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 |
|---|---|---|---|---|---|
| Do Understanding and Generation Fight? A Diagnostic Study of DPO for Unified Multimodal Models Abinav Rao, Sujan Rachuri Published: 2026-03-17Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-03-17 | cs.LG | ai-safety, cslg, preprint | E5 / R4 (95%) | - |
| DyJR: Preserving Diversity in Reinforcement Learning with Verifiable Rewards via Dynamic Jensen-Shannon Replay Chao Qu, Long Li, Shirui Pan, Tianyi Wang Published: 2026-03-17Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-03-17 | cs.LG | ai-safety, cslg, preprint | E5 / R3 (95%) | - |
| DynamicGate MLP Conditional Computation via Learned Structural Dropout and Input Dependent Gating for Functional Plasticity Yong Il Choi Published: 2026-03-17Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-03-17 | cs.LG | ai-safety, cslg, preprint | E5 / R3 (95%) | - |
| Early Quantization Shrinks Codebook: A Simple Fix for Diversity-Preserving Tokenization Dianbo Liu, Qiran Zou, Rushi Shah, Wenhao Zhao Published: 2026-03-17Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-03-17 | cs.LG | ai-safety, cslg, preprint | E6 / R3 (95%) | - |
| FEAT: A Linear-Complexity Foundation Model for Extremely Large Structured Data Bingbing Fang, Junbo Zhao, Lu Chen, Sheng Zhang Published: 2026-03-17Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-03-17 | cs.LG | ai-safety, cslg, preprint | E5 / R3 (94%) | - |
| FEAT: A Linear-Complexity Foundation Model for Extremely Large Structured Data Bingbing Fang, Junbo Zhao, Lu Chen, Sheng Zhang Published: 2026-03-17Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-03-17 | cs.LG | ai-safety, cslg, preprint | E5 / R3 (93%) | - |
| FederatedFactory: Generative One-Shot Learning for Extremely Non-IID Distributed Scenarios Ali Raza, Andrea Moleri, Barbara Hammer, Christian Intern貌 Published: 2026-03-17Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-03-17 | cs.LG | ai-safety, cslg, preprint | E5 / R4 (94%) | - |
| Federated Learning with Multi-Partner OneFlorida+ Consortium Data for Predicting Major Postoperative Complications Azra Bihorac, Benjamin Shickel, Parisa Rashidi, Tezcan Ozrazgat-Baslanti Published: 2026-03-17Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-03-17 | cs.LG | ai-safety, cslg, preprint | E5 / R3 (98%) | - |
| Functorial Neural Architectures from Higher Inductive Types Karen Sargsyan Published: 2026-03-17Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-03-17 | cs.LG | ai-safety, cslg, preprint | E5 / R3 (96%) | - |
| HIPO: Instruction Hierarchy via Constrained Reinforcement Learning Alvaro Velasquez, Jun Luo, Keru Chen, Nathaniel Bastian Published: 2026-03-17Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-03-17 | cs.LG | ai-safety, cslg, preprint | E6 / R4 (93%) | - |
| Manifold-Matching Autoencoders Chris Drummond, Hussein Al Osman, Isar Nejadgholi, Laurent Cheret Published: 2026-03-17Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-03-17 | cs.LG | ai-safety, cslg, preprint | E7 / R3 (93%) | - |
| NANOZK: Layerwise Zero-Knowledge Proofs for Verifiable Large Language Model Inference Zhaohui Geoffrey Wang Published: 2026-03-17Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-03-17 | cs.LG | ai-safety, cslg, preprint | E5 / R4 (94%) | - |
| REAL: Regression-Aware Reinforcement Learning for LLM-as-a-Judge Michal Lukasik, Mingyuan Zhou, Oscar Leong, Tianyu Chen Published: 2026-03-17Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-03-17 | cs.LG | ai-safety, cslg, preprint | E6 / R4 (94%) | - |
| Residual Stream Duality in Modern Transformer Architectures Yifan Zhang Published: 2026-03-17Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-03-17 | cs.LG | ai-safety, cslg, preprint | E6 / R3 (93%) | - |
| Sample-Efficient Adaptation of Drug-Response Models to Patient Tumors under Strong Biological Domain Shift Camille Jimenez Cortes, German Vega, Philippe Lalanda Published: 2026-03-17Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-03-17 | cs.LG | ai-safety, cslg, preprint | E5 / R3 (96%) | - |
| SpecMoE: Spectral Mixture-of-Experts Foundation Model for Cross-Species EEG Decoding C. Habermacher, D. Darankoum, J. Volle, S. Grudinin Published: 2026-03-17Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-03-17 | cs.LG | ai-safety, cslg, preprint | E5 / R3 (96%) | - |
| Target Concept Tuning Improves Extreme Weather Forecasting Bo Wu, Haifan Zhang, Jirong Wen, Liang Sun Published: 2026-03-17Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-03-17 | cs.LG | ai-safety, cslg, preprint | E5 / R3 (95%) | - |
| Trained Persistent Memory for Frozen Encoder--Decoder LLMs: Six Architectural Methods Hong Jeong Published: 2026-03-17Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-03-17 | cs.LG | ai-safety, cslg, preprint | E7 / R3 (92%) | - |
| AirDDE: Multifactor Neural Delay Differential Equations for Air Quality Forecasting Binqing Wu, Jiahui Xu, Jianlong Huang, Ling Chen Published: 2026-03-18Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-03-18 | cs.LG | ai-safety, cslg, preprint | E5 / R4 (97%) | - |
| Approximate Subgraph Matching with Neural Graph Representations and Reinforcement Learning Kaiyang Li, Shihao Ji, Wei Li, Zhipeng Cai Published: 2026-03-18Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-03-18 | cs.LG | ai-safety, cslg, preprint | E5 / R4 (97%) | - |
| ARTEMIS: A Neuro Symbolic Framework for Economically Constrained Market Dynamics Rahul D Ray Published: 2026-03-18Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-03-18 | cs.LG | ai-safety, cslg, preprint | E6 / R3 (96%) | - |
| Attention Sinks Induce Gradient Sinks Quanming Yao, Yihong Chen Published: 2026-03-18Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-03-18 | cs.LG | ai-safety, cslg, preprint | E6 / R6 (92%) | - |
| Auto-Unrolled Proximal Gradient Descent: An AutoML Approach to Interpretable Waveform Optimization Ahmet Kaplan Published: 2026-03-18Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-03-18 | cs.LG | ai-safety, cslg, preprint | E5 / R3 (97%) | - |
| Baguan-TS: A Sequence-Native In-Context Learning Model for Time Series Forecasting with Covariates Gezheng Xu, Liang Sun, Linxiao Yang, Linyuan Geng Published: 2026-03-18Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-03-18 | cs.LG | ai-safety, cslg, preprint | E5 / R4 (96%) | - |
| Benchmarking Reinforcement Learning via Stochastic Converse Optimality: Generating Systems with Known Optimal Policies Gr茅goire Ouerdane, Hadi Salloum, Henni Ouerdane, Pavel Osinenko Published: 2026-03-18Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-03-18 | cs.LG | ai-safety, cslg, preprint | E5 / R3 (93%) | - |
| Can Blindfolded LLMs Still Trade? An Anonymization-First Framework for Portfolio Optimization Hongchul Lee, Joohyoung Jeon Published: 2026-03-18Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-03-18 | cs.LG | ai-safety, cslg, preprint | E5 / R3 (96%) | - |
| CARE: Covariance-Aware and Rank-Enhanced Decomposition for Enabling Multi-Head Latent Attention Ben Athiwaratkun, Fengxiang Bie, Junxiong Wang, Shuaiwen Leon Song Published: 2026-03-18Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-03-18 | cs.LG | ai-safety, cslg, preprint | E5 / R3 (94%) | - |
| CLeAN: Continual Learning Adaptive Normalization in Dynamic Environments Davide Evangelista, Elena Loli Piccolomini, Isabella Marasco, Michele Colajanni Published: 2026-03-18Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-03-18 | cs.LG | ai-safety, cslg, preprint | E5 / R3 (97%) | - |
| Detection Is Cheap, Routing Is Learned: Why Refusal-Based Alignment Evaluation Fails Gregory N. Frank Published: 2026-03-18Area: cs.LGCitations: - Tags: ai-safety, alignment-training, cslg, preprint, safety-evaluation | 2026-03-18 | cs.LG | ai-safety, alignment-training, cslg, preprint, safety-evaluation | E8 / R4 (98%) | - |
| Discovering What You Can Control: Interventional Boundary Discovery for Reinforcement Learning Jiaxin Liu Published: 2026-03-18Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-03-18 | cs.LG | ai-safety, cslg, preprint | E6 / R4 (97%) | - |