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
Statistically Valid Post-Training Hyperparameter Selection: From Tuning to GuaranteesarXiv:2606.25601stat.MLAmirmohammad Farzaneh, Osvaldo Simeone11 Sept 2026
Physics-constrained neural networks for surrogate modeling of lossless periodic structuresarXiv:2606.28119physics.opticsEric Prehn, Peter Jung11 Sept 2026
The Zero Pattern of a Design Matrix Drives Multiple Descent in Over-parameterized RegressionarXiv:2607.24041math.STKevin Han Huang, Haoyu Ye, Somak Laha +111 Sept 2026
SparseDitto: An Agentic Sparse Compilation Framework through Architecture-Aware Synthesis on GPUsarXiv:2608.05033cs.DCShiyang Li, Guangyan Sun, Jinwei Tang +211 Sept 2026
What to Preserve, Where to Adapt: A Depth-Wise Analysis of Forgetting in Continual Gynecological Image SegmentationarXiv:2608.13660cs.CVAmal Saqib, Tausifa Jan Saleem, Numan Saeed +111 Sept 2026
SAC-Copula: Quality-Preserving Watermarking for Diffusion Language Models via Smooth Correlated Gumbel FieldsarXiv:2608.20839cs.CLBaixin Li, Haiyun He11 Sept 2026
EF1-Constrained Nash Social Welfare with Identical Additive Valuations: Complexity, Guarantees, and ExperimentsarXiv:2609.03846cs.GTZih-Sian Yang, Yi-Hao Chen, Yu-Te Kuan +211 Sept 2026
Representation learning of human cortical folding to reveal long lasting neurodevelopmental signaturesarXiv:2609.05438q-bio.QMJulien Laval, Robin Guiavarch, Antoine Dufournet +211 Sept 2026
A Gradient-based yet Spike-Timing-Dependent Solution to the Feedback Learning Problem in Neural MicrocircuitsarXiv:2609.08070cs.NEXiangnan Zhang, Jingxin Liu, Ranqi Lu +211 Sept 2026
Fixed-Dimensional Latent Flow for Generating Variable-Size 3D MoleculesarXiv:2609.08333physics.chem-phWeichi Yao, Cameron Gruich, Bryan R. Goldsmith +111 Sept 2026
Limitations of Automated Simulatability: LLM Simulators Can Bypass ExplanationsarXiv:2609.08585cs.CLAntonin Poch\'e, Fanny Jourdan, Nils Feldhus +211 Sept 2026
Silver Rate Is (Almost) Optimal for Gradient DescentarXiv:2609.09152math.OCYuhan Ye, Kaizhao Liu11 Sept 2026
Characterizing Language Generation in the Limit: Finite Witnesses and a Separation-Width HierarchyarXiv:2609.10525cs.FLXiaoyu Li, Andi Han, Jiaojiao Jiang +111 Sept 2026
Subagents vs Agent Skills: Executing Reusable Knowledge for Long-Horizon Agentic TasksarXiv:2609.09233cs.AIWasu Top Piriyakulkij, Rachel Lawrence, Alicia Curth +211 Sept 2026
Proof-Carrying Cognition: Closing the Verification Gap with Reality-Settled RewardarXiv:2609.09776cs.AIEshwar Reddy M, Sourav Karmakar11 Sept 2026
Belief-State Engine: Augmenting LLMs for Principled Planning Under Partial ObservabilityarXiv:2609.10036cs.AIArnab Chattopadhayay, Debdipta Halder11 Sept 2026
Agent-Based ML-LLM Fusion with Self-Optimizing Prompts for Plateau Weather AlertsarXiv:2609.10135cs.AIShuai Yan, Yang Xu, Shan He11 Sept 2026
Kernel-Managed Shared Memory for System-Wide PersonalizationarXiv:2609.10144cs.AIRyan Lum, Yongfeng Zhang11 Sept 2026
TRACE: Training Reasoning Agents for Causal Exploration with Synthesized RewardsarXiv:2609.10315cs.AIRui Sun, Zhan Shi, Bing He11 Sept 2026
Cyber-Financial Contagion: Modeling the Propagation of an AI Vendor Compromise Through the Banking SystemarXiv:2609.10350cs.AIAlex Leytes11 Sept 2026
Quantifying Logical Consistency in Transformers via Query-Key AlignmentarXiv:2502.17017cs.CLEduard Tulchinskii, Anastasia Voznyuk, Laida Kushnareva +211 Sept 2026
Scaling Post-Training Ternarisation to Qwen3-8B Capability Retention, Reproduction, Lossless Packing, and Packed ExecutionarXiv:2609.09240cs.LGAnirudh Malik, M Sparsh Mehra, Poojith Devan11 Sept 2026
Distribution-Consistent Inference for Dynamic Sparse Mixture-of-ExpertsarXiv:2609.09241cs.LGDohyeon Kim, Bedionita Soro, Sung Ju Hwang11 Sept 2026
Critical initialization destabilizes higher input derivatives in wide scalar-input networksarXiv:2609.09244stat.MLPrashant Singh, Pranav Singh11 Sept 2026
What Fixed-Rollout pass@k Evaluations Can IdentifyarXiv:2609.09245stat.MLPranav Singh, Prashant Singh11 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.