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 |
|---|---|---|---|---|---|
| MobileLLM-Flash: Latency-Guided On-Device LLM Design for Industry Scale Adithya Sagar, Andrey Gromov, Ayushi Dalmia, Bernard Beckerman Published: 2026-03-16Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-03-16 | cs.LG | ai-safety, cslg, preprint | E5 / R3 (96%) | - |
| More Test-Time Compute Can Hurt: Overestimation Bias in LLM Beam Search Assaf Hallak, Gal Chechik, Gal Dalal, Yftah Ziser Published: 2026-03-16Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-03-16 | cs.LG | ai-safety, cslg, preprint | E6 / R4 (94%) | - |
| Multi-Task Genetic Algorithm with Multi-Granularity Encoding for Protein-Nucleotide Binding Site Prediction An-Yang Lu, Liuyi Xu, Pengshan Cui, Xianpeng Wang Published: 2026-03-16Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-03-16 | cs.LG | ai-safety, cslg, preprint | E6 / R5 (97%) | - |
| OMNIFLOW: A Physics-Grounded Multimodal Agent for Generalized Scientific Reasoning Fan Xu, Fan Zhang, Hao Wu, Ruijian Gou Published: 2026-03-16Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-03-16 | cs.LG | ai-safety, cslg, preprint | E5 / R4 (96%) | - |
| PhasorFlow: A Python Library for Unit Circle Based Computing Dibakar Sigdel, Namuna Panday Published: 2026-03-16Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-03-16 | cs.LG | ai-safety, cslg, preprint | E5 / R4 (96%) | - |
| Physics-informed fine-tuning of foundation models for partial differential equations Andreas Rosskopf, Christopher Straub, Georg Kruse, Leon Armbruster Published: 2026-03-16Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-03-16 | cs.LG | ai-safety, cslg, preprint | E5 / R3 (94%) | - |
| Physics-Informed Neural Systems for the Simulation of EUV Electromagnetic Wave Diffraction from a Lithography Mask Egor V. Ivanov, Vasiliy A. Es'kin Published: 2026-03-16Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-03-16 | cs.LG | ai-safety, cslg, preprint | E5 / R3 (96%) | - |
| POLCA: Stochastic Generative Optimization with LLM Allen Nie, Ching-An Cheng, Tengyang Xie, Xuanfei Ren Published: 2026-03-16Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-03-16 | cs.LG | ai-safety, cslg, preprint | E7 / R3 (97%) | - |
| Real-Time Driver Safety Scoring Through Inverse Crash Probability Modeling Joyjit Roy, Samaresh Kumar Singh Published: 2026-03-16Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-03-16 | cs.LG | ai-safety, cslg, preprint | E5 / R4 (95%) | - |
| RESQ: A Unified Framework for REliability- and Security Enhancement of Quantized Deep Neural Networks Ali Azarpeyvand, Ali Soltan Mohammadi, Christian Herglotz, Mahdi Taheri Published: 2026-03-16Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-03-16 | cs.LG | ai-safety, cslg, preprint | E5 / R3 (96%) | - |
| Safe Flow Q-Learning: Offline Safe Reinforcement Learning with Reachability-Based Flow Policies Manan Tayal, Mumuksh Tayal, Ravi Prakash Published: 2026-03-16Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-03-16 | cs.LG | ai-safety, cslg, preprint | E5 / R4 (94%) | - |
| Sample-Efficient Hypergradient Estimation for Decentralized Bi-Level Reinforcement Learning Akifumi Wachi, Mikoto Kudo, Takumi Tanabe, Youhei Akimoto Published: 2026-03-16Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-03-16 | cs.LG | ai-safety, cslg, preprint | E5 / R3 (93%) | - |
| Seeking SOTA: Time-Series Forecasting Must Adopt Taxonomy-Specific Evaluation to Dispel Illusory Gains Blanka Horvath, Christoph Bergmeir, Daniel Schmidt, Frank Rudzicz Published: 2026-03-16Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint, safety-evaluation | 2026-03-16 | cs.LG | ai-safety, cslg, preprint, safety-evaluation | E5 / R3 (93%) | - |
| Seismic full-waveform inversion based on a physics-driven generative adversarial network Caiyun Liu, Jie Xiong, Qingfeng Yu, Xinyi Zhang Published: 2026-03-16Area: cs.LGCitations: - Tags: adversarial-robustness, ai-safety, cslg, preprint | 2026-03-16 | cs.LG | adversarial-robustness, ai-safety, cslg, preprint | E6 / R3 (97%) | - |
| TabKD: Tabular Knowledge Distillation through Interaction Diversity of Learned Feature Bins Krishna Khadka, Shovon Niverd Pereira, Yu Lei Published: 2026-03-16Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-03-16 | cs.LG | ai-safety, cslg, preprint | E5 / R3 (95%) | - |
| Tackling Over-smoothing on Hypergraphs: A Ricci Flow-guided Neural Diffusion Approach Guanghui Wang, Guiying Yan, Mengyao Zhou, Xiao Han Published: 2026-03-16Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-03-16 | cs.LG | ai-safety, cslg, preprint | E5 / R3 (95%) | - |
| The Agentic Researcher: A Practical Guide to AI-Assisted Research in Mathematics and Machine Learning Christophe Roux, Max Zimmer, Nico Pelleriti, Sebastian Pokutta Published: 2026-03-16Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-03-16 | cs.LG | ai-safety, cslg, preprint | E5 / R3 (96%) | - |
| The PokeAgent Challenge: Competitive and Long-Context Learning at Scale Amy Zhang, Anthony Sistilli, Arian Urdu, Benedikt Schink Published: 2026-03-16Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-03-16 | cs.LG | ai-safety, cslg, preprint | E6 / R4 (98%) | - |
| Towards Foundation Models for Consensus Rank Aggregation Chiara Balestra, Emmanuel M眉ller, Simon Kl眉ttermann, Yijun Jin Published: 2026-03-16Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-03-16 | cs.LG | ai-safety, cslg, preprint | E6 / R3 (96%) | - |
| TrajFlow: Nation-wide Pseudo GPS Trajectory Generation with Flow Matching Models Chihiro Shimizu, Haoran Zhang, Jiawei Wang, Noboru Koshizuka Published: 2026-03-16Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-03-16 | cs.LG | ai-safety, cslg, preprint | E5 / R4 (95%) | - |
| Transition Flow Matching Chenrui Ma Published: 2026-03-16Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-03-16 | cs.LG | ai-safety, cslg, preprint | E5 / R3 (94%) | - |
| Universe Routing: Why Self-Evolving Agents Need Epistemic Control Zhaohui Geoffrey Wang Published: 2026-03-16Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-03-16 | cs.LG | ai-safety, cslg, preprint | E6 / R3 (97%) | - |
| When Stability Fails: Hidden Failure Modes Of LLMS in Data-Constrained Scientific Decision-Making Nazia Riasat Published: 2026-03-16Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-03-16 | cs.LG | ai-safety, cslg, preprint | E5 / R3 (98%) | - |
| A General Deep Learning Framework for Wireless Resource Allocation under Discrete Constraints Rui Zhang, Yang Li, Yik-Chung Wu, Yikun Wang Published: 2026-03-17Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-03-17 | cs.LG | ai-safety, cslg, preprint | E5 / R3 (93%) | - |
| Age Predictors Through the Lens of Generalization, Bias Mitigation, and Interpretability: Reflections on Causal Implications Alessandro Cellerino, Debdas Paul, Elisa Ferrari, Irene Gravili Published: 2026-03-17Area: cs.LGCitations: - Tags: ai-safety, cslg, interpretability, preprint | 2026-03-17 | cs.LG | ai-safety, cslg, interpretability, preprint | E5 / R3 (92%) | - |
| Bridging the High-Frequency Data Gap: A Millisecond-Resolution Network Dataset for Advancing Time Series Foundation Models Marco Ruffini, Merim Dzaferagic, Seshu Tirupathi, Subina Khanal Published: 2026-03-17Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-03-17 | cs.LG | ai-safety, cslg, preprint | E6 / R3 (96%) | - |
| Catching rationalization in the act: detecting motivated reasoning before and after CoT via activation probing Mikhail Belkin, Parsa Mirtaheri Published: 2026-03-17Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-03-17 | cs.LG | ai-safety, cslg, preprint | E6 / R3 (95%) | - |
| CircuitBuilder: From Polynomials to Circuits via Reinforcement Learning Archit Ganapule, Bhaumik Mehta, Jarod Alper, Kaijie Jin Published: 2026-03-17Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-03-17 | cs.LG | ai-safety, cslg, preprint | E5 / R3 (95%) | - |
| Collaborative Temporal Feature Generation via Critic-Free Reinforcement Learning for Cross-User Sensor-Based Activity Recognition Feng Jiang, Kevin I-Kai Wang, Xiaozhou Ye, Xiulai Wang Published: 2026-03-17Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-03-17 | cs.LG | ai-safety, cslg, preprint | E5 / R3 (98%) | - |
| Cost Trade-offs in Matrix Inversion Updates for Streaming Outlier Detection Florian Grivet, Louise Trav茅-Massuy猫s Published: 2026-03-17Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-03-17 | cs.LG | ai-safety, cslg, preprint | E5 / R4 (98%) | - |