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 |
|---|---|---|---|---|---|
| JudgeCast: Time Series Forecasting with Experience-Informed Covariate Judgements Dongha Lee, Donguk Kwon, Wooseok Jeong Published: 2026-09-29Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-29 | cs.LG | ai-safety, cslg, preprint | E10 / R6 (90%) | - |
| JudgeCast: Time Series Forecasting with Experience-Informed Covariate Judgements Dongha Lee, Donguk Kwon, Wooseok Jeong Published: 2026-09-29Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-29 | cs.LG | ai-safety, cslg, preprint | - | - |
| LeapQuant: Efficient Linear Attention with Accurate Recurrent State Quantization Baris Kasikci, Haocheng Xi, Hongtao Zhang, Ion Stoica Published: 2026-09-29Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-29 | cs.LG | ai-safety, cslg, preprint | - | - |
| Learning Beyond What You Sample: Off-Policy-Aware Cross-Model Trajectory Exchange for RLVR Doohyuk Jang, Eunho Yang, Gyouk Chu, Sihwan Park Published: 2026-09-29Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-29 | cs.LG | ai-safety, cslg, preprint | - | - |
| LLMs Learn to Evade Latent Monitors from Prior Feedback Alone Christopher Leckie, Hugo Lyons Keenan, Sarah Erfani Published: 2026-09-29Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-29 | cs.LG | ai-safety, cslg, preprint | - | - |
| Longer Records, Broader Invariance: The Hidden Scaling Problem in Longitudinal Contrastive Learning Danny Yuxing Huang, Jeffrey Kaye, Rameen Mahmood, Xuhai "Orson" Xu Published: 2026-09-29Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-29 | cs.LG | ai-safety, cslg, preprint | - | - |
| LongSpark: Efficient speculative decoding with a fixed-cost parallel drafter Hao-Yuan He, Ming Li, Peng-Fei Liu, Si Shen Published: 2026-09-29Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-29 | cs.LG | ai-safety, cslg, preprint | - | - |
| Loss-Guided Pretraining Data Selection for Time-Series Foundation Models Jianmin Wang, Shaoxu Song, Yike Li Published: 2026-09-29Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-29 | cs.LG | ai-safety, cslg, preprint | - | - |
| Lucid Dreaming for World Models: Learning to Doubt Imagination and Decide by Trust Ching-Yu Cheng, Huazhu Fu, Lianyu Wang, Meng Wang Published: 2026-09-29Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-29 | cs.LG | ai-safety, cslg, preprint | - | - |
| MILO: Automated Harness Discovery via Orchestrated Multi-Agent Evolution Anoop Deoras, Hao Liu, Langlin Huang, Mononito Goswami Published: 2026-09-29Area: cs.LGCitations: 15 Tags: ai-safety, cslg, preprint | 2026-09-29 | cs.LG | ai-safety, cslg, preprint | E21 / R17 (89%) | 15 |
| MM-FinEval: A Multi-Task Multimodal Benchmark for Real-World Financial Forecasting Dong Shu, Haiyan Zhao, Hekun Huang, Huopu Zhang Published: 2026-09-29Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-29 | cs.LG | ai-safety, cslg, preprint | E15 / R10 (90%) | - |
| Multi-Agent Flow Matching with Decoupled Generative Guidance Fabio Pasqualetti, Magnus Egerstedt, Ruoyu Lin Published: 2026-09-29Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-29 | cs.LG | ai-safety, cslg, preprint | E10 / R9 (91%) | - |
| Normalize-Then-Precondition: A Hierarchical Approach to Marginal Scale and Interaction Geometry for LLM Training Jiaye Teng, Yong Liu, Zeyu Gan, Zixuan Gong Published: 2026-09-29Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-29 | cs.LG | ai-safety, cslg, preprint | - | - |
| No Scale Left Behind: Multi-Scale Autoencoder with Bi-directional Attention for Time Series Anomaly Detection Haochen Zhang, Jiaheng Guo, Jinhao Duan, Nicholas Konz Published: 2026-09-29Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-29 | cs.LG | ai-safety, cslg, preprint | - | - |
| NowcastDiT: Diffusion Transformers are Effective Precipitation Nowcasters Haoran Xu, Jianmin Wang, Jincheng Zhong, Mingsheng Long Published: 2026-09-29Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-29 | cs.LG | ai-safety, cslg, preprint | - | - |
| On the Off-Policy Teacher in On-Policy Distillation Hao Liu, Langlin Huang, Mononito Goswami, Nikos Kanakaris Published: 2026-09-29Area: cs.LGCitations: 26 Tags: ai-safety, cslg, preprint | 2026-09-29 | cs.LG | ai-safety, cslg, preprint | E11 / R7 (90%) | 26 |
| On Trajectory-Aware Training for Masked Diffusion Language Models Alice Bizeul, Amitis Shidani, Bhavika Devnani, Dan Busbridge Published: 2026-09-29Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-29 | cs.LG | ai-safety, cslg, preprint | - | - |
| Port-Hamiltonian Latent Deliberation: Mitigating the Deliberation Drift Cliff in Test-Time Compute Scaling Zeyu Jia Published: 2026-09-29Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-29 | cs.LG | ai-safety, cslg, preprint | - | - |
| Predictive Self-Supervised Learning Provably Identifies Stochastic Signals under Nuisance Fabian A. Mikulasch, Friedemann Zenke Published: 2026-09-29Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-29 | cs.LG | ai-safety, cslg, preprint | - | - |
| Privy to the Foil: Recasting Value Estimation with a Self-Privileged Critic for RLVR Chenming Tang, Clive Bai, Kun Liang, Qingyang Zhang Published: 2026-09-29Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-29 | cs.LG | ai-safety, cslg, preprint | - | - |
| ProCTI: Prototype-Refined Global Conditioning for Diffusion-Based Time Series Imputation Aruna Seneviratne, Duc Van Le, Fariza Rashid, Gustavo Batista Published: 2026-09-29Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-29 | cs.LG | ai-safety, cslg, preprint | - | - |
| Provable Test-Time Scaling for Beam Search in LLM Reasoning Qijia He, Yingbin Liang, Yuan Cheng, Yu Huang Published: 2026-09-29Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-29 | cs.LG | ai-safety, cslg, preprint | E8 / R6 (91%) | - |
| ReLaG: A Scalable Framework Generalizing Random Splits to Data with Latent Relations Anthony Lavertu, Isabeau Premont-Schwarz, Jacob Cote, Jacques Corbeil Published: 2026-09-29Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-29 | cs.LG | ai-safety, cslg, preprint | E8 / R7 (92%) | - |
| ReLMem: Learning Recurrent Memory for Longitudinal EHR Modeling Jian Wu, Xian Wu, Xiwei Dai, Yingying Zhang Published: 2026-09-29Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-29 | cs.LG | ai-safety, cslg, preprint | - | - |
| Revisiting scaling laws for reward optimization Ali Aouad, Aymane El Gadarri, Vivek F. Farias Published: 2026-09-29Area: cs.LGCitations: 15 Tags: ai-safety, cslg, preprint | 2026-09-29 | cs.LG | ai-safety, cslg, preprint | E8 / R5 (93%) | 15 |
| RLTL;DR: Self-improvement by Internalizing Self-generated Feedback Abbas Kazerouni, Alexander Toshev, Andrew Szot, Aryo Lotfi Published: 2026-09-29Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-29 | cs.LG | ai-safety, cslg, preprint | - | - |
| Safe-by-Design Learning via Energy-based Neural Networks Luca Laurenti, Morteza Lahijanian, Simone Betteti Published: 2026-09-29Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-29 | cs.LG | ai-safety, cslg, preprint | E6 / R5 (93%) | - |
| Safe-by-Design Learning via Energy-based Neural Networks Luca Laurenti, Morteza Lahijanian, Simone Betteti Published: 2026-09-29Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-29 | cs.LG | ai-safety, cslg, preprint | - | - |
| Scaling Influence Functions in LLMs through Eigenbasis-Corrected One-Bit Gradient Projection Dongwoo Kim, Jaeseung Heo, J Rosser Published: 2026-09-29Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-29 | cs.LG | ai-safety, cslg, preprint | - | - |
| SERA: Scale-Equalized Rollout Allocation for Maximum Likelihood Reinforcement Learning Fanxiang Xiong, Hongran Ren, Kehai Chen, Xuefeng Bai Published: 2026-09-29Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-29 | cs.LG | ai-safety, cslg, preprint | - | - |