Instant research discovery
Search and browse arXiv CS/AI/ML papers, enriched with AI-generated insights.
Generate novel research ideas grounded in real arXiv papers with Brainstorm.
PreviousNext
| Paper | Published | Area | Tags | Intel | Citations |
|---|---|---|---|---|---|
Search and browse arXiv CS/AI/ML papers, enriched with AI-generated insights.
Generate novel research ideas grounded in real arXiv papers with Brainstorm.
| Paper | Published | Area | Tags | Intel | Citations |
|---|---|---|---|---|---|
Search and browse arXiv CS/AI/ML papers, enriched with AI-generated insights.
Generate novel research ideas grounded in real arXiv papers with Brainstorm.
| Paper | Published | Area | Tags | Intel | Citations |
|---|---|---|---|---|---|
| Paper | Published | Area | Tags | Intel | Citations |
|---|---|---|---|---|---|
| Caught in the Act: Probes Effectively Detect Sabotage and Catch Unverbalized Deception Adam Gleave, Alex F. Spies, Chris Cundy, Oskar J. Hollinsworth Published: 2026-10-08Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-10-08 | cs.LG | ai-safety, cslg, preprint | E9 / R6 (93%) | - |
| Compactness and Consistency: A Conjoint Framework for Deep Graph Clustering Jiancheng Lv, Kangjie Zheng, Li Shen, Siyu Yi Published: 2026-10-08Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-10-08 | cs.LG | ai-safety, cslg, preprint | E9 / R8 (89%) | - |
| Emergent Inverse-Depth Scaling From Nonlinearity In Attention Jeff Gore, Yizhou Liu, Ziming Liu, Zirui Peng Published: 2026-10-08Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-10-08 | cs.LG | ai-safety, cslg, preprint | E7 / R5 (92%) | - |
| From Geometry to Generalization: Why Row Normalization Can Beat Adam and Muon Chulhee Yun, Dogyoon Song, Jihwan Kim Published: 2026-10-08Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-10-08 | cs.LG | ai-safety, cslg, preprint | E6 / R6 (93%) | - |
| Generative Adversarial Loops Aditya Desai, Kislay Aditya Oj, Kumar Krishna Agrawal, Nidhi Jain Published: 2026-10-08Area: cs.LGCitations: - Tags: adversarial-robustness, ai-safety, cslg, preprint | 2026-10-08 | cs.LG | adversarial-robustness, ai-safety, cslg, preprint | E15 / R14 (90%) | - |
| GRPODropout: Less is More for Online Reinforcement Learning Rollouts Chen Wang, Hexuan Deng, Jihong Zhang, Min Zhang Published: 2026-10-08Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-10-08 | cs.LG | ai-safety, cslg, preprint | E6 / R5 (92%) | - |
| How to post-train on a surrogate: Envelope sampling mitigates reward hacking Aaditya Ramdas, Alexandra Chouldechova, Michael Oberst, Samir Khan Published: 2026-10-08Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-10-08 | cs.LG | ai-safety, cslg, preprint | E8 / R5 (90%) | - |
| KITE: A Knowledge-Injected Temporal Encoder for Time-Series Event Forecasting Camilla Mazzoleni, Federico Martelli, Gian-Alessandro Lombardi, Jonas Petersen Published: 2026-10-08Area: cs.LGCitations: 30 Tags: ai-safety, cslg, preprint | 2026-10-08 | cs.LG | ai-safety, cslg, preprint | E10 / R9 (92%) | 30 |
| Kronecker Product Attention: Memory-Efficient KV Compression via Structured Factorization Bahareh Nikpour, Hossein Rajabzadeh, Maryam Dialameh, Parsa Omidi Published: 2026-10-08Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-10-08 | cs.LG | ai-safety, cslg, preprint | E10 / R6 (91%) | - |
| Machine Learning and Time-Series Foundation Models for Day-Ahead Electricity Forecasting in a University Building Amey Vasulkar, Arie-Willem de Leeuw, Samuel Kernan Freire, Tadeo-Baldiri Salcedo-Rahola Published: 2026-10-08Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-10-08 | cs.LG | ai-safety, cslg, preprint | E10 / R7 (92%) | - |
| Meta-Reflective Evolution Effectively Improves Production AI Systems Aditi Somayajula, Aditya G. Parameswaran, Anupam Datta, Avishree Khare Published: 2026-10-08Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-10-08 | cs.LG | ai-safety, cslg, preprint | E9 / R6 (92%) | - |
| MPGE: A Multi-Perspective Graph Explainer for Molecular Classification Explanation Mahtab Sarvmaili Published: 2026-10-08Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-10-08 | cs.LG | ai-safety, cslg, preprint | E13 / R11 (93%) | - |
| NanoProof: Open and Efficient Automated Theorem Proving in Lean 4 Matěj Kripner, Milan Straka Published: 2026-10-08Area: cs.LGCitations: 50 Tags: ai-safety, cslg, preprint | 2026-10-08 | cs.LG | ai-safety, cslg, preprint | E11 / R8 (95%) | 50 |
| Neuro-Memory Fuzzy Inference System for Mimicking Human-like Car Following Behavior Md Asif Raihan. Md. Hadiuzzaman, Nazmul Haque Published: 2026-10-08Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-10-08 | cs.LG | ai-safety, cslg, preprint | E11 / R11 (92%) | - |
| PIVOT: Perplexity-Informed KD-to-RL Transition Scheduling for Vertical-Domain Few-Shot Distillation Heng Li, Jing Xiao, Ning Cheng, Shaojun Wang Published: 2026-10-08Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-10-08 | cs.LG | ai-safety, cslg, preprint | E8 / R8 (92%) | - |
| Recurrent Harness for Agentic Continual Learning Bailin Wang, Jianyu Wang, Qifan Wang, Yang Song Published: 2026-10-08Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-10-08 | cs.LG | ai-safety, cslg, preprint | E14 / R13 (91%) | - |
| REDaCT: Collapse-Free Unlearning in Large Reasoning Models Joshua Maccoby, Wendy Hui Wang Published: 2026-10-08Area: cs.LGCitations: 15 Tags: ai-safety, cslg, preprint | 2026-10-08 | cs.LG | ai-safety, cslg, preprint | E9 / R7 (92%) | 15 |
| Scalable Hierarchical Graph Generation via Soft Community Structure Ahmet Tüzen, Helge Langseth, Kjetil Nørvåg Published: 2026-10-08Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-10-08 | cs.LG | ai-safety, cslg, preprint | E8 / R8 (91%) | - |
| Sera: Semantic Representation Aggregation for Reliable and Interpretable Battery Health Forecasting Fang Liu, Jiawei Li, Man-Fai Ng, Wei Zhang Published: 2026-10-08Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-10-08 | cs.LG | ai-safety, cslg, preprint | E6 / R5 (96%) | - |
| Sera: Semantic Representation Aggregation for Reliable and Interpretable Battery Health Forecasting Fang Liu, Jiawei Li, Man-Fai Ng, Wei Zhang Published: 2026-10-08Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-10-08 | cs.LG | ai-safety, cslg, preprint | E6 / R5 (94%) | - |
| Stability-Plasticity Balance via Singular-Vector Selection in LLM Continual Learning Hainan Zhang, Hongwei Zheng, Liang Pang, Lingxiang Wang Published: 2026-10-08Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-10-08 | cs.LG | ai-safety, cslg, preprint | E9 / R8 (91%) | - |
| Stochastic Grouping Conformal Prediction for Effective Subgroup Reliability Fan Zhou, Meihui Zhong, Ting Zhong, Wenxin Tai Published: 2026-10-08Area: cs.LGCitations: 15 Tags: ai-safety, cslg, preprint | 2026-10-08 | cs.LG | ai-safety, cslg, preprint | E10 / R10 (91%) | 15 |
| The Polytopal Neural Network A. Emilie J. Wedenborg, Anders V. Nørskov, Kristoffer Wickstrøm, Morten Mørup Published: 2026-10-08Area: cs.LGCitations: 15 Tags: ai-safety, cslg, preprint | 2026-10-08 | cs.LG | ai-safety, cslg, preprint | E7 / R6 (92%) | 15 |
| Timer-M1: A Multivariate Time Series Foundation Model via Learning Primitives Haixuan Liu, Haoran Zhang, Jianmin Wang, Mingsheng Long Published: 2026-10-08Area: cs.LGCitations: 15 Tags: ai-safety, cslg, preprint | 2026-10-08 | cs.LG | ai-safety, cslg, preprint | E12 / R9 (93%) | 15 |
| Uncovering and Fixing Collider Bias in Bayesian PINNs Michael Obermayr, Robert Peharz Published: 2026-10-08Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-10-08 | cs.LG | ai-safety, cslg, preprint | E10 / R8 (93%) | - |
| Using Weisfeiler-Leman Features for Algorithm Selection in Constraint Optimisation Alessio Pellegrino, Jacopo Mauro Published: 2026-10-08Area: cs.LGCitations: 15 Tags: ai-safety, cslg, preprint | 2026-10-08 | cs.LG | ai-safety, cslg, preprint | E10 / R6 (93%) | 15 |
| Zatom-2: Multitask Pretraining on Atomistic Data for Generative Modeling across Domains Alex Abrudan, Alex Morehead, Antonia Panescu, Joseph Jacobson Published: 2026-10-08Area: cs.LGCitations: 12 Tags: ai-safety, cslg, preprint | 2026-10-08 | cs.LG | ai-safety, cslg, preprint | E8 / R10 (92%) | 12 |
| Activation-Aware Weight Tensorization: A Calibration-Time Preconditioner for Tensor-Network LLM Compression Alessandro Beatini, Emanuele Rodolà, Marco Maronese Published: 2026-10-07Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-10-07 | cs.LG | ai-safety, cslg, preprint | E11 / R7 (95%) | - |
| A Good Self-Teacher Meets the Student Where They Are: Joint On-Policy Learning and Teaching Arnav Dalal, Jiantao Jiao, Randy Ardywibowo Published: 2026-10-07Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-10-07 | cs.LG | ai-safety, cslg, preprint | E9 / R8 (92%) | - |
| Align Before You Combine: Reference Space Calibration for Supervision Without Ground Truth Jackson Eshbaugh, Jorge Silveyra Published: 2026-10-07Area: cs.LGCitations: 26 Tags: ai-safety, cslg, preprint | 2026-10-07 | cs.LG | ai-safety, cslg, preprint | E11 / R9 (93%) | 26 |