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 |
|---|---|---|---|---|---|
| Hypergradient-based Bilevel Reinforcement Learning with Improved Sample Complexity Mudit Gaur, Naman Saxena, Vaneet Aggarwal Published: 2026-07-30Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-07-30 | cs.LG | ai-safety, cslg, preprint | E10 / R8 (94%) | - |
| Information Bottleneck Learning for Faithful Time Series Forecasting Explanations Dongsheng Luo, Jingchao Ni, Mo Sha, Wei Cheng Published: 2026-07-30Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-07-30 | cs.LG | ai-safety, cslg, preprint | E9 / R6 (87%) | - |
| LoRA Scaffolded Policy Optimization (LSPO): A Sampling-Time Low-Rank Scaffold for Recovering Reinforcement-Learning Gradient on Zero-Reward Cliff Prompts Ken Ding Published: 2026-07-30Area: cs.LGCitations: 15 Tags: ai-safety, cslg, preprint | 2026-07-30 | cs.LG | ai-safety, cslg, preprint | E9 / R6 (94%) | 15 |
| On-Policy and Off-Policy Learning for Large Action Spaces Imad Aouali Published: 2026-07-30Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-07-30 | cs.LG | ai-safety, cslg, preprint | E11 / R9 (94%) | - |
| Persistent Gaussian Perturbations Prevent Oversmoothing in Recurrent Graph Neural Networks Mostafa Haghir Chehreghani Published: 2026-07-30Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-07-30 | cs.LG | ai-safety, cslg, preprint | E8 / R6 (94%) | - |
| Policy Gradient Steering: Interventions from Behavioral Objectives Aur茅lie Beynier, Nicolas Maudet, Yoann Poupart Published: 2026-07-30Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-07-30 | cs.LG | ai-safety, cslg, preprint | E12 / R9 (91%) | - |
| Predicting Steel Fatigue Life from Micrographs Using Physics-Informed Deep Learning Aryuemaan Kumar Chowdhury Published: 2026-07-30Area: cs.LGCitations: 19 Tags: ai-safety, cslg, preprint | 2026-07-30 | cs.LG | ai-safety, cslg, preprint | E9 / R8 (92%) | 19 |
| QQWorld: Quantile-Quantile Matching for World Model Regularization Xiangyu Xu, Xiaoyu Hu, Zhoushun Yu Published: 2026-07-30Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-07-30 | cs.LG | ai-safety, cslg, preprint | E10 / R10 (90%) | - |
| ROCS: Request-Oriented Compute Sharing for Efficient Large-Scale Recommendation Ao Cai, Bin Yu, Birmingham Guan, Boda Li Published: 2026-07-30Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-07-30 | cs.LG | ai-safety, cslg, preprint | E7 / R6 (94%) | - |
| Search Strategies for Optimal Classification and Regression Trees Emir Demirovi膰, Jacobus G. M. van der Linden, Mim van den Bos Published: 2026-07-30Area: cs.LGCitations: 15 Tags: ai-safety, cslg, preprint | 2026-07-30 | cs.LG | ai-safety, cslg, preprint | E10 / R7 (90%) | 15 |
| SEDR-Seq2P: A Lightweight Dilated Residual Sequence-to-Point Network for Multi-Task Industrial NILM Feres Jerbi, Hatem Haddad, Issam Smaali Published: 2026-07-30Area: cs.LGCitations: 22 Tags: ai-safety, cslg, preprint | 2026-07-30 | cs.LG | ai-safety, cslg, preprint | E13 / R7 (94%) | 22 |
| TAPO: Transition-Aware Policy Optimization for LLM Agents Cong Li, Peixi Peng, Shudong Liu, Xinyu Hu Published: 2026-07-30Area: cs.LGCitations: 45 Tags: ai-safety, cslg, preprint | 2026-07-30 | cs.LG | ai-safety, cslg, preprint | E9 / R7 (93%) | 45 |
| Technological Advances in Detecting and Managing Cognitive Impairment in Older Adults: Trends, Challenges, and Future Directions Anurag Rajkumar Bombarde, Azizuddin Khan, Mohammad Asif, Mohd Azam Published: 2026-07-30Area: cs.LGCitations: 72 Tags: ai-safety, cslg, preprint | 2026-07-30 | cs.LG | ai-safety, cslg, preprint | E19 / R14 (92%) | 72 |
| Towards joint scaling laws with optimal batch size schedules Jiaxiang Li, Shiyun Xu, Zhiqi Bu Published: 2026-07-30Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-07-30 | cs.LG | ai-safety, cslg, preprint | E9 / R6 (95%) | - |
| Train Small, Deploy Large: Zero-Shot GNN Transfer Through Geometric Renormalization M. 脕ngeles Serrano, Mari谩n Bogu帽谩, Melanie Weber, Pedro Almagro-Blanco Published: 2026-07-30Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-07-30 | cs.LG | ai-safety, cslg, preprint | E13 / R11 (90%) | - |
| Understanding Submodular Information Measure Based Objectives for Representation Learning: A Variance and Separation Perspective Anay Majee, Rishabh Iyer, Truong Pham Published: 2026-07-30Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-07-30 | cs.LG | ai-safety, cslg, preprint | E12 / R7 (93%) | - |
| Actions Have Consequences: Detecting Outcome Performativity using Intervention Testing Brandon Gower-Winter, Georg Krempl Published: 2026-07-29Area: cs.LGCitations: 21 Tags: ai-safety, cslg, preprint | 2026-07-29 | cs.LG | ai-safety, cslg, preprint | E10 / R9 (93%) | 21 |
| AgentGFM: A Graph Foundation Model with Node-Agent Information-Flow Control Di Jin, Dongxiao He, Jingbo Cui, Jitao Zhao Published: 2026-07-29Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-07-29 | cs.LG | ai-safety, cslg, preprint | E8 / R6 (90%) | - |
| BayesAME: Bayesian Active Model Evaluation Arnaud Doucet, Paula Cordero Encinar, Silvia Chiappa, Taylan Cemgil Published: 2026-07-29Area: cs.LGCitations: 15 Tags: ai-safety, cslg, preprint, safety-evaluation | 2026-07-29 | cs.LG | ai-safety, cslg, preprint, safety-evaluation | E8 / R6 (91%) | 15 |
| Benchmarking the Residual: What Long-Horizon Evaluations Add Beyond Matched Short-Task Performance Chao Peng, Hande Dong, Peijie Dong, Qiang Lin Published: 2026-07-29Area: cs.LGCitations: 25 Tags: ai-safety, cslg, preprint, safety-evaluation | 2026-07-29 | cs.LG | ai-safety, cslg, preprint, safety-evaluation | E7 / R6 (90%) | 25 |
| Budget-Aware LLM Discovery via Cost-Calibrated Frontier Utility Chen Ma, Jiamin Chen, Kai Xie, Tianyu Liu Published: 2026-07-29Area: cs.LGCitations: 45 Tags: ai-safety, cslg, preprint | 2026-07-29 | cs.LG | ai-safety, cslg, preprint | E9 / R7 (92%) | 45 |
| Budget-Aware LLM Discovery via Cost-Calibrated Frontier Utility Chen Ma, Jiamin Chen, Kai Xie, Tianyu Liu Published: 2026-07-29Area: cs.LGCitations: 15 Tags: ai-safety, cslg, preprint | 2026-07-29 | cs.LG | ai-safety, cslg, preprint | E7 / R6 (90%) | 15 |
| CoCaRS: Correlation Calibration-Based Redundancy Suppression for Heterogeneous Knowledge Distillation Baoying Ma, Chunling Chen, Fengming Yu, Haiwei Pan Published: 2026-07-29Area: cs.LGCitations: 15 Tags: ai-safety, cslg, preprint | 2026-07-29 | cs.LG | ai-safety, cslg, preprint | E18 / R14 (90%) | 15 |
| Collaborative Weighting with Pessimistic Critic for Mitigating Overestimation in Off-Policy Reinforcement Learning Gong Gao, Guojie Chen, Weidong Zhao, Xianhui Liu Published: 2026-07-29Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-07-29 | cs.LG | ai-safety, cslg, preprint | E12 / R10 (92%) | - |
| Cost-Sensitive Conformal Prediction and Human-in-the-Loop Abstention for Imbalanced High-Stakes Decision Support: A Multi-Domain Benchmark Akshatha Srikantha, Manpreet Singh, Shyamal Lakhanpal Published: 2026-07-29Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-07-29 | cs.LG | ai-safety, cslg, preprint | - | - |
| ECG-InterpBench: Benchmarking the Interpretability of ECG Foundation Models with Matched-Scale Sparse Autoencoders Wei Qiu, Yixuan Duan Published: 2026-07-29Area: cs.LGCitations: - Tags: ai-safety, cslg, interpretability, preprint | 2026-07-29 | cs.LG | ai-safety, cslg, interpretability, preprint | E13 / R12 (91%) | - |
| Efficient Heteroscedastic Bayesian Optimization for Risk-Aware AutoRL Alexander von Rohr, Marius Lindauer, Mingxuan Che, Theresa Eimer Published: 2026-07-29Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-07-29 | cs.LG | ai-safety, cslg, preprint | E10 / R8 (92%) | - |
| Expanding Data-Agnostic Pivotal Instances Selection Models with Proximity Trees and Ensemble Learning Alessio Cascione, Cristiano Landi, Mattia Setzu, Paolo Maria Mancarella Published: 2026-07-29Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-07-29 | cs.LG | ai-safety, cslg, preprint | E10 / R8 (94%) | - |
| Explorative Modeling: Unlocking a Third Pretraining Axis and End-to-End Generation Alexi Gladstone, Heng Ji, Yilun Du Published: 2026-07-29Area: cs.LGCitations: 102 Tags: ai-safety, cslg, preprint | 2026-07-29 | cs.LG | ai-safety, cslg, preprint | E8 / R5 (91%) | 102 |
| FedTopo: Relation-Level Topology Sharing for Model-Heterogeneous Federated Learning Jing Wang, Lipo Wang, Xin Gao, Youfang Lin Published: 2026-07-29Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-07-29 | cs.LG | ai-safety, cslg, preprint | E11 / R9 (90%) | - |