Skip to content
AI Atlas
Research

Papers

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

378 total

Reset
Papers
TitleAuthorsPublishedCategoriesOrganization / venueQuality
Structural priors for data-efficient language learningarXiv:2609.11505Yana Veitsman, Jonas Mayer Martins, Jonathan Lautenschlager +111 Sept 2026cs.CL—89
Enabling Knowledge Graph Understanding at Scale with the EXplore Your Graphs ENgine (EXYGEN)arXiv:2609.11569Harshdeep Singh, Yurui Zhu, Giovanni Colavizza +111 Sept 2026cs.AI—89
Distributed Optimization of Modular Production Systems using Model-based Reinforcement Learning with Inverse ModelsarXiv:2609.11615Andreas Schwung, Steve Yuwono, Sofiene Lassoued +111 Sept 2026cs.AI—89
ZipCodec: Ultra-Low-Frame-Rate Streaming Speech CodingarXiv:2609.11642Luca Della Libera, Cem Subakan, Mirco Ravanelli11 Sept 2026cs.SD—89
ORCH: Organizational Principles Enable Collective Intelligence in Embodied AIarXiv:2609.11737Zhengran Ji, Jonathan Hyun, Boyuan Chen11 Sept 2026cs.MA—89
LOCUS: Task-Aware Low-Rank Post-Training for Token-Efficient Language GenerationarXiv:2609.11739Dongfang Zhao11 Sept 2026cs.CL—89
SIRF: A Spec-Internalized Risk Foundation Model for Industrial Content Risk ControlarXiv:2609.11752Suwan Wu, Yumeng Lin, Pengcheng Yuan +111 Sept 2026cs.AI—89
A Unified Per-Token Gating Family for On-Policy Distillation: FKL/RKL Mixing with Multi-Channel and Bias CoefficientsarXiv:2609.11768Suwan Wu, Yumeng Lin, Pengcheng Yuan +111 Sept 2026cs.AI—89
Logit Refiner: Improving Visual Autoregressive Models via Intra-Scale Dependency ModelingarXiv:2609.11804Meimingwei Li, Stefan Andreas Baumann, Felix Krause +111 Sept 2026cs.CV—89
Explainability Assistant: A Conversational XAI Interface for Interpreting Energy Consumption ModelsarXiv:2609.11860Rodion Krjut\v{s}kov, Eduard Barbu, Nikos Sakkas +111 Sept 2026cs.AI—89
Domain-Specific Hallucination Detection in Large Language ModelsarXiv:2609.11878Varun Teja Chundru, Debasmita Biswas11 Sept 2026cs.CL—89
Generative Marketing Mix Modeling: A Causal Inference Framework Linking GEO and GEM to Business ImpactarXiv:2609.11915Masahiro Kato, Daiki Honma, Taka Kato11 Sept 2026stat.ML—89
Optimizing Three Critical Factors for Practical and Effective OOD Detection Fine-TuningarXiv:2308.01030Hyunjun Choi, JaeHo Chung, Hawook Jeong11 Sept 2026cs.LG—89
ExpTest: Loss-Curve Hypothesis Testing for Autonomous Learning-Rate Selection in Deep Neural NetworksarXiv:2411.16975Zan Chaudhry, Naoko Mizuno11 Sept 2026cs.LG—89
SG-Blend: Learning an Interpolation Between Improved Swish and GELU for Robust Neural RepresentationsarXiv:2505.23942Gaurav Sarkar, Syed Affan Daimi, Jay Gala +111 Sept 2026cs.LG—89
Generalization in VAE and Diffusion Models: A Unified Information-Theoretic AnalysisarXiv:2506.00849Qi Chen, Jierui Zhu, Florian Shkurti11 Sept 2026cs.LG—89
CertDW: Towards Certified Dataset Ownership Verification via Conformal CalibrationarXiv:2506.13160Ting Qiao, Yiming Li, Jianbin Li +211 Sept 2026cs.LG—89
Learning Intrinsic Water-Quality Dynamics with Rainfall for Data-Driven ForecastingarXiv:2508.08279Ziqi Wang, Hailiang Zhao, Cheng Bao +211 Sept 2026cs.LG—89
Evidence for Limited Metacognition in LLMsarXiv:2509.21545Christopher Ackerman11 Sept 2026cs.LG—89
On the Societal Impact of Machine LearningarXiv:2510.23693Joachim Baumann11 Sept 2026cs.LG—89
Output Embedding Centering for Stable LLM PretrainingarXiv:2601.02031Felix Stollenwerk, Anna Lokrantz, Niclas Hertzberg11 Sept 2026cs.LG—89
MOSAIC: A Universal Agent-Level Interface for Cross-Paradigm Agent Mixing and Human-AI CollaborationarXiv:2603.01260Abdulhamid M. Mousa, Jinhui Pang, Rakhmonberdi Khajiev +211 Sept 2026cs.LG—89
HISA: Efficient Hierarchical Indexing for Fine-Grained Sparse AttentionarXiv:2603.28458Yufei Xu, Fanxu Meng, Fan Jiang +211 Sept 2026cs.LG—89
Monotone Neural Policy Iteration for High-Dimensional First-Order Hamilton--Jacobi--Bellman EquationsarXiv:2605.07116Minseok Kim, Yeongjong Kim, Namkyeong Cho +111 Sept 2026cs.LG—89
Terminal Symmetry as a Carrier of Asymmetric Process Knowledge: Statewise Refinement for Anytime Verified ConstructionarXiv:2608.11318Yi Liu11 Sept 2026cs.LG—89
CAT-GS: Balanced Multimodal Learning via Calibrated Gating and Fusion SurgeryarXiv:2608.24947Mahir Shahriar Tamim, Sharjil Khan, Md. Samiul Alim +211 Sept 2026cs.LG—89
How Proper Scoring Rules Shape LLM ForecastingarXiv:2608.28482Benjamin Turtel, Paul Wilczewski, Kris Skotheim +211 Sept 2026cs.LG—89
REAL-Q: E2E LLM Quantization via Dynamic Gradient DescentarXiv:2609.00049Qian Zhang, Yaoming Li, Zhewen Tan +211 Sept 2026cs.LG—89
No Screening is More Efficient with Multiple ObjectsarXiv:2408.10077Shunya Noda, Genta Okada11 Sept 2026econ.TH—89
Federated Learning for Surgical Vision in Appendicitis Classification: Results of the FedSurg EndoVis 2024 ChallengearXiv:2510.04772Max Kirchner, Hanna Hoffmann, Alexander C. Jenke +211 Sept 2026cs.CV—89
Perturbation: A simple and efficient adversarial tracer for representation learning in language modelsarXiv:2603.23821Joshua Rozner, Cory Shain11 Sept 2026cs.CL—89
Wiggle and Go! System Identification for Zero-Shot Dynamic Rope ManipulationarXiv:2604.22102Arthur Jakobsson, Abhinav Mahajan, Karthik Pullalarevu +211 Sept 2026cs.RO—89
Continuous Diffusion Scales Competitively with Discrete Diffusion for LanguagearXiv:2605.18530Zhihan Yang, Wei Guo, Shuibai Zhang +211 Sept 2026cs.CL—89
CLSP-REQA: A Real-Time Quality-Aware Closed-Loop Seizure Prediction Framework with Mamba-BiLSTM and Confidence-Gated InterventionarXiv:2606.00074Mufeng Chen, Qi Wu, Bingchao Huang +211 Sept 2026eess.SP—89
AI Economist Agent: An Agentic Framework for Evidence-Based Economic and Financial Analysis with RAG, Knowledge Graphs, and Large Language ModelsarXiv:2606.20041Masahiro Kato11 Sept 2026econ.GN—89
ProsMAE: Multi-Source MAE Pretraining for ISUP Grade ClassificationarXiv:2607.08162Anna Jung, Kyeonghun Kim, Youngung Han +211 Sept 2026cs.CV—89
Sympathetic Framing: Evaluating AI Alignment across Sociodemographic GroupsarXiv:2607.27232Haran Shani-Narkiss, Michael Fire, Oren Tsur11 Sept 2026cs.CL—89
VALG: An Agentic System for ML Theory ResearcharXiv:2608.13060Dechen Zhang, Xuan Tang, Xinxiang Yin +211 Sept 2026cs.AI—89
Clearing the Fog: Towards Installing and Refining Proactive Exploration Capabilities in LLM AgentsarXiv:2608.14339Zhizhao Guan, Chen Huang, Ziming Liu +211 Sept 2026cs.AI—89
GameWAM: A World Action Model for Video GamesarXiv:2608.26200Yuncheng Guo, Zhanqiu Zhang, Yiwen Guo +111 Sept 2026cs.AI—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.