryptionarXiv:2603.22437Tanvir Ahmed, Yixuan Gao, Adnan Armouti +111 Sept 2026cs.CR—89
Active noise cancellation on open-ear smart glassesarXiv:2604.05519Kuang Yuan, Freddy Yifei Liu, Tong Xiao +211 Sept 2026eess.AS—89
Discriminative Span as a Predictor of Synthetic Data Utility via Classifier ReconstructionarXiv:2605.09697Radhika Amar Desai, Modigari Narendra11 Sept 2026cs.CV—89
Goal-Oriented Lower-Tail Calibration of Gaussian Processes for Bayesian OptimizationarXiv:2605.20145Aur\'elien Pion, Emmanuel Vazquez11 Sept 2026stat.ML—89
Activation-Based Active Learning for In-Context Learning: Challenges and InsightsarXiv:2606.05134Yaseen M. Osman, Geoff V. Merrett, Stuart E. Middleton11 Sept 2026cs.CL—89
Statistically Valid Post-Training Hyperparameter Selection: From Tuning to GuaranteesarXiv:2606.25601Amirmohammad Farzaneh, Osvaldo Simeone11 Sept 2026stat.ML—89
Physics-constrained neural networks for surrogate modeling of lossless periodic structuresarXiv:2606.28119Eric Prehn, Peter Jung11 Sept 2026physics.optics—89
The Zero Pattern of a Design Matrix Drives Multiple Descent in Over-parameterized RegressionarXiv:2607.24041Kevin Han Huang, Haoyu Ye, Somak Laha +111 Sept 2026math.ST—89
SparseDitto: An Agentic Sparse Compilation Framework through Architecture-Aware Synthesis on GPUsarXiv:2608.05033Shiyang Li, Guangyan Sun, Jinwei Tang +211 Sept 2026cs.DC—89
What to Preserve, Where to Adapt: A Depth-Wise Analysis of Forgetting in Continual Gynecological Image SegmentationarXiv:2608.13660Amal Saqib, Tausifa Jan Saleem, Numan Saeed +111 Sept 2026cs.CV—89
SAC-Copula: Quality-Preserving Watermarking for Diffusion Language Models via Smooth Correlated Gumbel FieldsarXiv:2608.20839Baixin Li, Haiyun He11 Sept 2026cs.CL—89
EF1-Constrained Nash Social Welfare with Identical Additive Valuations: Complexity, Guarantees, and ExperimentsarXiv:2609.03846Zih-Sian Yang, Yi-Hao Chen, Yu-Te Kuan +211 Sept 2026cs.GT—89
Representation learning of human cortical folding to reveal long lasting neurodevelopmental signaturesarXiv:2609.05438Julien Laval, Robin Guiavarch, Antoine Dufournet +211 Sept 2026q-bio.QM—89
A Gradient-based yet Spike-Timing-Dependent Solution to the Feedback Learning Problem in Neural MicrocircuitsarXiv:2609.08070Xiangnan Zhang, Jingxin Liu, Ranqi Lu +211 Sept 2026cs.NE—89
Fixed-Dimensional Latent Flow for Generating Variable-Size 3D MoleculesarXiv:2609.08333Weichi Yao, Cameron Gruich, Bryan R. Goldsmith +111 Sept 2026physics.chem-ph—89
Limitations of Automated Simulatability: LLM Simulators Can Bypass ExplanationsarXiv:2609.08585Antonin Poch\'e, Fanny Jourdan, Nils Feldhus +211 Sept 2026cs.CL—89
Silver Rate Is (Almost) Optimal for Gradient DescentarXiv:2609.09152Yuhan Ye, Kaizhao Liu11 Sept 2026math.OC—89
Characterizing Language Generation in the Limit: Finite Witnesses and a Separation-Width HierarchyarXiv:2609.10525Xiaoyu Li, Andi Han, Jiaojiao Jiang +111 Sept 2026cs.FL—89
Subagents vs Agent Skills: Executing Reusable Knowledge for Long-Horizon Agentic TasksarXiv:2609.09233Wasu Top Piriyakulkij, Rachel Lawrence, Alicia Curth +211 Sept 2026cs.AI—89
Proof-Carrying Cognition: Closing the Verification Gap with Reality-Settled RewardarXiv:2609.09776Eshwar Reddy M, Sourav Karmakar11 Sept 2026cs.AI—89
Belief-State Engine: Augmenting LLMs for Principled Planning Under Partial ObservabilityarXiv:2609.10036Arnab Chattopadhayay, Debdipta Halder11 Sept 2026cs.AI—89
Agent-Based ML-LLM Fusion with Self-Optimizing Prompts for Plateau Weather AlertsarXiv:2609.10135Shuai Yan, Yang Xu, Shan He11 Sept 2026cs.AI—89
Kernel-Managed Shared Memory for System-Wide PersonalizationarXiv:2609.10144Ryan Lum, Yongfeng Zhang11 Sept 2026cs.AI—89
TRACE: Training Reasoning Agents for Causal Exploration with Synthesized RewardsarXiv:2609.10315Rui Sun, Zhan Shi, Bing He11 Sept 2026cs.AI—89
Cyber-Financial Contagion: Modeling the Propagation of an AI Vendor Compromise Through the Banking SystemarXiv:2609.10350Alex Leytes11 Sept 2026cs.AI—89
Quantifying Logical Consistency in Transformers via Query-Key AlignmentarXiv:2502.17017Eduard Tulchinskii, Anastasia Voznyuk, Laida Kushnareva +211 Sept 2026cs.CL—89
Scaling Post-Training Ternarisation to Qwen3-8B Capability Retention, Reproduction, Lossless Packing, and Packed ExecutionarXiv:2609.09240Anirudh Malik, M Sparsh Mehra, Poojith Devan11 Sept 2026cs.LG—89
Distribution-Consistent Inference for Dynamic Sparse Mixture-of-ExpertsarXiv:2609.09241Dohyeon Kim, Bedionita Soro, Sung Ju Hwang11 Sept 2026cs.LG—89
Critical initialization destabilizes higher input derivatives in wide scalar-input networksarXiv:2609.09244Prashant Singh, Pranav Singh11 Sept 2026stat.ML—89
What Fixed-Rollout pass@k Evaluations Can IdentifyarXiv:2609.09245Pranav Singh, Prashant Singh11 Sept 2026stat.ML—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.