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 |
|---|---|---|---|---|---|
| Dropout Robustness and Cognitive Profiling of Transformer Models via Stochastic Inference Antônio Junior Alves Caiado, Michael Hahsler Published: 2026-03-18Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-03-18 | cs.LG | ai-safety, cslg, preprint | E5 / R3 (94%) | - |
| Efficient Exploration at Scale Benjamin Van Roy, Chris Chute, Mehdi Jafarnia, Seyed Mohammad Asghari Published: 2026-03-18Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-03-18 | cs.LG | ai-safety, cslg, preprint | E5 / R3 (95%) | - |
| Enactor: From Traffic Simulators to Surrogate World Models Anand Rangarajan, Rahul Sengupta, Sanjay Ranka, Yash Ranjan Published: 2026-03-18Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-03-18 | cs.LG | ai-safety, cslg, preprint | E5 / R3 (95%) | - |
| Enhancing Reinforcement Learning Fine-Tuning with an Online Refiner Hao Ma, Xiaolin Ai, Yang Liu, Zhiqiang Pu Published: 2026-03-18Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-03-18 | cs.LG | ai-safety, cslg, preprint | E6 / R3 (95%) | - |
| FoMo X: Modular Explainability Signals for Outlier Detection Foundation Models Emmanuel Müller, Phuong Huong Nguyen, Simon Klüttermann, Tim Katzke Published: 2026-03-18Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-03-18 | cs.LG | ai-safety, cslg, preprint | E6 / R4 (97%) | - |
| Gradient-Informed Temporal Sampling Improves Rollout Accuracy in PDE Surrogate Training Fan Zhang, Wenshuo Wang Published: 2026-03-18Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-03-18 | cs.LG | ai-safety, cslg, preprint | E5 / R3 (95%) | - |
| Identifying Latent Actions and Dynamics from Offline Data via Demonstrator Diversity Felix Schur Published: 2026-03-18Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-03-18 | cs.LG | ai-safety, cslg, preprint | E5 / R3 (94%) | - |
| Learning Permutation Distributions via Reflected Diffusion on Ranks David van Dijk, Shiyang Zhang, Sizhuang He, Yangtian Zhang Published: 2026-03-18Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-03-18 | cs.LG | ai-safety, cslg, preprint | E5 / R3 (96%) | - |
| Lightweight Adaptation for LLM-based Technical Service Agent: Latent Logic Augmentation and Robust Noise Reduction Chenghuang Shen, Guangquan Hu, Gurong Cui, Hangyi Sun Published: 2026-03-18Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-03-18 | cs.LG | ai-safety, cslg, preprint | E4 / R3 (92%) | - |
| LLM-Augmented Computational Phenotyping of Long Covid Amar Sra, Jeremy C Weiss, Jie Shen, Jing Wang Published: 2026-03-18Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-03-18 | cs.LG | ai-safety, cslg, preprint | E7 / R4 (96%) | - |
| MolRGen: A Training and Evaluation Setting for De Novo Molecular Generation with Reasonning Models Ismail Ben Ayed, Maxime Darrin, Pablo Piantanida, Philippe Formont Published: 2026-03-18Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint, safety-evaluation | 2026-03-18 | cs.LG | ai-safety, cslg, preprint, safety-evaluation | E5 / R3 (93%) | - |
| Objective Mispricing Detection for Shortlisting Undervalued Football Players via Market Dynamics and News Signals Chinenye Omejieke, Shuyao Chen, Xia Cui Published: 2026-03-18Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-03-18 | cs.LG | ai-safety, cslg, preprint | E5 / R3 (94%) | - |
| Pathology-Aware Multi-View Contrastive Learning for Patient-Independent ECG Reconstruction Jitin Singla, Youssef Youssef Published: 2026-03-18Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-03-18 | cs.LG | ai-safety, cslg, preprint | E5 / R3 (96%) | - |
| Probabilistic Federated Learning on Uncertain and Heterogeneous Data with Model Personalization Dinh C. Nguyen, Ratun Rahman Published: 2026-03-18Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-03-18 | cs.LG | ai-safety, cslg, preprint | E5 / R3 (98%) | - |
| Procedural Generation of Algorithm Discovery Tasks in Machine Learning Adrian Hayler, Aleksandra Kalisz, Alexander D. Goldie, Alistair Letcher Published: 2026-03-18Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-03-18 | cs.LG | ai-safety, cslg, preprint | E4 / R3 (94%) | - |
| QuantFL: Sustainable Federated Learning for Edge IoT via Pre-Trained Model Quantisation Charuka Herath, Sangarapillai Lambotharan, Varuna De Silva, Yogachandran Rahulamathavan Published: 2026-03-18Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-03-18 | cs.LG | ai-safety, cslg, preprint | E7 / R4 (97%) | - |
| R2-Dreamer: Redundancy-Reduced World Models without Decoders or Augmentation Akinobu Hayashi, Amal Nahar, Kartik Bharadwaj, Naoki Morihira Published: 2026-03-18Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-03-18 | cs.LG | ai-safety, cslg, preprint | E6 / R3 (95%) | - |
| R2-Dreamer: Redundancy-Reduced World Models without Decoders or Augmentation Akinobu Hayashi, Amal Nahar, Kartik Bharadwaj, Naoki Morihira Published: 2026-03-18Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-03-18 | cs.LG | ai-safety, cslg, preprint | E5 / R3 (96%) | - |
| RAMP: Reinforcement Adaptive Mixed Precision Quantization for Efficient On Device LLM Inference Arpit Singh Gautam, Saurabh Jha Published: 2026-03-18Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-03-18 | cs.LG | ai-safety, cslg, preprint | E6 / R4 (98%) | - |
| RangeAD: Fast On-Model Anomaly Detection Emmanuel Müller, Luca Hinkamp, Simon Klüttermann Published: 2026-03-18Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-03-18 | cs.LG | ai-safety, cslg, preprint | E5 / R3 (94%) | - |
| SCALE:Scalable Conditional Atlas-Level Endpoint transport for virtual cell perturbation prediction Hao Wu, Kedu Jin, Lang Yu, Lei Bai Published: 2026-03-18Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-03-18 | cs.LG | ai-safety, cslg, preprint | E5 / R3 (94%) | - |
| Sharpness-Aware Minimization in Logit Space Efficiently Enhances Direct Preference Optimization Dinh Phung, Haocheng Luo, Mehrtash Harandi, Thanh-Toan Do Published: 2026-03-18Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-03-18 | cs.LG | ai-safety, cslg, preprint | E5 / R3 (94%) | - |
| SLEA-RL: Step-Level Experience Augmented Reinforcement Learning for Multi-Turn Agentic Training Prince Zizhuang Wang, Shuli Jiang Published: 2026-03-18Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-03-18 | cs.LG | ai-safety, cslg, preprint | E5 / R3 (96%) | - |
| The Phasor Transformer: Resolving Attention Bottlenecks on the Unit Circle Dibakar Sigdel Published: 2026-03-18Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-03-18 | cs.LG | ai-safety, cslg, preprint | E5 / R3 (97%) | - |
| TimeAPN: Adaptive Amplitude-Phase Non-Stationarity Normalization for Time Series Forecasting Baosheng Yu, Dacheng Tao, Jialiang Tang, Jing Zhang Published: 2026-03-18Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-03-18 | cs.LG | ai-safety, cslg, preprint | E5 / R3 (95%) | - |
| Tula: Optimizing Time, Cost, and Generalization in Distributed Large-Batch Training Feiyi Wang, Sahil Tyagi Published: 2026-03-18Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-03-18 | cs.LG | ai-safety, cslg, preprint | E5 / R3 (95%) | - |
| Unsupervised Symbolic Anomaly Detection Emmanuel Müller, Md Maruf Hossain, Simon Klüttermann, Tim Katzke Published: 2026-03-18Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-03-18 | cs.LG | ai-safety, cslg, preprint | E5 / R3 (94%) | - |
| VC-Soup: Value-Consistency Guided Multi-Value Alignment for Large Language Models Han Wu, Hefei Xu, Le Wu, Meng Wang Published: 2026-03-18Area: cs.LGCitations: - Tags: ai-safety, alignment-training, cslg, preprint | 2026-03-18 | cs.LG | ai-safety, alignment-training, cslg, preprint | E5 / R3 (96%) | - |
| Adaptive Layerwise Perturbation: Unifying Off-Policy Corrections for LLM RL Abhinav Gullapalli, Chenlu Ye, Hao Chen, Jing Huang Published: 2026-03-19Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-03-19 | cs.LG | ai-safety, cslg, preprint | E5 / R3 (96%) | - |
| Adaptive Regime-Aware Stock Price Prediction Using Autoencoder-Gated Dual Node Transformers with Reinforcement Learning Control Hussein Al Osman, Mahtab Haj Ali, Mohammad Al Ridhawi Published: 2026-03-19Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-03-19 | cs.LG | ai-safety, cslg, preprint | E5 / R3 (95%) | - |