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 |
|---|---|---|---|---|---|
| When Do Supervised UQ Ensembles Improve LLM Hallucination Detection? A Robustness Study Dylan Bouchard, Mohit Singh Chauhan, Vipin Gyanchandani Published: 2026-08-25Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-08-25 | cs.LG | ai-safety, cslg, preprint | - | - |
| A Physical Response-and-Memory Model for Muon Optimization Hongjun Xiang, Hongyu Yu, Xingao Gong, Yinze Hu Published: 2026-08-24Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-08-24 | cs.LG | ai-safety, cslg, preprint | - | - |
| Best Practice Critic Optimization Penghui Qi, Wee Sun Lee, Xiangxin Zhou Published: 2026-08-24Area: cs.LGCitations: 15 Tags: ai-safety, cslg, preprint | 2026-08-24 | cs.LG | ai-safety, cslg, preprint | E9 / R10 (93%) | 15 |
| CatchBench: When Can an Agent Failure Be Caught? Yue Zhao Published: 2026-08-24Area: cs.LGCitations: 25 Tags: ai-safety, cslg, preprint | 2026-08-24 | cs.LG | ai-safety, cslg, preprint | E16 / R12 (92%) | 25 |
| CAT-GS: Balanced Multimodal Learning via Calibrated Gating and Fusion Surgery Mahir Shahriar Tamim, Md. Samiul Alim, Nabeel Mohammed, Shafin Rahman Published: 2026-08-24Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-08-24 | cs.LG | ai-safety, cslg, preprint | E15 / R16 (94%) | - |
| CAT-GS: Balanced Multimodal Learning via Calibrated Gating and Fusion Surgery Mahir Shahriar Tamim, Md. Samiul Alim, Nabeel Mohammed, Shafin Rahman Published: 2026-08-24Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-08-24 | cs.LG | ai-safety, cslg, preprint | E2 / R14 (91%) | - |
| ChebBooster: A Training-Free Approach for Efficient Diffusion Transformer Inference via Chebyshev-Inspired Extrapolation Chengjie Lu, Chengwen Luo, Tianchi Deng, Xueliang Li Published: 2026-08-24Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-08-24 | cs.LG | ai-safety, cslg, preprint | - | - |
| Counterfactual Transition Graphs: Evaluating Cross-Class Transition Quality Grzegorz J. Nalepa, Myra Spiliopoulou, Syed Muhammad Hamza Zaidi, Szymon Bobek Published: 2026-08-24Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-08-24 | cs.LG | ai-safety, cslg, preprint | - | - |
| DeMixPert: Decomposed Response Modeling with Gaussian Mixtures for OOD Single-Cell Perturbation Prediction Bing Liu, Hongmin Cai, Jiaming Liang, Jiawen Liu Published: 2026-08-24Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-08-24 | cs.LG | ai-safety, cslg, preprint | - | - |
| Demystifying Reinforcement Learning Post-Training of Language Models Donovan Clay, Jacob Morrison, Min Jang, Natasha Jaques Published: 2026-08-24Area: cs.LGCitations: 45 Tags: ai-safety, cslg, preprint | 2026-08-24 | cs.LG | ai-safety, cslg, preprint | E11 / R9 (92%) | 45 |
| Discovering Cross-Language Reasoning Invariance in LLMs with Geometry-Invariant Sparse Autoencoders Changcheng Huang, Igor Bogdanov Published: 2026-08-24Area: cs.LGCitations: 12 Tags: ai-safety, cslg, preprint | 2026-08-24 | cs.LG | ai-safety, cslg, preprint | E12 / R10 (94%) | 12 |
| Disentangled Skill Representations for Predictive Human Modeling Deepak Gopinath, Guy Rosman, Mariah Schrum, Srijan Srivatsa Published: 2026-08-24Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-08-24 | cs.LG | ai-safety, cslg, preprint | E8 / R6 (94%) | - |
| ExFold: Unified Expert Folding for Training-Free MoE Prefill-Decode Acceleration Chaoran Feng, Juntong Wu, Junyi Chen, Liujie Zhang Published: 2026-08-24Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-08-24 | cs.LG | ai-safety, cslg, preprint | E10 / R9 (93%) | - |
| Fairness-Aware Mixture-of-Experts via Subgroup Reweighting and Gate Regularization Sunhee Hwang Published: 2026-08-24Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-08-24 | cs.LG | ai-safety, cslg, preprint | - | - |
| FAMPWQ: Fisher Information-based Adaptive Mixed Precision Weight Quantization for Effective LLM Inference Gongwei Lee, Ji Liu, Ji Wu, Juncheng Jia Published: 2026-08-24Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-08-24 | cs.LG | ai-safety, cslg, preprint | E8 / R6 (93%) | - |
| FedCC: Towards Addressing Label Distribution Skews in Distillation-Based Federated Learning Georg Carle, Onur Ayan, Wenxuan Ye, Xueli An Published: 2026-08-24Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-08-24 | cs.LG | ai-safety, cslg, preprint | - | - |
| FedCC: Towards Addressing Label Distribution Skews in Distillation-Based Federated Learning Georg Carle, Onur Ayan, Wenxuan Ye, Xueli An Published: 2026-08-24Area: cs.LGCitations: 26 Tags: ai-safety, cslg, preprint | 2026-08-24 | cs.LG | ai-safety, cslg, preprint | E10 / R7 (94%) | 26 |
| From Causal Plausibility to Causal Reliability: Evaluating LLMs as Calibrated Direct Causal-Edge Classifiers Amit Kumar, Elnur Adl Zarabi, Kaiqun Fu, Lei Zhang Published: 2026-08-24Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-08-24 | cs.LG | ai-safety, cslg, preprint | E15 / R10 (94%) | - |
| Hierarchy-Aware Supervised Uncertainty Estimation for Black-box LLM Taxonomic Reasoning Graham W. Taylor, Nathaniel Lesperance, Shuting Xie Published: 2026-08-24Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-08-24 | cs.LG | ai-safety, cslg, preprint | - | - |
| How Much Regularization Survives Averaging? Update Masking in Federated Learning Fu Kuroda, Wenhao Yan, Yucheng Jin, Zhenke Chen Published: 2026-08-24Area: cs.LGCitations: 10 Tags: ai-safety, cslg, preprint | 2026-08-24 | cs.LG | ai-safety, cslg, preprint | E7 / R5 (93%) | 10 |
| How Much Regularization Survives Averaging? Update Masking in Federated Learning Fu Kuroda, Wenhao Yan, Yucheng Jin, Zhenke Chen Published: 2026-08-24Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-08-24 | cs.LG | ai-safety, cslg, preprint | - | - |
| How to Train a Critic Stably and Efficiently Penghui Qi, Wee Sun Lee, Xiangxin Zhou Published: 2026-08-24Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-08-24 | cs.LG | ai-safety, cslg, preprint | - | - |
| Learning to Grade Efficiently: A Bandit-Driven Prompt-Selection Framework for Low-Cost LLM Essay Scoring Igor Bogdanov, Olga Manakina Published: 2026-08-24Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-08-24 | cs.LG | ai-safety, cslg, preprint | E8 / R6 (94%) | - |
| MetaCaster: Meta-Harness-Optimized Agent for End-to-End Few-Shot Learning of Lightweight Time Series Forecasters ChengAo Shen, Dongjin Song, Dongsheng Luo, Fangyu Wu Published: 2026-08-24Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-08-24 | cs.LG | ai-safety, cslg, preprint | - | - |
| Multi-Modal Anomaly Detection: A Survey Chuan Luo, Chunming Hu, Renyu Yang, Shiru Chen Published: 2026-08-24Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-08-24 | cs.LG | ai-safety, cslg, preprint | E12 / R12 (92%) | - |
| PolyChirp: Multi-Species Birdsong Classification Using TinyML on Low-Power Acoustic Sensors Antoine Lavandier, Emmanuel Baccelli, Felix Bie脽mann, Nathan Duboisset Published: 2026-08-24Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-08-24 | cs.LG | ai-safety, cslg, preprint | - | - |
| Revelation Control Qinyou Wang Published: 2026-08-24Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-08-24 | cs.LG | ai-safety, cslg, preprint | E7 / R5 (92%) | - |
| Safety Hacking in Constrained Best-of-$N$ Inference-time Scaling Akifumi Wachi, Takumi Tanabe, Youhei Akimoto Published: 2026-08-24Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-08-24 | cs.LG | ai-safety, cslg, preprint | - | - |
| Sigmoid Attention as a Better Substrate for Learned KV Cache Eviction Isaac, Li Published: 2026-08-24Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-08-24 | cs.LG | ai-safety, cslg, preprint | - | - |
| SplitLite: Low-Rank Residual Compression for Split Learning Qi Guo, Tao Li, Xianhao Chen, Yulin Tang Published: 2026-08-24Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-08-24 | cs.LG | ai-safety, cslg, preprint | - | - |