| Harbor Adapters and Harbor-Index: Infrastructure and a Curated Meta-Dataset for Large-Scale Agentic EvaluationarXiv:2609.04298cs.AI | Lin Shi (Audrey), Haowei Lin (Audrey), Zixuan Zhu (Audrey) +2 | — | 12 Sept 2026 | — | — | — | — |
| Artificial Intelligence Algorithms for the Detection of Pathologies Related to Lung Cancer through Image Analysis using Convolutional Neural Networks and Data Augmentation: a systematic mapping of the literaturearXiv:2609.10652cs.LG | Pablo Ramirez Amador | — | 11 Sept 2026 | — | — | — | — |
| The information geometry of large language models is shared, learned, and controllablearXiv:2609.11063cs.LG | Dario Picozzi | — | 11 Sept 2026 | — | — | — | — |
| Beyond Solver Verdicts: Generative Reward Models for AutoformalizationarXiv:2609.11085cs.LG | Vikash Singh, Debargha Ganguly, Aman Goel +2 | — | 11 Sept 2026 | — | — | — | — |
| LILA: Calibration-Free Structured Pruning of Large Language Models via Latent Spectral GeometryarXiv:2609.11163cs.LG | Sankar Behera, Dhruv Singh, Anshika Agnihotri +2 | — | 11 Sept 2026 | — | — | — | — |
| REVA: Reusable Evidence View Aggregation for Context-Efficient RAG ServingarXiv:2609.11209cs.LG | Tuan Nguyen, Qiran Hu, Banruo Liu +2 | — | 11 Sept 2026 | — | — | — | — |
| MUtE: A Dual Framework for Concept Erasure and Counterfactual InterventionsarXiv:2609.11253cs.LG | Antoine Saillenfest | — | 11 Sept 2026 | — | — | — | — |
| Why Does Post-Training Quantization Work?arXiv:2609.11716cs.LG | Yuxiang Chen, Michael Beyer, Jun Zhu +1 | — | 11 Sept 2026 | — | — | — | — |
| Data Scarcity and Model Sparsity: Mixtures-of-Experts Overfit More to Repeated DataarXiv:2609.11917cs.LG | Atindra Jha, Margaret Li, Jure Leskovec +2 | — | 11 Sept 2026 | — | — | — | — |
| Detectable Only Where It Is Confounded: What Verified Duplication Counts Say About Membership Evidence in Language ModelsarXiv:2609.10830cs.CL | Arman Nik Khah | — | 11 Sept 2026 | — | — | — | — |
| Structurally Speaking: Motif-Oriented Graph Captioning through Bidirectional Graph-Text TranslationarXiv:2609.10923cs.CL | Hsiao-Ying Lu, Dongyu Liu, Kwan-Liu Ma | — | 11 Sept 2026 | — | — | — | — |
| Empirical Evaluation of Membership Inference Attacks on NLP Text Classifiers: A Baseline Study on SST-2arXiv:2609.10935cs.CR | William Novak (Minot State University), Muhammad Abusaqer (Minot State University) | — | 11 Sept 2026 | — | — | — | — |
| Rebalancing Token Importance in Language Models with TF-IDF Weighted Cross-Entropy LossarXiv:2609.11029cs.CL | Zhijian Li, Stefan Larson, Kevin Leach | — | 11 Sept 2026 | — | — | — | — |
| When Noise Fabricates Bias: The Fragility of LLM-as-a-Judge Bias Measurement under Noisy TextarXiv:2609.11067cs.CL | DongHyun Ryu, Jaehyeok Lee, YeongJun Hwang +1 | — | 11 Sept 2026 | — | — | — | — |
| Negative Self-Distillation: Learning to Reason by Avoiding FlawsarXiv:2609.11699cs.CL | Rongcan Pei, Zhepei Wei, Shuyao Xu +2 | — | 11 Sept 2026 | — | — | — | — |
| Mapping Seven Decades of Philosophy in Colombia: Dynamic Topic Modelling of Ideas y ValoresarXiv:2412.04236cs.LG | Juan R. Loaiza, Miguel Gonz\'alez-Duque | — | 11 Sept 2026 | — | — | — | — |
| Evaluating Memory Structure in LLM AgentsarXiv:2602.11243cs.LG | Alina Shutova, Alexandra Olenina, Ivan Vinogradov +1 | — | 11 Sept 2026 | — | — | — | — |
| Progressive Agent Skill Generation via Reinforcement LearningarXiv:2608.01678cs.LG | Junhao Shen, Zhanqiu Zhang, Yiwen Guo +1 | — | 11 Sept 2026 | — | — | — | — |
| Narrative Consolidation: Formulating a New Task for Unifying Multi-Perspective AccountsarXiv:2512.18041cs.CL | Roger A. Finger, Eduardo G. Cortes, Sandro J. Rigo +1 | — | 11 Sept 2026 | — | — | — | — |
| Activation-Based Active Learning for In-Context Learning: Challenges and InsightsarXiv:2606.05134cs.CL | Yaseen M. Osman, Geoff V. Merrett, Stuart E. Middleton | — | 11 Sept 2026 | — | — | — | — |
| SAC-Copula: Quality-Preserving Watermarking for Diffusion Language Models via Smooth Correlated Gumbel FieldsarXiv:2608.20839cs.CL | Baixin Li, Haiyun He | — | 11 Sept 2026 | — | — | — | — |
| Limitations of Automated Simulatability: LLM Simulators Can Bypass ExplanationsarXiv:2609.08585cs.CL | Antonin Poch\'e, Fanny Jourdan, Nils Feldhus +2 | — | 11 Sept 2026 | — | — | — | — |
| NCP-ArchPreview Technical Report: Moving towards Latent Space Language Models through Next Concept PredictionarXiv:2609.10715cs.CL | NCP Team, Jiaqi Cao, Chiyu Chen +2 | — | 11 Sept 2026 | — | — | — | — |
| CMNIE: An Information Extraction Benchmark for Chinese Military NewsarXiv:2609.10722cs.CL | Yan Yu, Mengna Zhu, Zhenyu Song +2 | — | 11 Sept 2026 | — | — | — | — |
| Think Before You Link: Rarity, Reasoning, and Retrieval in Multilingual Entity LinkingarXiv:2609.10745cs.CL | Parinthapat Pengpun, Simran Khanuja, Graham Neubig | — | 11 Sept 2026 | — | — | — | — |