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 |
|---|---|---|---|---|---|
| AgentDS Technical Report: Benchmarking the Future of Human-AI Collaboration in Domain-Specific Data Science An Luo, Ashish Kundu, Charles Fleming, Fangqiao Tian Published: 2026-03-19Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-03-19 | cs.LG | ai-safety, cslg, preprint | E4 / R3 (96%) | - |
| Are complicated loss functions necessary for teaching LLMs to reason? Andrea Sassella, Federico Toschi, Gabriele Carrino, Mark James Carman Published: 2026-03-19Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-03-19 | cs.LG | ai-safety, cslg, preprint | E5 / R3 (97%) | - |
| Automatic Configuration of LLM Post-Training Pipelines Channe Chwa, Xinle Wu, Yao Lu Published: 2026-03-19Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-03-19 | cs.LG | ai-safety, cslg, preprint | E5 / R3 (94%) | - |
| Beyond Weighted Summation: Learnable Nonlinear Aggregation Functions for Robust Artificial Neurons Berke Deniz Bozyigit Published: 2026-03-19Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-03-19 | cs.LG | ai-safety, cslg, preprint | E5 / R4 (97%) | - |
| CausalRM: Causal-Theoretic Reward Modeling for RLHF from Observational User Feedbacks Chunyuan Zheng, Hao Wang, Haoxuan Li, Licheng Pan Published: 2026-03-19Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-03-19 | cs.LG | ai-safety, cslg, preprint | E5 / R3 (93%) | - |
| Collaborative Adaptive Curriculum for Progressive Knowledge Distillation Bobo Ju, Bo Hu, Chengfang Li, Han Yu Published: 2026-03-19Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-03-19 | cs.LG | ai-safety, cslg, preprint | E36 / R28 (96%) | - |
| Discounted Beta--Bernoulli Reward Estimation for Sample-Efficient Reinforcement Learning with Verifiable Rewards Doohyuk Jang, Eunho Yang, Gyouk Chu, Haechan Kim Published: 2026-03-19Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-03-19 | cs.LG | ai-safety, cslg, preprint | E5 / R3 (95%) | - |
| Do Post-Training Algorithms Actually Differ? A Controlled Study Across Model Scales Uncovers Scale-Dependent Ranking Inversions Xiaoyi Li Published: 2026-03-19Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-03-19 | cs.LG | ai-safety, cslg, preprint | E6 / R4 (96%) | - |
| Elastic Weight Consolidation Done Right for Continual Learning Xiaobin Chang, Xuan Liu Published: 2026-03-19Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-03-19 | cs.LG | ai-safety, cslg, preprint | E5 / R3 (95%) | - |
| Elastic Weight Consolidation Done Right for Continual Learning Xiaobin Chang, Xuan Liu Published: 2026-03-19Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-03-19 | cs.LG | ai-safety, cslg, preprint | E6 / R4 (97%) | - |
| Foundations of Schr枚dinger Bridges for Generative Modeling Sophia Tang Published: 2026-03-19Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-03-19 | cs.LG | ai-safety, cslg, preprint | E6 / R4 (99%) | - |
| Global Convergence of Multiplicative Updates for the Matrix Mechanism: A Collaborative Proof with Gemini 3 Keith Rush Published: 2026-03-19Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-03-19 | cs.LG | ai-safety, cslg, preprint | E5 / R3 (96%) | - |
| Global Convergence of Multiplicative Updates for the Matrix Mechanism: A Collaborative Proof with Gemini 3 Keith Rush Published: 2026-03-19Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-03-19 | cs.LG | ai-safety, cslg, preprint | E5 / R3 (94%) | - |
| HISR: Hindsight Information Modulated Segmental Process Rewards For Multi-turn Agentic Reinforcement Learning Changyuan Tian, Deheng Ye, Guangluan Xu, Li Jin Published: 2026-03-19Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-03-19 | cs.LG | ai-safety, cslg, preprint | E5 / R4 (95%) | - |
| MARLIN: Multi-Agent Reinforcement Learning for Incremental DAG Discovery Chen Zhao, Dong Li, Haifeng Chen, Linlin Yu Published: 2026-03-19Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-03-19 | cs.LG | ai-safety, cslg, preprint | E30 / R24 (97%) | - |
| Self-Tuning Sparse Attention: Multi-Fidelity Hyperparameter Optimization for Transformer Acceleration Arundhathi Dev, Justin Zhan Published: 2026-03-19Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-03-19 | cs.LG | ai-safety, cslg, preprint | E5 / R3 (97%) | - |
| SOL-ExecBench: Speed-of-Light Benchmarking for Real-World GPU Kernels Against Hardware Limits Aditya Kane, Christos Kozyrakis, Cyril Zeller, Dheeraj Peri Published: 2026-03-19Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-03-19 | cs.LG | ai-safety, cslg, preprint | E5 / R3 (96%) | - |
| SpecForge: A Flexible and Efficient Open-Source Training Framework for Speculative Decoding Chao Wang, Fan Yin, Ivor Tsang, Ji Li Published: 2026-03-19Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-03-19 | cs.LG | ai-safety, cslg, preprint | E5 / R4 (97%) | - |
| TRACE: Trajectory Recovery with State Propagation Diffusion for Urban Mobility Geyong Min, Hai Wang, Hongkai Wen, Jinming Wang Published: 2026-03-19Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-03-19 | cs.LG | ai-safety, cslg, preprint | E5 / R3 (97%) | - |
| Transformer-Based Predictive Maintenance for Risk-Aware Instrument Calibration Adithya Parthasarathy, Akshay Deshpande, Aswathnarayan Muthukrishnan Kirubakaran, Nachiappan Chockalingam Published: 2026-03-19Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-03-19 | cs.LG | ai-safety, cslg, preprint | E33 / R21 (96%) | - |
| Transformers Learn Robust In-Context Regression under Distributional Uncertainty Hai D. V. Trinh, Hoang T. H. Cao, Lan V. Truong, Tho Quan Published: 2026-03-19Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-03-19 | cs.LG | ai-safety, cslg, preprint | E5 / R3 (95%) | - |
| A Direct Classification Approach for Reliable Wind Ramp Event Forecasting under Severe Class Imbalance Alejandro Morales-Hern谩ndez, Alfredo Vaccaro, Fabrizio De Caroa, Gianluca Bontempi Published: 2026-03-20Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-03-20 | cs.LG | ai-safety, cslg, preprint | E5 / R3 (95%) | - |
| AEGIS: An Operational Infrastructure for Post-Market Governance of Adaptive Medical AI Under US and EU Regulations Fardin Afdideh, Farhad Abtahi, Fernando Seoane, Mehdi Astaraki Published: 2026-03-20Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-03-20 | cs.LG | ai-safety, cslg, preprint | E5 / R3 (97%) | - |
| A Multi-Modal CNN-LSTM Framework with Multi-Head Attention and Focal Loss for Real-Time Elderly Fall Detection Lijie Zhou, Luran Wang Published: 2026-03-20Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-03-20 | cs.LG | ai-safety, cslg, preprint | E5 / R3 (96%) | - |
| A Multi-Task Targeted Learning Framework for Lithium-Ion Battery State-of-Health and Remaining Useful Life Chenhan Wang, Chunxiang Zhu, Huipin Lin, Jiahao Nie Published: 2026-03-20Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-03-20 | cs.LG | ai-safety, cslg, preprint | E6 / R4 (97%) | - |
| ARMOR: Adaptive Resilience Against Model Poisoning Attacks in Continual Federated Learning for Mobile Indoor Localization Akhil Singampalli, Danish Gufran, Sudeep Pasricha Published: 2026-03-20Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-03-20 | cs.LG | ai-safety, cslg, preprint | E5 / R4 (96%) | - |
| Beyond the Mean: Distribution-Aware Loss Functions for Bimodal Regression Abolfazl Mohammadi-Seif, Carlos Soares, Ricardo Baeza-Yates, Rita P. Ribeiro Published: 2026-03-20Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-03-20 | cs.LG | ai-safety, cslg, preprint | E5 / R3 (94%) | - |
| Bounded Coupled AI Learning Dynamics in Tri-Hierarchical Drone Swarms Oleksii Bychkov Published: 2026-03-20Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-03-20 | cs.LG | ai-safety, cslg, preprint | E30 / R26 (95%) | - |
| Breaking the Capability Ceiling of LLM Post-Training by Reintroducing Markov States Tengyang Xie, Yurun Yuan Published: 2026-03-20Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-03-20 | cs.LG | ai-safety, cslg, preprint | E5 / R3 (94%) | - |
| CAMA: Exploring Collusive Adversarial Attacks in c-MARL Men Niu, Quanliang Jing, Shaoye Luo, Xinxin Fan Published: 2026-03-20Area: cs.LGCitations: - Tags: adversarial-robustness, ai-safety, cslg, preprint | 2026-03-20 | cs.LG | adversarial-robustness, ai-safety, cslg, preprint | E31 / R23 (95%) | - |