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 |
|---|---|---|---|---|---|
| scTrilemma: Balancing Identity, Invariance, and Fidelity in Single-Cell Representation Learning Chanyoung Park, Hyomin Kim, Jaechang Lim, Junseok Lee Published: 2026-09-30Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-30 | cs.LG | ai-safety, cslg, preprint | E11 / R10 (90%) | - |
| Semifactual Credit-Augmented Policy Optimization Junshu Pan, Qiaosheng Zhang, Shulin Huang, Wenqi Shao Published: 2026-09-30Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-30 | cs.LG | ai-safety, cslg, preprint | - | - |
| SHARPO: Segment-Level Credit Assignment for Agentic Reinforcement Learning Alborz Geramifard, Han Yu, Rohit Jain, Sen Na Published: 2026-09-30Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-30 | cs.LG | ai-safety, cslg, preprint | E9 / R9 (93%) | - |
| SHARPO: Segment-Level Credit Assignment for Agentic Reinforcement Learning Alborz Geramifard, Han Yu, Rohit Jain, Sen Na Published: 2026-09-30Area: cs.LGCitations: 15 Tags: ai-safety, cslg, preprint | 2026-09-30 | cs.LG | ai-safety, cslg, preprint | E12 / R11 (92%) | 15 |
| Signal-Routed Temperature Scaling: Low-Capacity Risk-Conditioned Calibration for Small Validation Budgets Liangwei Nathan Zheng, Lin Yue, Mingyu Guo, Olaf Maennel Published: 2026-09-30Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-30 | cs.LG | ai-safety, cslg, preprint | - | - |
| Structure-aware Reinforcement Learning for Protein Directed Evolution Siqi Fan, Suyuan Zhao, Yizhen Luo, Zaiqing Nie Published: 2026-09-30Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-30 | cs.LG | ai-safety, cslg, preprint | - | - |
| Switching Linear Attention E. Kelly Buchanan, Emily B. Fox, Hyun Dong Lee, Nicolas Zucchet Published: 2026-09-30Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-30 | cs.LG | ai-safety, cslg, preprint | - | - |
| T2SPO: Trajectory-to-Step Policy Optimization for Agentic Reinforcement Learning Bo-Wen Zhang, Feiran Li, Junwei He, Lan-Zhe Guo Published: 2026-09-30Area: cs.LGCitations: 15 Tags: ai-safety, cslg, preprint | 2026-09-30 | cs.LG | ai-safety, cslg, preprint | E11 / R6 (92%) | 15 |
| The Life Cycle of a Massive Activation: Stochastic Birth, Weight-Decay-Driven Growth, and Competitive Consolidation Antonios Saravanos, Jorge Gallego-Feliciano, S. Aaron McClendon Published: 2026-09-30Area: cs.LGCitations: 45 Tags: ai-safety, cslg, preprint | 2026-09-30 | cs.LG | ai-safety, cslg, preprint | E7 / R5 (92%) | 45 |
| The Life Cycle of a Massive Activation: Stochastic Birth, Weight-Decay-Driven Growth, and Competitive Consolidation Antonios Saravanos, Jorge Gallego-Feliciano, S. Aaron McClendon Published: 2026-09-30Area: cs.LGCitations: 12 Tags: ai-safety, cslg, preprint | 2026-09-30 | cs.LG | ai-safety, cslg, preprint | E8 / R5 (94%) | 12 |
| TRACE: Trajectory Selection for Parallel Scaling of Search Agents Qiaoyu Tan, Qisheng Zhou, Zhen Xiong Published: 2026-09-30Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-30 | cs.LG | ai-safety, cslg, preprint | - | - |
| Training-Aware Target Coverage for Synthetic Data Selection Michelle V. Mancenido, Rong Pan, Yang Ba Published: 2026-09-30Area: cs.LGCitations: 15 Tags: ai-safety, cslg, preprint | 2026-09-30 | cs.LG | ai-safety, cslg, preprint | E5 / R6 (91%) | 15 |
| T-Router: Learning Thalamic Routing for Reasoning with Parameter-Efficient Reinforcement Learning Jiale Dai, Jiaqi Li, Liuxian Ma, Lu Mi Published: 2026-09-30Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-30 | cs.LG | ai-safety, cslg, preprint | - | - |
| Trust the Critic More Arvind Mahankali, Kaiyue Wen, Luke Bailey, Tengyu Ma Published: 2026-09-30Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-30 | cs.LG | ai-safety, cslg, preprint | - | - |
| Trust the Critic More Arvind Mahankali, Kaiyue Wen, Luke Bailey, Tengyu Ma Published: 2026-09-30Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-30 | cs.LG | ai-safety, cslg, preprint | E7 / R5 (92%) | - |
| Unlearning Deceptive Behaviors in LLMs with Contrastive Forget Sets Haoran Tang, Rajiv Khanna Published: 2026-09-30Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-30 | cs.LG | ai-safety, cslg, preprint | E8 / R6 (92%) | - |
| Unmerge: Efficient Machine Unlearning via Task Arithmetic Andrew Tan, Haoran Tang, Rajiv Khanna Published: 2026-09-30Area: cs.LGCitations: 15 Tags: ai-safety, cslg, preprint | 2026-09-30 | cs.LG | ai-safety, cslg, preprint | E12 / R8 (92%) | 15 |
| Wavelet Flow Matching for Time Series Jorge da Silva Goncalves, Julia E. Vogt, Lucas Poinsignon, Samuel Ruiperez-Campillo Published: 2026-09-30Area: cs.LGCitations: 15 Tags: ai-safety, cslg, preprint | 2026-09-30 | cs.LG | ai-safety, cslg, preprint | E8 / R6 (92%) | 15 |
| Wavelet Flow Matching for Time Series Jorge da Silva Gon莽alves, Julia E. Vogt, Lucas Poinsignon, Samuel Ruip茅rez-Campillo Published: 2026-09-30Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-30 | cs.LG | ai-safety, cslg, preprint | - | - |
| What Limits Recursive Reasoning Models: Optimization, Architecture and Test-Time Scaling Dmitrii Kharchev, Dmitry Bocharov, Inessa Fedorova, Ivan Oseledets Published: 2026-09-30Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-30 | cs.LG | ai-safety, cslg, preprint | - | - |
| What Streaming Anomaly Detection Finds (and Misses) in Industrial Time Series 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 | - | - |
| WinoTS: Wavelet-based Self-Distillation for Time Series Models Kathy Razmadze, Noam Major, Yoli Shavit Published: 2026-09-30Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-30 | cs.LG | ai-safety, cslg, preprint | - | - |
| XOR-Trellis: Ultra-Low-Complexity Dequantization and Curvature-Aware Hadamard-Free LLM Quantization Dibakar Gope, Nir Elkayam, Shuokai Pan, Spandan Pyakurel Published: 2026-09-30Area: cs.LGCitations: 12 Tags: ai-safety, cslg, preprint | 2026-09-30 | cs.LG | ai-safety, cslg, preprint | E8 / R6 (94%) | 12 |
| $S^3$: Spectral Null-Space Swap Makes Reasoning Models Efficient Bangji Yang, Ge Liu, Hongbo Ma, Jiajun Fan Published: 2026-09-29Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-29 | cs.LG | ai-safety, cslg, preprint | - | - |
| Abductive World Modeling via Causal Representation Learning Jiatong Liu, Lijun Peng, Linfan Zhou, Long Wan Published: 2026-09-29Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-29 | cs.LG | ai-safety, cslg, preprint | - | - |
| A Comprehensive View of Fairness through Distributional Stability Charlotte Laclau, Gayane Taturyan, Stephan Cl茅mencon Published: 2026-09-29Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-29 | cs.LG | ai-safety, cslg, preprint | - | - |
| Adapting Context Compression for Long-Horizon Agents with Counterfactual Continuations Chen Chen, Guanghui Min, Liangjie Hong, Liang Wu Published: 2026-09-29Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-29 | cs.LG | ai-safety, cslg, preprint | - | - |
| Alignment via Training Against Probes Without Losing Monitorability Alexander Panfilov, Ben Rank, Jonas Geiping, Lena Libon Published: 2026-09-29Area: cs.LGCitations: - Tags: ai-safety, alignment-training, cslg, preprint | 2026-09-29 | cs.LG | ai-safety, alignment-training, cslg, preprint | E20 / R13 (89%) | - |
| Alignment via Training Against Probes Without Losing Monitorability Alexander Panfilov, Ben Rank, Jonas Geiping, Lena Libon Published: 2026-09-29Area: cs.LGCitations: 45 Tags: ai-safety, alignment-training, cslg, preprint | 2026-09-29 | cs.LG | ai-safety, alignment-training, cslg, preprint | E14 / R11 (92%) | 45 |
| A Sharp Transition in Data Reconstruction under Differential Privacy Marco Mondelli, Max Cairney-Leeming, Simone Bombari Published: 2026-09-29Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-29 | cs.LG | ai-safety, cslg, preprint | - | - |