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 |
|---|---|---|---|---|---|
| An Informational Curse of Horizon in Goal-Conditioned Policy Learning John L. Zhou, Jonathan C. Kao, Yuxuan Dong Published: 2026-10-07Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-10-07 | cs.LG | ai-safety, cslg, preprint | E8 / R6 (92%) | - |
| Beyond Owls: Subliminal Learning Can Transfer Learned Capabilities and Backdoors Anna Sztyber-Betley, Jan Betley, Jan Dubi艅ski, Owain Evans Published: 2026-10-07Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-10-07 | cs.LG | ai-safety, cslg, preprint | E8 / R6 (92%) | - |
| Beyond Policy Support: Interaction Constrained Offline Reinforcement Learning for Autonomous Driving Cristina Cipriani, Karl Henrik Johansson, Mahmoud Selim Published: 2026-10-07Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-10-07 | cs.LG | ai-safety, cslg, preprint | E7 / R6 (94%) | - |
| Beyond Reward Suppression: Near-Optimal Offline Attacks on Warm-Start Bandits with Bounded Rewards Jinhang Zuo, Manhin Poon, Qirun Zeng, Qixin Zhang Published: 2026-10-07Area: cs.LGCitations: 15 Tags: ai-safety, cslg, preprint | 2026-10-07 | cs.LG | ai-safety, cslg, preprint | E9 / R5 (94%) | 15 |
| Beyond the Ergodic Wall: A Discrete Geometric Physics Sandbox for Analysing AI Scaling Limits and Complexity Collapse Simon Richard Daniel Published: 2026-10-07Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-10-07 | cs.LG | ai-safety, cslg, preprint | E10 / R8 (94%) | - |
| Budgeted Multi-Source Counterfactual Annotation for Off-Policy Evaluation Ali Eshragh, Biao Xiang, Kai Wang, Yuexing Li Published: 2026-10-07Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint, safety-evaluation | 2026-10-07 | cs.LG | ai-safety, cslg, preprint, safety-evaluation | E8 / R6 (92%) | - |
| CERO: Where and When to Allocate Rollouts for RL Post-Training Jiashuo Jiang, Xing Hu, Yige Wang, Yiming Zong Published: 2026-10-07Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-10-07 | cs.LG | ai-safety, cslg, preprint | E9 / R7 (89%) | - |
| CircuitTree: Composing Circuits into A Syllable Transcriber Ewan Dunbar, Gerald Penn, Jiankun Wei Published: 2026-10-07Area: cs.LGCitations: 18 Tags: ai-safety, cslg, preprint | 2026-10-07 | cs.LG | ai-safety, cslg, preprint | E8 / R7 (93%) | 18 |
| Coding-Agent Benchmarks Should Match Their Users' Task Flows Igor Slinko, Sergey Titov, Yaroslav Golubev Published: 2026-10-07Area: cs.LGCitations: 45 Tags: ai-safety, cslg, preprint | 2026-10-07 | cs.LG | ai-safety, cslg, preprint | E7 / R5 (94%) | 45 |
| Collaborative Reasoning Distillation via Cross-Feedback and Coherent Curation Dongsu Han, Seunggeun Cho, Taehoon Kim Published: 2026-10-07Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-10-07 | cs.LG | ai-safety, cslg, preprint | E11 / R10 (91%) | - |
| Composing What Each Teacher Learned: Multi-Teacher On-Policy Distillation through Teacher-Relative Shifts Alborz Geramifard, Hejian Sang, Rohit Jain, Shayan Mohajer Hamidi Published: 2026-10-07Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-10-07 | cs.LG | ai-safety, cslg, preprint | E11 / R7 (91%) | - |
| Conversational Task Disambiguation over Tabular Data: Leakage-Aware Formulation, Benchmark Suite, and Training Dino D'Agostino, Hannah Chen, Keyvan Golestan, Luis Scoccola Published: 2026-10-07Area: cs.LGCitations: 15 Tags: ai-safety, cslg, preprint | 2026-10-07 | cs.LG | ai-safety, cslg, preprint | E13 / R11 (93%) | 15 |
| Coverage-Aware Reasoning with Medical Tokens for Diagnosis Prediction Hang Lv, Haotian Fang, Junmeng Zhou, Kaisong Zhang Published: 2026-10-07Area: cs.LGCitations: 15 Tags: ai-safety, cslg, preprint | 2026-10-07 | cs.LG | ai-safety, cslg, preprint | E9 / R7 (93%) | 15 |
| Decoupling Exploration from Optimization in RLVR Micah Goldblum, Saif Punjwani Published: 2026-10-07Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-10-07 | cs.LG | ai-safety, cslg, preprint | E8 / R6 (91%) | - |
| Denoising Blocks, Not Tokens: Efficient Compressed Continuous Diffusion with Branching Token Realization Daniel M. Bikel, Haipeng Chen, Jiayun Wang, Peng Du Published: 2026-10-07Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-10-07 | cs.LG | ai-safety, cslg, preprint | E6 / R4 (92%) | - |
| DSReg: Provably Recovering Individual World Latents without Reconstruction Bernhard Sch枚lkopf, David Klindt, Randall Balestriero, Yujia Zheng Published: 2026-10-07Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-10-07 | cs.LG | ai-safety, cslg, preprint | E8 / R7 (92%) | - |
| Efficient Best-of-N policy evaluation for inference-time alignment Athiya Deviyani, Dennis Frauen, Jonas Schweisthal, Stefan Feuerriegel Published: 2026-10-07Area: cs.LGCitations: - Tags: ai-safety, alignment-training, cslg, preprint, safety-evaluation | 2026-10-07 | cs.LG | ai-safety, alignment-training, cslg, preprint, safety-evaluation | E7 / R6 (94%) | - |
| Efficient Patch-Based Anomaly Detection Fused with Diffusion Driven Generative Modeling for Semiconductor Wafer Bin Map Open Set Anomaly Detection Limon Bin Hossain, Md Sadib Rahman Ananta Published: 2026-10-07Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-10-07 | cs.LG | ai-safety, cslg, preprint | E7 / R7 (95%) | - |
| Evaluating Trajectory Features for Routing Final-Layer Attention Yupeng Yao Published: 2026-10-07Area: cs.LGCitations: 12 Tags: ai-safety, cslg, preprint | 2026-10-07 | cs.LG | ai-safety, cslg, preprint | E13 / R7 (93%) | 12 |
| Fault-tolerant foundation models Ila R. Fiete, Isaac L. Chuang, Trevor McCourt Published: 2026-10-07Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-10-07 | cs.LG | ai-safety, cslg, preprint | E10 / R8 (95%) | - |
| Few-Shot Learning for Personalised Automated Pain Assessment Friedhelm Schwenker, Hans A. Kestler, Heinke Hihn, Ibrahim Eisawy Published: 2026-10-07Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-10-07 | cs.LG | ai-safety, cslg, preprint | E16 / R23 (97%) | - |
| From Prompts to Trees: Effective LLM-Guided Tree Generation for Few-Shot Tabular Classification Bingsheng He, Qinbin Li, Yiqun Diao, Yue Qiu Published: 2026-10-07Area: cs.LGCitations: 15 Tags: ai-safety, cslg, preprint | 2026-10-07 | cs.LG | ai-safety, cslg, preprint | E12 / R9 (91%) | 15 |
| Fully Interpretable Minimal Transformers: From Geometry to Algorithm Raneem Mahajne, Toviah Moldwin Published: 2026-10-07Area: cs.LGCitations: 1 Tags: ai-safety, cslg, preprint | 2026-10-07 | cs.LG | ai-safety, cslg, preprint | E10 / R8 (94%) | 1 |
| GeoPrior-Mamba: Structured Process Priors with Mamba for Fine-Resolution XCO2 Reconstruction Haohuan Fu, Juepeng Zheng, Siru Zhong, Yinan Cai Published: 2026-10-07Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-10-07 | cs.LG | ai-safety, cslg, preprint | E11 / R10 (91%) | - |
| KGATE : a Knowledge Graph Embedding Training Environment Ana茂s Baudot, Antoine Toffano, Benjamin Loire, C茅lia Brahimi Published: 2026-10-07Area: cs.LGCitations: 15 Tags: ai-safety, cslg, preprint | 2026-10-07 | cs.LG | ai-safety, cslg, preprint | E21 / R19 (92%) | 15 |
| Kuration SDK: Addressing the Virtual2Real Gap via Data Curation Eric Song, Kunal Sawarkar, Mayank Sengupta, Nirmit Desai Published: 2026-10-07Area: cs.LGCitations: 15 Tags: ai-safety, cslg, preprint | 2026-10-07 | cs.LG | ai-safety, cslg, preprint | E10 / R7 (94%) | 15 |
| LeCuration: A Tiny World Model as a Data Curation Multi-Tool Eric Song, Kunal Sawarkar, Mayank Sengupta, Nirmit Desai Published: 2026-10-07Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-10-07 | cs.LG | ai-safety, cslg, preprint | E9 / R8 (93%) | - |
| Logarithmic Regret via Passive Change Detection in Piecewise-Stationary Self-Tuning Regulation A. Ch. Madhusudanarao, Rahul Singh Published: 2026-10-07Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-10-07 | cs.LG | ai-safety, cslg, preprint | E6 / R5 (92%) | - |
| MemoWM: How World Models Change What Agents Need to Remember Bingfan Zeng, Chenbo Sang, Jingwei Song, Jinpeng Wang Published: 2026-10-07Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-10-07 | cs.LG | ai-safety, cslg, preprint | E9 / R8 (94%) | - |
| MORA: Modeling Observed Changes for Drift-Robust Time-Series Anomaly Detection Hui Wang, Pin Liu, Renyu Yang, Rui Wang Published: 2026-10-07Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-10-07 | cs.LG | ai-safety, cslg, preprint | E10 / R8 (94%) | - |