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 |
|---|---|---|---|---|---|
| The Curse and Blessing of Mean Bias in FP4-Quantized LLM Training Anrui Chen, Fang Dong, Fanqi Yu, Fan Yang Published: 2026-03-11Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-03-11 | cs.LG | ai-safety, cslg, preprint | E5 / R3 (96%) | - |
| Towards Cold-Start Drafting and Continual Refining: A Value-Driven Memory Approach with Application to NPU Kernel Synthesis Bo Tang, Hanjing Wang, Jiaqian Wang, Junchi Yan Published: 2026-03-11Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-03-11 | cs.LG | ai-safety, cslg, preprint | E5 / R3 (95%) | - |
| UAV-MARL: Multi-Agent Reinforcement Learning for Time-Critical and Dynamic Medical Supply Delivery Islam Guven, Mehmet Parlak Published: 2026-03-11Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-03-11 | cs.LG | ai-safety, cslg, preprint | E5 / R3 (96%) | - |
| A Multi-Label Temporal Convolutional Framework for Transcription Factor Binding Characterization Ferdinando Zanchetta, Giovanni Perini, Pietro Demurtas, Rita Fioresi Published: 2026-03-12Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-03-12 | cs.LG | ai-safety, cslg, preprint | E5 / R3 (94%) | - |
| A Quantitative Characterization of Forgetting in Post-Training Krishnakumar Balasubramanian, Shiva Prasad Kasiviswanathan Published: 2026-03-12Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-03-12 | cs.LG | ai-safety, cslg, preprint | E7 / R4 (93%) | - |
| ARROW: Augmented Replay for RObust World models Abdallah Al Siyabi, Abdulaziz Alyahya, Gideon Kowadlo, Levin Kuhlmann Published: 2026-03-12Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-03-12 | cs.LG | ai-safety, cslg, preprint | E6 / R4 (95%) | - |
| A Stable Neural Statistical Dependence Estimator for Autoencoder Feature Analysis Bo Hu, Jose C Principe Published: 2026-03-12Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-03-12 | cs.LG | ai-safety, cslg, preprint | E4 / R2 (94%) | - |
| Automatic Generation of High-Performance RL Environments Chi Jin, Rahul Dev Appapogu, Seth Karten Published: 2026-03-12Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-03-12 | cs.LG | ai-safety, cslg, preprint | E7 / R4 (98%) | - |
| Bridging Discrete Marks and Continuous Dynamics: Dual-Path Cross-Interaction for Marked Temporal Point Processes Peng He, Qiao Liu, Tong Luo, Yanglei Gan Published: 2026-03-12Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-03-12 | cs.LG | ai-safety, cslg, preprint | E5 / R4 (96%) | - |
| Chemical Reaction Networks Learn Better than Spiking Neural Networks Ivo F. Sbalzarini, Sophie Jaffard Published: 2026-03-12Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-03-12 | cs.LG | ai-safety, cslg, preprint | E5 / R3 (95%) | - |
| Effective Resistance Rewiring: A Simple Topological Correction for Over-Squashing Alexis Molina, Bertran Miquel-Oliver, Manel Gil-Sorribes, Victor Guallar Published: 2026-03-12Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-03-12 | cs.LG | ai-safety, cslg, preprint | E6 / R3 (97%) | - |
| EnTransformer: A Deep Generative Transformer for Multivariate Probabilistic Forecasting Madhurima Panja, Palash Ghosh, Rahul Goswami, Rajdeep Pathak Published: 2026-03-12Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-03-12 | cs.LG | ai-safety, cslg, preprint | E5 / R4 (96%) | - |
| Entropy-Preserving Reinforcement Learning Aleksei Petrenko, Ben Lipkin, Erik Wijmans, Kevin Chen Published: 2026-03-12Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-03-12 | cs.LG | ai-safety, cslg, preprint | E5 / R3 (95%) | - |
| Exploiting Expertise of Non-Expert and Diverse Agents in Social Bandit Learning: A Free Energy Approach Alireza Tavakoli, Erfan Mirzaei, Majid Nili Ahmadabadi, Reshad Hosseini Published: 2026-03-12Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-03-12 | cs.LG | ai-safety, cslg, preprint | E5 / R3 (94%) | - |
| Flowcean - Model Learning for Cyber-Physical Systems Goerschwin Fey, Hendrik Rose, Jan Christian Wieck, Markus Knitt Published: 2026-03-12Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-03-12 | cs.LG | ai-safety, cslg, preprint | E5 / R4 (96%) | - |
| Geometry-Aware Probabilistic Circuits via Voronoi Tessellations Sahil Sidheekh, Sriraam Natarajan Published: 2026-03-12Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-03-12 | cs.LG | ai-safety, cslg, preprint | E4 / R3 (94%) | - |
| Grammar of the Wave: Towards Explainable Multivariate Time Series Event Detection via Neuro-Symbolic VLM Agents Aymeric Jan, Sky Chenwei Wan, Tianjun Hou, Xiqing Chang Published: 2026-03-12Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-03-12 | cs.LG | ai-safety, cslg, preprint | E5 / R4 (95%) | - |
| IsoCompute Playbook: Optimally Scaling Sampling Compute for LLM RL Amrith Setlur, Aviral Kumar, Eric Xing, Feng Yao Published: 2026-03-12Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-03-12 | cs.LG | ai-safety, cslg, preprint | E5 / R3 (95%) | - |
| KEPo: Knowledge Evolution Poison on Graph-based Retrieval-Augmented Generation Chao Qi, Dongyang Zhang, Ke Qin, Muquan Li Published: 2026-03-12Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-03-12 | cs.LG | ai-safety, cslg, preprint | E5 / R4 (96%) | - |
| MobileKernelBench: Can LLMs Write Efficient Kernels for Mobile Devices? Chengfei Lv, Haoji Hu, Haolei Bai, Huan Wang Published: 2026-03-12Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-03-12 | cs.LG | ai-safety, cslg, preprint | E5 / R3 (96%) | - |
| Neural Thickets: Diverse Task Experts Are Dense Around Pretrained Weights Phillip Isola, Yulu Gan Published: 2026-03-12Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-03-12 | cs.LG | ai-safety, cslg, preprint | E6 / R3 (95%) | - |
| Resource-Efficient Iterative LLM-Based NAS with Feedback Memory Dmitry Ignatov, Radu Timofte, Xiaojie Gu Published: 2026-03-12Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-03-12 | cs.LG | ai-safety, cslg, preprint | E6 / R3 (97%) | - |
| Security Considerations for Artificial Intelligence Agents Jerry Ma, Kaiyuan Zhang, Kyle Polley, Ninghui Li Published: 2026-03-12Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-03-12 | cs.LG | ai-safety, cslg, preprint | E6 / R3 (95%) | - |
| Separable neural architectures as a primitive for unified predictive and generative intelligence Andrew Klichine, Apurba Sarker, Rajib Mostakim, Reza T. Batley Published: 2026-03-12Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-03-12 | cs.LG | ai-safety, cslg, preprint | E5 / R3 (94%) | - |
| Slow-Fast Inference: Training-Free Inference Acceleration via Within-Sentence Support Stability Kim-Chuan Toh, Shuicheng Yan, Tao Wang, Xingyu Xie Published: 2026-03-12Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-03-12 | cs.LG | ai-safety, cslg, preprint | E4 / R3 (95%) | - |
| Survival Meets Classification: A Novel Framework for Early Risk Prediction Models of Chronic Diseases Muddassar Farooq, Muhammad Usamah Shahid, Shaheer Ahmad Khan Published: 2026-03-12Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-03-12 | cs.LG | ai-safety, cslg, preprint | E6 / R3 (96%) | - |
| Taming the Adversary: Stable Minimax Deep Deterministic Policy Gradient via Fractional Objectives Donghwan Lee, Taeho Lee Published: 2026-03-12Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-03-12 | cs.LG | ai-safety, cslg, preprint | E5 / R3 (96%) | - |
| The Latent Color Subspace: Emergent Order in High-Dimensional Chaos Jessica Bader, Mateusz Pach, Quentin Bouniot, Serge Belongie Published: 2026-03-12Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-03-12 | cs.LG | ai-safety, cslg, preprint | E5 / R3 (95%) | - |
| Align Forward, Adapt Backward: Closing the Discretization Gap in Logic Gate Networks Youngsung Kim Published: 2026-03-14Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-03-14 | cs.LG | ai-safety, cslg, preprint | E6 / R4 (96%) | - |
| Chunk-Guided Q-Learning Gwanwoo Song, Kwanyoung Park, Youngwoon Lee Published: 2026-03-14Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-03-14 | cs.LG | ai-safety, cslg, preprint | E4 / R3 (94%) | - |