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 |
|---|---|---|---|---|---|
| AutoLoCo: Communication Efficient Distributed LLM Training via Adaptive Synchronization Guangwen Yang, Pengyu He, Ruien Li, Yan Zhang Published: 2026-09-29Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-29 | cs.LG | ai-safety, cslg, preprint | - | - |
| Beam Search as Test-Time Self-Distillation via Counterfactual Contexts Haitham Bou-Ammar, Matthieu Zimmer, Rasul Tutunov, Su Ee Tan Published: 2026-09-29Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-29 | cs.LG | ai-safety, cslg, preprint | - | - |
| Beyond Compression: Diagnosing How Post-Training Changes Mathematical Reasoning Caesar Wu, Hongyang Li, Pascal Bouvry, Said Mammar Published: 2026-09-29Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-29 | cs.LG | ai-safety, cslg, preprint | - | - |
| Beyond Conditional Independence: Root Cause Analysis with Deep Causal Models Kenneth Lee, Md Musfiqur Rahman, Murat Kocaoglu, Padmaja Jonnalagedda Published: 2026-09-29Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-29 | cs.LG | ai-safety, cslg, preprint | - | - |
| Beyond Interaction Capacity: Estimator Scaling with Recursive Models for CTR Prediction Fotis Iliopoulos, Gaurav Menghani, Shivang Chopra, Zsolt Kira Published: 2026-09-29Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-29 | cs.LG | ai-safety, cslg, preprint | - | - |
| Challenges and Solutions for Bandits in the Wild: Warm-Started Mixture Bandits for Cross-Cohort Slate Recommendation Ali Arshad Sadal, Eyke H眉llermeier, Ilias Ek艧i, Jakob Karolus Published: 2026-09-29Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-29 | cs.LG | ai-safety, cslg, preprint | - | - |
| Channel-Dependent State Space Model for Multivariate Time Series Forecasting Duane S. Boning, Fan-Keng Sun, Li-Chun Lu, Yu-Cheng Wu Published: 2026-09-29Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-29 | cs.LG | ai-safety, cslg, preprint | - | - |
| Constitutional adapters: Inference-time interventions for misalignment and misuse Adam S. Lowet, Mark Kurzeja Published: 2026-09-29Area: cs.LGCitations: - Tags: ai-safety, alignment-training, cslg, preprint | 2026-09-29 | cs.LG | ai-safety, alignment-training, cslg, preprint | - | - |
| Differentiable Structure Learning for Cyclic Linear Gaussian Models with Latent Confounders Ali Najar, Negar Kiyavash, Saber Salehkaleybar, Sadegh Khorasani Published: 2026-09-29Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-29 | cs.LG | ai-safety, cslg, preprint | E7 / R7 (95%) | - |
| Diffusion Policy Improvement with Proposal-Conditioned Refinement Flows Byungwoo Park, Juho Lee, Junhyun Ha Published: 2026-09-29Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-29 | cs.LG | ai-safety, cslg, preprint | - | - |
| Diffusion Policy Improvement with Proposal-Conditioned Refinement Flows Byoungwoo Park, Juho Lee, Junhyun Ha Published: 2026-09-29Area: cs.LGCitations: 15 Tags: ai-safety, cslg, preprint | 2026-09-29 | cs.LG | ai-safety, cslg, preprint | E7 / R6 (91%) | 15 |
| Does Gradient Conflict Predict the Understanding--Generation Trade-off? A Controlled Audit of Conflict-Metric Validity in Unified Multimodal Models Fucheng Deng, Shuyang Jiang, Yuchuan Luo, Zhenyu Wu Published: 2026-09-29Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-29 | cs.LG | ai-safety, cslg, preprint | E9 / R5 (85%) | - |
| Does This Action Still Explain the Task? Reverse Scoring for Diffusion Language Model Agents Christopher E. Mower, Haitham Bou-Ammar, Jan Peters, Jiacheng Qiu Published: 2026-09-29Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-29 | cs.LG | ai-safety, cslg, preprint | E10 / R9 (93%) | - |
| Dr. OPD: Learning What to Follow for Optimal On-Policy Distillation of Large Language Models Linjun Zhang, Tianze Wang, Yifan Hu, Zhenyu Wang Published: 2026-09-29Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-29 | cs.LG | ai-safety, cslg, preprint | - | - |
| Factorized Scheduling Principle: Learning Interpretable and Transferable Policies via Structured Additive Functions Hong Je-Gal, Hyun-Suk Lee Published: 2026-09-29Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-29 | cs.LG | ai-safety, cslg, preprint | - | - |
| FlexRouter: Learning Complementary Model Sets for Flexible LLM Routing Andy Zhao, Franck Dernoncourt, Harry Yang, Hoda Eldardiry Published: 2026-09-29Area: cs.LGCitations: 15 Tags: ai-safety, cslg, preprint | 2026-09-29 | cs.LG | ai-safety, cslg, preprint | E8 / R6 (92%) | 15 |
| From Checkpoint Variation to Selection Gains in Supervised Fine-Tuning Wenxuan Zhang, Yuan Wu, Yupeng Chang Published: 2026-09-29Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-29 | cs.LG | ai-safety, cslg, preprint | - | - |
| GARDiff: Graph-Aligned Residual Diffusion for Probabilistic Multivariate Time-Series Forecasting Min Yang, Rui Han, Wei Liu, Xinghao Yang Published: 2026-09-29Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-29 | cs.LG | ai-safety, cslg, preprint | - | - |
| Group-Marginalized Self-Rewarding RL Drives Zero-Label Self-Evolving Qingyuan Tian, Rui Wang, Xingyu Chen, Yikang Liu Published: 2026-09-29Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-29 | cs.LG | ai-safety, cslg, preprint | - | - |
| Guard Models Are Overconfident Where Base Models Are Uncertain Jonghyun Hong, MinJae Jung, Minwoo Kim Published: 2026-09-29Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-29 | cs.LG | ai-safety, cslg, preprint | - | - |
| Hermes: Learning Contextual Reasoning Unlocks Test-Time Scaling Hao Liu, Langlin Huang, Mononito Goswami, Nikos Kanakaris Published: 2026-09-29Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-29 | cs.LG | ai-safety, cslg, preprint | E13 / R9 (93%) | - |
| Hidden Reasoning Must Leak, but Need Not Be Readable: Fundamental Opportunities and Limits for Chain-of-Thought Monitoring Madhava Krishna, Michael Hahn, Mohammadali Mohammadkhani, Yash Sarrof Published: 2026-09-29Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-29 | cs.LG | ai-safety, cslg, preprint | - | - |
| Hierarchical Compression of Vision-Language Model Benchmarks Hyunjong Ok, Jaeho Lee, Seunggu Kang Published: 2026-09-29Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-29 | cs.LG | ai-safety, cslg, preprint | - | - |
| HiTS-CL: A Continual Learning Framework for Long-Horizon Temporal Knowledge Graph Extrapolation Da Fu, Fuwei Zhang, Fuzhen Zhuang, Hongwei Zhao Published: 2026-09-29Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-29 | cs.LG | ai-safety, cslg, preprint | - | - |
| Identifying ODEs from Unstructured Data with Causal Representation Learning Alessandro Trenta, Davide Bacciu, Riccardo Massidda, Sara Magliacane Published: 2026-09-29Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-29 | cs.LG | ai-safety, cslg, preprint | - | - |
| Inducing Process Supervision from Outcome-Only Reinforcement Learning Haotian Chen, Shengda Fan, Xin Cong, Yankai Lin Published: 2026-09-29Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-29 | cs.LG | ai-safety, cslg, preprint | - | - |
| Interactive-Policy Distillation with Bidirectional Propose-and-Verify Anderson Schneider, Brendan Rappazzo, Daiheng Zhang, Jiawei Zhang Published: 2026-09-29Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-29 | cs.LG | ai-safety, cslg, preprint | - | - |
| Interpolated Policy Distillation: A Controllable Continuum Between Off-Policy and On-Policy Distillation Dacheng Yin, Dong Liu, Fengyun Rao, Guangting Wang Published: 2026-09-29Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-29 | cs.LG | ai-safety, cslg, preprint | - | - |
| Interpretable but Fragile? Robustness of Concept Bottlenecks under Geometric-Semantic Perturbations Gaojie Jin, Hanwei Zhang, Ronghui Mu, Tianma Hu Published: 2026-09-29Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-29 | cs.LG | ai-safety, cslg, preprint | E10 / R7 (95%) | - |
| Jaxolotl: A Unified High-Performance Benchmark Suite for LTL-Based Multi-Task RL Alessandro Abate, Jacques Cloete, Mathias Jackermeier Published: 2026-09-29Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-29 | cs.LG | ai-safety, cslg, preprint | - | - |