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 |
|---|---|---|---|---|---|
| Causal Discovery in Action: Learning Chain-Reaction Mechanisms from Interventions 脰zg眉r 艦im艧ek, Panayiotis Panayiotou Published: 2026-03-23Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-03-23 | cs.LG | ai-safety, cslg, preprint | E4 / R2 (95%) | - |
| Confidence-Based Decoding is Provably Efficient for Diffusion Language Models Changxiao Cai, Gen Li Published: 2026-03-23Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-03-23 | cs.LG | ai-safety, cslg, preprint | E5 / R3 (95%) | - |
| CoRA: Boosting Time Series Foundation Models for Multivariate Forecasting through Correlation-aware Adapter Bin Yang, Chenjuan Guo, Hanyin Cheng, Lujia Pan Published: 2026-03-23Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-03-23 | cs.LG | ai-safety, cslg, preprint | E4 / R3 (95%) | - |
| Deep Reinforcement Learning and The Tale of Two Temporal Difference Errors Chi-Guhn Lee, Juan Sebastian Rojas Published: 2026-03-23Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-03-23 | cs.LG | ai-safety, cslg, preprint | E5 / R2 (93%) | - |
| DSPA: Dynamic SAE Steering for Data-Efficient Preference Alignment Aashiq Muhamed, James Wedgwood, Mona T. Diab, Virginia Smith Published: 2026-03-23Area: cs.LGCitations: - Tags: ai-safety, alignment-training, cslg, preprint | 2026-03-23 | cs.LG | ai-safety, alignment-training, cslg, preprint | E6 / R3 (97%) | - |
| Extending Precipitation Nowcasting Horizons via Spectral Fusion of Radar Observations and Foundation Model Priors Qingyong Li, Wen Wang, Yangli-ao Geng, Yan Liu Published: 2026-03-23Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-03-23 | cs.LG | ai-safety, cslg, preprint | E5 / R3 (96%) | - |
| Extending Precipitation Nowcasting Horizons via Spectral Fusion of Radar Observations and Foundation Model Priors Qingyong Li, Wen Wang, Yangli-ao Geng, Yan Liu Published: 2026-03-23Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-03-23 | cs.LG | ai-safety, cslg, preprint | E6 / R3 (96%) | - |
| FAAR: Format-Aware Adaptive Rounding for NVFP4 Chen Lin, Hanglin Li, Kun Zhan, Shuchang Tian Published: 2026-03-23Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-03-23 | cs.LG | ai-safety, cslg, preprint | E6 / R3 (96%) | - |
| FISformer: Replacing Self-Attention with a Fuzzy Inference System in Transformer Models for Time Series Forecasting Bulent Haznedar, Levent Karacan Published: 2026-03-23Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-03-23 | cs.LG | ai-safety, cslg, preprint | E5 / R3 (98%) | - |
| Instruction-Tuned, but Not More Verifiable Instruction-Following: A Cross-Task Diagnosis for LoRA Adapters Junyi Zou Published: 2026-03-23Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-03-23 | cs.LG | ai-safety, cslg, preprint | E5 / R3 (94%) | - |
| Learning When to Act: Interval-Aware Reinforcement Learning with Predictive Temporal Structure Davide Di Gioia Published: 2026-03-23Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-03-23 | cs.LG | ai-safety, cslg, preprint | E5 / R3 (96%) | - |
| Learning When to Act: Interval-Aware Reinforcement Learning with Predictive Temporal Structure Davide Di Gioia Published: 2026-03-23Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-03-23 | cs.LG | ai-safety, cslg, preprint | E5 / R3 (96%) | - |
| MCLR: Improving Conditional Modeling in Visual Generative Models via Inter-Class Likelihood-Ratio Maximization and Establishing the Equivalence between Classifier-Free Guidance and Alignment Objectives Jeffrey A. Fessler, Qing Qu, Rongrong Wang, Xiang Li Published: 2026-03-23Area: cs.LGCitations: - Tags: ai-safety, alignment-training, cslg, preprint | 2026-03-23 | cs.LG | ai-safety, alignment-training, cslg, preprint | E6 / R3 (96%) | - |
| mSFT: Addressing Dataset Mixtures Overfiting Heterogeneously in Multi-task SFT Jaehyeong Choi, Jeyoung Jeon, Se-Young Yun, Soowon Oh Published: 2026-03-23Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-03-23 | cs.LG | ai-safety, cslg, preprint | E7 / R3 (94%) | - |
| mSFT: Addressing Dataset Mixtures Overfitting Heterogeneously in Multi-task SFT Jaehyeong Choi, Jeyoung Jeon, Se-Young Yun, Soowon Oh Published: 2026-03-23Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-03-23 | cs.LG | ai-safety, cslg, preprint | E7 / R3 (94%) | - |
| mSFT: Addressing Dataset Mixtures Overfitting Heterogeneously in Multi-task SFT Jaehyeong Choi, Jeyoung Jeon, Se-Young Yun, Soowon Oh Published: 2026-03-23Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-03-23 | cs.LG | ai-safety, cslg, preprint | E7 / R3 (93%) | - |
| Multimodal Survival Analysis with Locally Deployable Large Language Models Christopher Yau, Moritz G枚gl Published: 2026-03-23Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-03-23 | cs.LG | ai-safety, cslg, preprint | E5 / R3 (95%) | - |
| On the Direction of RLVR Updates for LLM Reasoning: Identification and Exploitation Bolin Ding, Chiyu Ma, Guoyin Wang, Haoming Meng Published: 2026-03-23Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-03-23 | cs.LG | ai-safety, cslg, preprint | E5 / R3 (97%) | - |
| On the Failure of Topic-Matched Contrast Baselines in Multi-Directional Refusal Abliteration Valentin Petrov Published: 2026-03-23Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-03-23 | cs.LG | ai-safety, cslg, preprint | E5 / R3 (98%) | - |
| On the Number of Conditional Independence Tests in Constraint-based Causal Discovery Caroline Uhler, Jiaqi Zhang, Marc Franquesa Mon茅s Published: 2026-03-23Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-03-23 | cs.LG | ai-safety, cslg, preprint | E5 / R3 (94%) | - |
| Optimizing Feature Extraction for On-device Model Inference with User Behavior Sequences Chen Gong, Fan Wu, Guihai Chen, Sheng Wang Published: 2026-03-23Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-03-23 | cs.LG | ai-safety, cslg, preprint | E4 / R3 (95%) | - |
| P^2O: Joint Policy and Prompt Optimization Boxi Cao, Hongyu Lin, Jinglin Yang, Kaiqi Zhang Published: 2026-03-23Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-03-23 | cs.LG | ai-safety, cslg, preprint | E5 / R3 (94%) | - |
| P^2O: Joint Policy and Prompt Optimization Boxi Cao, Hongyu Lin, Jinglin Yang, Kaiqi Zhang Published: 2026-03-23Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-03-23 | cs.LG | ai-safety, cslg, preprint | E5 / R3 (96%) | - |
| Quotient Geometry, Effective Curvature, and Implicit Bias in Simple Shallow Neural Networks Hang-Cheng Dong, Pengcheng Cheng Published: 2026-03-23Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-03-23 | cs.LG | ai-safety, cslg, preprint | E6 / R3 (92%) | - |
| Rethinking Multimodal Fusion for Time Series: Auxiliary Modalities Need Constrained Fusion Dongwan Kang, Hwanil Choi, Jaehoon Lee, Jun Seo Published: 2026-03-23Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-03-23 | cs.LG | ai-safety, cslg, preprint | E5 / R3 (94%) | - |
| Riemannian Geometry Speaks Louder Than Words: From Graph Foundation Model to Next-Generation Graph Intelligence Li Sun, Philip S. Yu Published: 2026-03-23Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-03-23 | cs.LG | ai-safety, cslg, preprint | E5 / R3 (95%) | - |
| ROM: Real-time Overthinking Mitigation via Streaming Detection and Intervention Chaowei Xiao, Xiaogeng Liu, Xinyan Wang Published: 2026-03-23Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-03-23 | cs.LG | ai-safety, cslg, preprint | E4 / R3 (95%) | - |
| Rule-State Inference (RSI): A Bayesian Framework for Compliance Monitoring in Rule-Governed Domains Abdou-Raouf Atarmla Published: 2026-03-23Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-03-23 | cs.LG | ai-safety, cslg, preprint | E4 / R3 (95%) | - |
| Sharper Generalization Bounds for Transformer Huiming Zhang, Tao Hu, Wan Tian, Yawen Li Published: 2026-03-23Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-03-23 | cs.LG | ai-safety, cslg, preprint | E5 / R2 (95%) | - |
| SmaAT-QMix-UNet: A Parameter-Efficient Vector-Quantized UNet for Precipitation Nowcasting Nikolas Stavrou, Siamak Mehrkanoon Published: 2026-03-23Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-03-23 | cs.LG | ai-safety, cslg, preprint | E7 / R4 (96%) | - |