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 |
|---|---|---|---|---|---|
| dattri-LLM: A Unified and Efficient Library for Training Data Attribution at LLM Scale Jiaqi W. Ma, Junwei Deng, Pingbang Hu, Shixuan Liu Published: 2026-09-30Area: cs.LGCitations: 15 Tags: ai-safety, cslg, preprint | 2026-09-30 | cs.LG | ai-safety, cslg, preprint | E18 / R16 (91%) | 15 |
| Deep Learning for Anomaly Detection in Railway Systems: A Structured Survey Ammar Bouketta, Hamza Ouarnoughi, Smail Niar Published: 2026-09-30Area: cs.LGCitations: 158 Tags: ai-safety, cslg, preprint | 2026-09-30 | cs.LG | ai-safety, cslg, preprint | E10 / R7 (91%) | 158 |
| Distilling Diffusion Score Discrepancy for Efficient Training Data Attribution Jiaqi W. Ma, Jinju Kim, Joan Serr脿, Kin Wai Cheuk Published: 2026-09-30Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-30 | cs.LG | ai-safety, cslg, preprint | E11 / R7 (95%) | - |
| Distilling Diffusion Score Discrepancy for Efficient Training Data Attribution Jiaqi W. Ma, Jinju Kim, Joan Serr脿, Kin Wai Cheuk Published: 2026-09-30Area: cs.LGCitations: 15 Tags: ai-safety, cslg, preprint | 2026-09-30 | cs.LG | ai-safety, cslg, preprint | E12 / R9 (93%) | 15 |
| Do Better Goal Representations Improve Goal-Conditioned Reinforcement Learning? Abdul Monaf Chowdhury, Md Mehedi Hasan, Nafiul Haque, Shifat E Arman Published: 2026-09-30Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-30 | cs.LG | ai-safety, cslg, preprint | - | - |
| Does Learning Protein Folding Generalize to Broader Reasoning? Shuangjia Zheng, Xiaoliang Shi, Yizhou Dang, Yong Liu Published: 2026-09-30Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-30 | cs.LG | ai-safety, cslg, preprint | E10 / R9 (94%) | - |
| Efficient Active Auditing of Multi-Group Fairness with Bias Probes Ayoub Ajarra, Debabrota Basu Published: 2026-09-30Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-30 | cs.LG | ai-safety, cslg, preprint | - | - |
| Evaluating Persistent Calibration under Evolving Model Knowledge Elias Stengel-Eskin, Mohit Bansal, Thomas Hofweber, Victor Wang Published: 2026-09-30Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-30 | cs.LG | ai-safety, cslg, preprint | E13 / R11 (95%) | - |
| Explicit Trajectory Diversity for RL-Based Post-Training of LLM Agents Hao Wang, Heng Cao, Huaiyu Fu, Jian Ya Published: 2026-09-30Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-30 | cs.LG | ai-safety, cslg, preprint | E10 / R7 (94%) | - |
| Exploring More, Reasoning Better: Stepwise Risk-Sensitive GRPO for Diffusion Language Models Bowen Zuo, David Crandall, Dongruo Zhou, Yinglun Zhu Published: 2026-09-30Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-30 | cs.LG | ai-safety, cslg, preprint | E9 / R6 (92%) | - |
| FAER: Auditable Utility-Aligned Trajectory Replay for Language Model Post-Training Bokun Wang, Daren Zha, Jun Xiao, Miaobo Hu Published: 2026-09-30Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-30 | cs.LG | ai-safety, cslg, preprint | E10 / R6 (94%) | - |
| Fenchel Tilting: Weighted Correction for Efficient Finetuning of Generative Models Dmitry Dylov, Maksim Bobrin, Maksim Zhdanov Published: 2026-09-30Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-30 | cs.LG | ai-safety, cslg, preprint | E11 / R8 (91%) | - |
| Fenchel Tilting: Weighted Correction for Efficient Finetuning of Generative Models Dmitry Dylov, Maksim Bobrin, Maksim Zhdanov Published: 2026-09-30Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-30 | cs.LG | ai-safety, cslg, preprint | - | - |
| Free Everywhere, Exact on Trees: PPO's Dropped Correction Buys Sample Efficiency Under Aggressive Reuse Nima H. Siboni Published: 2026-09-30Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-30 | cs.LG | ai-safety, cslg, preprint | - | - |
| Free Everywhere, Exact on Trees: PPO's Dropped Correction Buys Sample Efficiency Under Aggressive Reuse Nima H. Siboni Published: 2026-09-30Area: cs.LGCitations: 27 Tags: ai-safety, cslg, preprint | 2026-09-30 | cs.LG | ai-safety, cslg, preprint | E11 / R6 (96%) | 27 |
| From Benchmarks to Production: Transferring Time Series Anomaly Detection Methods for Electricity Production Monitoring Christophe Degouy, F茅licie Bizeul, Manel Boumghar, Nardi Xhepi Published: 2026-09-30Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-30 | cs.LG | ai-safety, cslg, preprint | - | - |
| From Imitation to Reward Discovery: On-Policy Warmup for Agentic RL Jian Wang, Jinjie Gu, Lei Liu, Tiantian He Published: 2026-09-30Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-30 | cs.LG | ai-safety, cslg, preprint | - | - |
| From Modes to Memories: Characterizing the Scale-Space Dynamics of Diffusion Models Cristina L贸pez Amado, Francesco Locatello, Marco Fumero Published: 2026-09-30Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-30 | cs.LG | ai-safety, cslg, preprint | - | - |
| From Search to Signal: Online Post-Training in Automatic Heuristic Design Tianyu Zhou, Yilun Yuan, Zhenzhou Tang Published: 2026-09-30Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-30 | cs.LG | ai-safety, cslg, preprint | - | - |
| Game-Guided Skill Discovery through Self-Play for Playable Agent Control Jeonghwan Kim, Sehoon Ha, Seungeun Rho, Xue Bin Peng Published: 2026-09-30Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-30 | cs.LG | ai-safety, cslg, preprint | - | - |
| GeoNest: Learning to Select Failure-Aware Neighborhoods for the Irregular Knapsack Problem in a Circular Container Baochang Zhang, Huiming Zhang, Linlin Yang, Sheng Xu Published: 2026-09-30Area: cs.LGCitations: 15 Tags: ai-safety, cslg, preprint | 2026-09-30 | cs.LG | ai-safety, cslg, preprint | E6 / R6 (92%) | 15 |
| GFD-OPD: Guidance-Folded On-Policy Distillation of Diffusion Models Across Scales Dan Guo, Jiayan Teng, Jiazheng Xu, Jie Tang Published: 2026-09-30Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-30 | cs.LG | ai-safety, cslg, preprint | - | - |
| GRPO Training Dynamics for Small Language Models Aryan Singhal, Debojyoti Dutta, Henry Wong, Rajat Ghosh Published: 2026-09-30Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-30 | cs.LG | ai-safety, cslg, preprint | - | - |
| Gumbel Straight Flow: Distilling Autoregressive Models into One-step Flow Maps Andrew Campbell, Arnaud Doucet, David Ruhe, Thomas Mensink Published: 2026-09-30Area: cs.LGCitations: 25 Tags: ai-safety, cslg, preprint | 2026-09-30 | cs.LG | ai-safety, cslg, preprint | E7 / R5 (91%) | 25 |
| Hard-Gate Candidacy in a Deployed Validator Suite Xin Xu Published: 2026-09-30Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-30 | cs.LG | ai-safety, cslg, preprint | - | - |
| HO-FL: Hybrid-Order Federated Learning for Heterogeneous Edge Devices Qiyuan Chen, Xianhao Chen, Xian Wu, Yanan Ma Published: 2026-09-30Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-30 | cs.LG | ai-safety, cslg, preprint | - | - |
| How Does Local Landscape Geometry Evolve in Language Model Pre-Training? Bingrui Li, Huaijin Wu, Jinbo Wang, Junchi Yan Published: 2026-09-30Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-30 | cs.LG | ai-safety, cslg, preprint | - | - |
| In a Streaming World, Should You Stand Still? A Comprehensive Benchmark of Anomaly Detection in Streams Antoine Ajenjo, Emmanuel Remy, Magali Parrino, Paul Boniol Published: 2026-09-30Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-30 | cs.LG | ai-safety, cslg, preprint | - | - |
| Increasing Width Allows Greedy Layer-wise Training to Rival End-to-End Backpropagation in Self-Supervised Learning Joel Zylberberg, Syon Mansur Published: 2026-09-30Area: cs.LGCitations: 12 Tags: ai-safety, cslg, preprint | 2026-09-30 | cs.LG | ai-safety, cslg, preprint | E12 / R8 (94%) | 12 |
| Inference Auctions Asher Trockman, Keegan Harris, Michael I. Jordan, Nika Haghtalab Published: 2026-09-30Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-30 | cs.LG | ai-safety, cslg, preprint | - | - |