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 |
|---|---|---|---|---|---|
| Ramp Metering Control via Hybrid State Deep Reinforcement Learning in Partially Observable Connected Vehicle Environments Meriem Bouali, Nadir Farhi, Youcef Mehamlia Published: 2026-10-05Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-10-05 | cs.LG | ai-safety, cslg, preprint | - | - |
| RELACE: retrospective likelihood-based action credit estimation for long-horizon language agents Sathish Reddy Indurthi, Sayak Chakrabarti Published: 2026-10-05Area: cs.LGCitations: 15 Tags: ai-safety, cslg, preprint | 2026-10-05 | cs.LG | ai-safety, cslg, preprint | E10 / R9 (94%) | 15 |
| Scale-Invariant Training for Time Series Foundation Models Artur Dubrawski, Ignacy Stepka, Kin G. Olivares, Willa Potosnak Published: 2026-10-05Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-10-05 | cs.LG | ai-safety, cslg, preprint | E10 / R6 (91%) | - |
| Scaling Down the Scaling Laws: Parameter Efficiency and Compute-Optimal Training in Resource-Constrained Large Language Models Joe Dwyer Published: 2026-10-05Area: cs.LGCitations: 15 Tags: ai-safety, cslg, preprint | 2026-10-05 | cs.LG | ai-safety, cslg, preprint | E13 / R9 (91%) | 15 |
| Scaling Down the Scaling Laws: Parameter Efficiency and Compute-Optimal Training in Resource-Constrained Large Language Models Joe Dwyer Published: 2026-10-05Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-10-05 | cs.LG | ai-safety, cslg, preprint | - | - |
| SchemaFill: Efficient LLM Tool Calling via Slot-Parallel Speculative Decoding De-Chuan Zhan, Han-Jia Ye, Song-Yan Li, Zhi-Kai Chen Published: 2026-10-05Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-10-05 | cs.LG | ai-safety, cslg, preprint | E7 / R6 (90%) | - |
| Selecting Long-Horizon Trajectories for Reliable and Efficient Terminal-Agent Training Cuong Dang, Hoang Anh Just, Ruoxi Jia Published: 2026-10-05Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-10-05 | cs.LG | ai-safety, cslg, preprint | - | - |
| Selective Critique for Cost-Aware LLM Agents in Long-Horizon Decision Making Heewon Park, Minhae Kwon, Somin Im Published: 2026-10-05Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-10-05 | cs.LG | ai-safety, cslg, preprint | E10 / R8 (92%) | - |
| Sharpen Without Search: On-Policy Distillation of Sequence-Level Power Distribution Arya Fayyazi, Erfan Baghaei Potraghloo, Massoud Pedram, Mehdi Kamal Published: 2026-10-05Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-10-05 | cs.LG | ai-safety, cslg, preprint | - | - |
| SO(3)-RoPE for Spherical Transformers Alexander S. Ecker, Chase van de Geijn, Christian Libner, Maurice Weiler Published: 2026-10-05Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-10-05 | cs.LG | ai-safety, cslg, preprint | - | - |
| Square-Root Regret for Adversarial Multiplayer Bandits without Collision Information or Shared Randomness Chenyu Gan Published: 2026-10-05Area: cs.LGCitations: 19 Tags: adversarial-robustness, ai-safety, cslg, preprint | 2026-10-05 | cs.LG | adversarial-robustness, ai-safety, cslg, preprint | E8 / R6 (96%) | 19 |
| Steering by Influence: Curvature Aware Data Weighting for Activation Steering Francesco Quinzan, James A. E. Dixon, Stephen J. Roberts Published: 2026-10-05Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-10-05 | cs.LG | ai-safety, cslg, preprint | - | - |
| Stepped MoE: Segment-Level Routing with Configurable Inference Complexity Arnav Kundu, Bairu Hou, Chang Gao, Reed Li Published: 2026-10-05Area: cs.LGCitations: 15 Tags: ai-safety, cslg, preprint | 2026-10-05 | cs.LG | ai-safety, cslg, preprint | E11 / R11 (92%) | 15 |
| Structure, Not Belief: Correlated Thompson Sampling from LLM-Derived Covariance in Combinatorial Semi-Bandits Anany Kotawala, Anish Kataria, Vikram Kakaria Published: 2026-10-05Area: cs.LGCitations: 14 Tags: ai-safety, cslg, preprint | 2026-10-05 | cs.LG | ai-safety, cslg, preprint | E8 / R7 (91%) | 14 |
| ThunderSyncRL: Lossless Acceleration of Agentic Reinforcement Learning Azalia Mirhoseini, Hangoo Kang, Seil Kang, Seong Jae Hwang Published: 2026-10-05Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-10-05 | cs.LG | ai-safety, cslg, preprint | - | - |
| Transfer-Stratified On-Policy Distillation for RL-Improved Reasoning Teachers Bintao Wu, Bo Shao, Fengge Wu, Feng Sun Published: 2026-10-05Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-10-05 | cs.LG | ai-safety, cslg, preprint | - | - |
| TRIAGE: Direction-Aware Mismatch Stabilization of Native NVFP4 Reinforcement Learning Congkai Xie, Hongxia Yang, Junjie Lai, Mingfa Feng Published: 2026-10-05Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-10-05 | cs.LG | ai-safety, cslg, preprint | E11 / R7 (90%) | - |
| When Are Concept Bottleneck Model Explanations Faithful and Compact? Antonio Vergari, Emanuele Marconato, Stefano Teso, Steve Azzolin Published: 2026-10-05Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-10-05 | cs.LG | ai-safety, cslg, preprint | - | - |
| Who Bears the Burden? Learning Responsibility for Shared Constraints in Multi-Agent Reinforcement Learning Alexandre M. Bayen, Jingqi Li, Xiaoyang Cao, Zhe Fu Published: 2026-10-05Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-10-05 | cs.LG | ai-safety, cslg, preprint | E11 / R11 (94%) | - |
| Will the Judge Flip? Predicting Position-Sensitive LLM Judgments from Residual Stream Activations Alex Doboli, Gnaneswar Villuri, Hashmath Shaik Published: 2026-10-05Area: cs.LGCitations: 12 Tags: ai-safety, cslg, preprint | 2026-10-05 | cs.LG | ai-safety, cslg, preprint | E10 / R6 (98%) | 12 |
| A Graph-Based Inspection and Intervention Tool for Assessing Mechanistic Learning in PINNs Abhijeet Salunke, Adwait Patkhedkar, Alifaraz Lakhani, Prathmesh Mohite Published: 2026-10-04Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-10-04 | cs.LG | ai-safety, cslg, preprint | - | - |
| An LLM-in-the-loop RL Framework for Bioinformatics Feature Selection Deepti Agrawal, Xinyuan Wang, Yanjie Fu Published: 2026-10-04Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-10-04 | cs.LG | ai-safety, cslg, preprint | - | - |
| Bayesian Entropy-based Reordering for Calibrated Diffusion Language Models Mijung Park, Zhejun Jiang Published: 2026-10-04Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-10-04 | cs.LG | ai-safety, cslg, preprint | - | - |
| BeliefGraph-JEPA: Structured Latent World Models for Action-Conditioned Time Series Kangqi Ni, Tianlong Chen, Yue Li, Zhen Tan Published: 2026-10-04Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-10-04 | cs.LG | ai-safety, cslg, preprint | - | - |
| Best-of-$N$ Guidance for Test-time Diffusion Alignment Gyuwon Sim, Il-chul Moon, Minsang Park, Richard Lee Kim Published: 2026-10-04Area: cs.LGCitations: - Tags: ai-safety, alignment-training, cslg, preprint | 2026-10-04 | cs.LG | ai-safety, alignment-training, cslg, preprint | - | - |
| Best-of-$N$ Guidance for Test-time Diffusion Alignment Gyuwon Sim, Il-chul Moon, Minsang Park, Richard Lee Kim Published: 2026-10-04Area: cs.LGCitations: - Tags: ai-safety, alignment-training, cslg, preprint | 2026-10-04 | cs.LG | ai-safety, alignment-training, cslg, preprint | E8 / R8 (92%) | - |
| Cross-Modal Contrastive Learning for the Retrieval of Immunotherapy-Associated Molecular Signatures from Histopathology Felip Vilardell, Mar Teixid贸, Miquel Pi帽ol, Robert Montal Published: 2026-10-04Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-10-04 | cs.LG | ai-safety, cslg, preprint | - | - |
| Cut Binary Cross Entropy: Efficient Large-Vocabulary Loss and Gradient Kernels for Sequential Recommendation Haowen Ning, Mohamed Hammad, Yaoyiran Li Published: 2026-10-04Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-10-04 | cs.LG | ai-safety, cslg, preprint | - | - |
| DART-ES: Difficulty-Aware Reweighting and Targeted Replay for Fine-Tuning LLMs with Evolution Strategies Guang Dai, Haishan Ye, Hongzhan Wang, Sizhe Dang Published: 2026-10-04Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-10-04 | cs.LG | ai-safety, cslg, preprint | E7 / R6 (92%) | - |
| D-DOIT: Training-free Adaptation of Discrete Diffusion via Doob's h-Transform Han Liu, Jieke Wu, Minshuo Chen, Qijie Zhu Published: 2026-10-04Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-10-04 | cs.LG | ai-safety, cslg, preprint | - | - |