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 |
|---|---|---|---|---|---|
| Transformers converge to invariant algorithmic cores Joshua S. Schiffman Published: 2026-02-26Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-02-26 | cs.LG | ai-safety, cslg, preprint | E12 / R13 (92%) | - |
| Adaptive Correlation-Weighted Intrinsic Rewards for Reinforcement Learning Phuong Thai Nguyen, Viet Bac Nguyen Published: 2026-02-27Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-02-27 | cs.LG | ai-safety, cslg, preprint | E6 / R6 (93%) | - |
| An Efficient Unsupervised Federated Learning Approach for Anomaly Detection in Heterogeneous IoT Networks Atena Shiranzaei, Mahdi Rabbani, Mahtab Jamali, Mohsen Tajgardan Published: 2026-02-27Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-02-27 | cs.LG | ai-safety, cslg, preprint | E15 / R10 (95%) | - |
| Beyond State-Wise Mirror Descent: Offline Policy Optimization with Parametric Policies Nan Jiang, Xiang Li, Yuheng Zhang Published: 2026-02-27Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-02-27 | cs.LG | ai-safety, cslg, preprint | E8 / R6 (88%) | - |
| Bridging Dynamics Gaps via Diffusion Schr枚dinger Bridge for Cross-Domain Reinforcement Learning Hanping Zhang, Yuhong Guo Published: 2026-02-27Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-02-27 | cs.LG | ai-safety, cslg, preprint | E6 / R5 (94%) | - |
| Brittlebench: Quantifying LLM robustness via prompt sensitivity Adina Williams, Anaelia Ovalle, Angelika Romanou, Antoine Bosselut Published: 2026-02-27Area: cs.LGCitations: 150 Tags: ai-safety, cslg, preprint | 2026-02-27 | cs.LG | ai-safety, cslg, preprint | E17 / R16 (94%) | 150 |
| CAMEL-CLIP: Channel-aware Multimodal Electroencephalography-text Alignment for Generalizable Brain Foundation Models Hanseul Choi, Jibum Kim, Jinyeong Park, Seongwon Jin Published: 2026-02-27Area: cs.LGCitations: 45 Tags: ai-safety, alignment-training, cslg, preprint | 2026-02-27 | cs.LG | ai-safety, alignment-training, cslg, preprint | E12 / R9 (92%) | 45 |
| Causal Mechanism Reduction: Mechanism Replacement for Neural Network Pruning and Abstraction Amir Asiaee Published: 2026-02-27Area: cs.LGCitations: 40 Tags: ai-safety, cslg, preprint | 2026-02-27 | cs.LG | ai-safety, cslg, preprint | E9 / R8 (91%) | 40 |
| CUDA Agent: Large-Scale Agentic RL for High-Performance CUDA Kernel Generation Chengquan Jiang, Hanlin Wu, Hao Zhou, Hongli Yu Published: 2026-02-27Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-02-27 | cs.LG | ai-safety, cslg, preprint | E8 / R7 (91%) | - |
| Demand Acceptance using Reinforcement Learning for Dynamic Vehicle Routing Problem with Emission Quota Dominique Barth, Farid Najar, Yann Strozecki Published: 2026-02-27Area: cs.LGCitations: 25 Tags: ai-safety, cslg, preprint | 2026-02-27 | cs.LG | ai-safety, cslg, preprint | E7 / R6 (92%) | 25 |
| Dynamics of Learning under User Choice: Overspecialization and Peer-Model Probing Adhyyan Narang, Lillian J Ratliff, Maryam Fazel, Sarah Dean Published: 2026-02-27Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-02-27 | cs.LG | ai-safety, cslg, preprint | E12 / R11 (95%) | - |
| FastODT: A tree-based framework for efficient continual learning Daniel Bretsko, Devashish Khulbe, Piotr Walas, Sebastian Stros Published: 2026-02-27Area: cs.LGCitations: 21 Tags: ai-safety, cslg, preprint | 2026-02-27 | cs.LG | ai-safety, cslg, preprint | E8 / R7 (93%) | 21 |
| FedNSAM:Consistency of Local and Global Flatness for Federated Learning Fanhua Shang, Hongying Liu, Junkang Liu, Yuanyuan Liu Published: 2026-02-27Area: cs.LGCitations: 15 Tags: ai-safety, cslg, preprint | 2026-02-27 | cs.LG | ai-safety, cslg, preprint | E11 / R6 (92%) | 15 |
| FedRot-LoRA: Mitigating Rotational Misalignment in Federated LoRA Dongjun Kim, Haoran Zhang, Haris Vikalo, Seohyeon Cha Published: 2026-02-27Area: cs.LGCitations: 15 Tags: ai-safety, alignment-training, cslg, preprint | 2026-02-27 | cs.LG | ai-safety, alignment-training, cslg, preprint | E13 / R8 (88%) | 15 |
| FedTreeLoRA: Reconciling Statistical and Functional Heterogeneity in Federated LoRA Fine-Tuning Jieming Bian, Jie Xu, Lei Wang, Letian Zhang Published: 2026-02-27Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-02-27 | cs.LG | ai-safety, cslg, preprint | E10 / R6 (88%) | - |
| FlexGuard: Continuous Risk Scoring for Strictness-Adaptive LLM Content Moderation Jieming Shi, Jinming Li, Ze Lu, Zhihao Ding Published: 2026-02-27Area: cs.LGCitations: 45 Tags: ai-safety, cslg, preprint | 2026-02-27 | cs.LG | ai-safety, cslg, preprint | E8 / R6 (90%) | 45 |
| Flowette: Flow Matching with Graphette Priors for Graph Generation Asiri Wijesinghe, Cheng Soon Ong, Daniel M. Steinberg, Sevvandi Kandanaarachchi Published: 2026-02-27Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-02-27 | cs.LG | ai-safety, cslg, preprint | E6 / R5 (90%) | - |
| Foundation World Models for Agents that Learn, Verify, and Adapt Reliably Beyond Static Environments Florent Delgrange Published: 2026-02-27Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-02-27 | cs.LG | ai-safety, cslg, preprint | E8 / R7 (93%) | - |
| Hierarchical Concept-based Interpretable Models Mateja Jamnik, Mateo Espinosa Zarlenga, Oscar Hill Published: 2026-02-27Area: cs.LGCitations: 15 Tags: ai-safety, cslg, preprint | 2026-02-27 | cs.LG | ai-safety, cslg, preprint | E9 / R8 (95%) | 15 |
| HURRI-GAN: A Novel Approach for Hurricane Bias-Correction Beyond Gauge Stations using Generative Adversarial Networks Carola Kaiser, Clint Dawson, Hadi Majed, Hartmut Kaiser Published: 2026-02-27Area: cs.LGCitations: - Tags: adversarial-robustness, ai-safety, cslg, preprint | 2026-02-27 | cs.LG | adversarial-robustness, ai-safety, cslg, preprint | E8 / R6 (91%) | - |
| ICaRus: Identical Cache Reuse for Efficient Multi Model Inference Ahreum Seo, Baeseong Park, Dongsoo Lee, Hoseung Kim Published: 2026-02-27Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-02-27 | cs.LG | ai-safety, cslg, preprint | E10 / R10 (90%) | - |
| Intrinsic Lorentz Neural Network Nicu Sebe, Xianglong Shi, Yunhan Jiang, Ziheng Chen Published: 2026-02-27Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-02-27 | cs.LG | ai-safety, cslg, preprint | E10 / R9 (90%) | - |
| Learning from Partial Chain-of-Thought via Truncated-Reasoning Self-Distillation Edoardo Cetin, Gianluigi Silvestri Published: 2026-02-27Area: cs.LGCitations: 15 Tags: ai-safety, cslg, preprint | 2026-02-27 | cs.LG | ai-safety, cslg, preprint | E7 / R7 (93%) | 15 |
| Learning Retrieval Models with Sparse Autoencoders Herv茅 Dejean, Maxime Louis, St茅phane Clinchant, Thibault Formal Published: 2026-02-27Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-02-27 | cs.LG | ai-safety, cslg, preprint | E10 / R6 (91%) | - |
| Learning to maintain safety through expert demonstrations in settings with unknown constraints: A Q-learning perspective George A. Vouros, George Papadopoulos Published: 2026-02-27Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-02-27 | cs.LG | ai-safety, cslg, preprint | E8 / R5 (93%) | - |
| Memory Caching: RNNs with Growing Memory Ali Behrouz, Meisam Razaviyayn, Peilin Zhong, Vahab Mirrokni Published: 2026-02-27Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-02-27 | cs.LG | ai-safety, cslg, preprint | E12 / R10 (89%) | - |
| MINT: Multimodal Imaging-to-Speech Knowledge Transfer for Early Alzheimer's Screening Anouck Girard, M. A. Ganaie, Vrushank Ahire, Yogesh Kumar Published: 2026-02-27Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-02-27 | cs.LG | ai-safety, cslg, preprint | E9 / R7 (93%) | - |
| MPU: Towards Secure and Privacy-Preserving Knowledge Unlearning for Large Language Models Pengjun Xie, Tiantong Wang, Tiantong Wu, Wei Yang Bryan Lim Published: 2026-02-27Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-02-27 | cs.LG | ai-safety, cslg, preprint | E8 / R9 (91%) | - |
| On Emergences of Non-Classical Statistical Characteristics in Classical Neural Networks Hanyu Zhao, Yang Wu, Yuexian Hou Published: 2026-02-27Area: cs.LGCitations: 45 Tags: ai-safety, cslg, preprint | 2026-02-27 | cs.LG | ai-safety, cslg, preprint | E10 / R8 (92%) | 45 |
| Optimizer-Induced Low-Dimensional Drift and Transverse Dynamics in Transformer Training Yongzhong Xu Published: 2026-02-27Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-02-27 | cs.LG | ai-safety, cslg, preprint | E6 / R5 (92%) | - |