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 |
|---|---|---|---|---|---|
| OptiSelect: How does the Optimizer Shape Data Curriculum? Alireza Abdollahpoorrostam, Martin Jaggi, Simin Fan Published: 2026-10-02Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-10-02 | cs.LG | ai-safety, cslg, preprint | - | - |
| Prospective Hindsight: Self-Calibrating Reinforcement Learning via Prediction-Reality Gaps Chien-Sheng Wu, Hiroaki Hayashi, Jiaxin Zhang, Qinglin Chen Published: 2026-10-02Area: cs.LGCitations: 45 Tags: ai-safety, cslg, preprint | 2026-10-02 | cs.LG | ai-safety, cslg, preprint | E8 / R6 (92%) | 45 |
| Rethinking Epistemic Uncertainty in Node Classification through Information Growth Andrea Passerini, Bruno Lepri, Emma Meneghini, Francesco Ferrini Published: 2026-10-02Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-10-02 | cs.LG | ai-safety, cslg, preprint | - | - |
| Retrieval-Centric Deep Learning in Growing Nonparametric Neural Networks Jo茫o Sacramento, Johannes von Oswald, Kazuki Irie, Maximilian Schlegel Published: 2026-10-02Area: cs.LGCitations: 15 Tags: ai-safety, cslg, preprint | 2026-10-02 | cs.LG | ai-safety, cslg, preprint | E8 / R7 (92%) | 15 |
| Robust blind unmixing: A geometric approach to overcoming basis variation Dumitru Mirauta, Matthew J. Rosseinsky, Michael W. Gaultois, Vladimir V. Gusev Published: 2026-10-02Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-10-02 | cs.LG | ai-safety, cslg, preprint | E7 / R6 (93%) | - |
| SEER: Self-Evolving Event Reasoning and Retrieval for Time Series Forecasting Chun-Liang Li, Jinsung Yoon, Mihir Parmar, Mingtian Tan Published: 2026-10-02Area: cs.LGCitations: 15 Tags: ai-safety, cslg, preprint | 2026-10-02 | cs.LG | ai-safety, cslg, preprint | E8 / R6 (91%) | 15 |
| Selective Backpropagation for Efficient Few-Shot Class-Incremental Learning Abdulmoumen Al-Atrash, Ali Ayub, Eeham Khan Published: 2026-10-02Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-10-02 | cs.LG | ai-safety, cslg, preprint | E10 / R7 (94%) | - |
| Sentry: Learning to Recover from LLM Agent Failures at Test Time Amy Lu, Changxiu Ji, Kunle Olukotun, Qizheng Zhang Published: 2026-10-02Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-10-02 | cs.LG | ai-safety, cslg, preprint | - | - |
| Single or Multiple Policies for Phase-Structured Reinforcement Learning? Guilhem Loussouarn, Kin K. Leung, Nancy Nayak Published: 2026-10-02Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-10-02 | cs.LG | ai-safety, cslg, preprint | - | - |
| Slaying the Hydra: Interaction-Aware Circuit Discovery in Language Models Daniel Waxman, Emily Bunnapradist, Michelangelo Naim, Rafal Urbaniak Published: 2026-10-02Area: cs.LGCitations: 12 Tags: ai-safety, cslg, preprint | 2026-10-02 | cs.LG | ai-safety, cslg, preprint | E15 / R7 (96%) | 12 |
| SPEAR: A Spectral-Disentangled MoE Neural Operator with Knowledge-Guided Expert Aggregation for Large-Scale PDE Pretraining Bin Luo, Dengdi Sun, Jin Tang, Wanli Lyu Published: 2026-10-02Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-10-02 | cs.LG | ai-safety, cslg, preprint | - | - |
| Tailoring the Quantization Space for 1-Bit KV Cache Compression Donghyun Son, Minsoo Cheong, Sungjoo Yoo Published: 2026-10-02Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-10-02 | cs.LG | ai-safety, cslg, preprint | - | - |
| Temporal Geometry of Deep Networks: Hyperbolic Representations of Training Dynamics for Intrinsic Explainability Ambarish Moharil Published: 2026-10-02Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-10-02 | cs.LG | ai-safety, cslg, preprint | - | - |
| Test-time Calibration Learning for Large Language Model Reasoning Bo Han, Jingwei Sun, Mingxuan Yuan, Rong Yao Published: 2026-10-02Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-10-02 | cs.LG | ai-safety, cslg, preprint | E9 / R7 (90%) | - |
| Training-Loss Guarantees for Muon with Finite-Step Newton--Schulz Orthogonalization Amartya Roy, Souvik Chakraborty Published: 2026-10-02Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-10-02 | cs.LG | ai-safety, cslg, preprint | - | - |
| ULTRADISCOVERY: Abductive Exploration in an Interconnected, Epistemically Open Universe Ginny Y. Wong, Simon See, Tianshi Zheng, Weihan Li Published: 2026-10-02Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-10-02 | cs.LG | ai-safety, cslg, preprint | - | - |
| WebFovea: When the Model Is Right but the Click Is Wrong -- Reliable Round Trips for Vision-Based Web Agents on Live Websites Jiangang Han Published: 2026-10-02Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-10-02 | cs.LG | ai-safety, cslg, preprint | - | - |
| WebFovea: When the Model Is Right but the Click Is Wrong -- Reliable Round Trips for Vision-Based Web Agents on Live Websites Jiangang Han Published: 2026-10-02Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-10-02 | cs.LG | ai-safety, cslg, preprint | E11 / R9 (98%) | - |
| What Should World Models Forget? Stratified Retention for Continual Adaptation Dinesh Manocha, Nishit Anand, Ramani Duraiswami Published: 2026-10-02Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-10-02 | cs.LG | ai-safety, cslg, preprint | - | - |
| When Can We Trust the Matching Principle? Robust Deployment Geometry Under Finite-Sample and Model Uncertainty Vishal Rajput Published: 2026-10-02Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-10-02 | cs.LG | ai-safety, cslg, preprint | - | - |
| Zephon: Elastic Determinism for Online, Stateful Foundation Model Data Loading Pipelines Ana Klimovic, Ari Morcos, Bogdan Gaza, Cody Blakeney Published: 2026-10-02Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-10-02 | cs.LG | ai-safety, cslg, preprint | - | - |
| $唯$-Resilience: Model-Free Feature Importance from 1D Topological Signals Darian Onchis, Fabian Galis, Pedro Real Jurado Published: 2026-10-01Area: cs.LGCitations: 23 Tags: ai-safety, cslg, preprint | 2026-10-01 | cs.LG | ai-safety, cslg, preprint | E9 / R6 (93%) | 23 |
| Are you Synthesizing or Recalling? Evaluating LLMs on Algorithmic Code Retrieval Antonio Vergari, Nickil Maveli, Shay B. Cohen Published: 2026-10-01Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-10-01 | cs.LG | ai-safety, cslg, preprint | E19 / R14 (93%) | - |
| Asynchronous LLM Post-Training: Group-Mass Capping and Convergence Analysis Jun Luo, Qijia He, Ruinan Jin, Shaofeng Zou Published: 2026-10-01Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-10-01 | cs.LG | ai-safety, cslg, preprint | E6 / R4 (92%) | - |
| Auto-Formalizing Neuro-Symbolic Predictors Andrea Passerini, Antonio Vergari, Han Zhao, Samuele Bortolotti Published: 2026-10-01Area: cs.LGCitations: 15 Tags: ai-safety, cslg, preprint | 2026-10-01 | cs.LG | ai-safety, cslg, preprint | E12 / R10 (89%) | 15 |
| Beyond Pointwise Error: A Multi-Metric Evaluation of Spatial Climate Downscaling Etienne Le Naour, Loys Masquelier Published: 2026-10-01Area: cs.LGCitations: 29 Tags: ai-safety, cslg, preprint, safety-evaluation | 2026-10-01 | cs.LG | ai-safety, cslg, preprint, safety-evaluation | E14 / R9 (94%) | 29 |
| CARM: Cancellation-Aware Response Masking for LLM Reinforcement Learning Sicong Liao, Songshuo Lu, Yafei Zhang, Yaohua Tang Published: 2026-10-01Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-10-01 | cs.LG | ai-safety, cslg, preprint | E15 / R16 (92%) | - |
| Counterfactual Generation via Flow Matching: Coupling-Sensitive End-to-End Rates Krishnakumar Balasubramanian, Shiva Prasad Kasiviswanathan, Yunrui Guan Published: 2026-10-01Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-10-01 | cs.LG | ai-safety, cslg, preprint | E13 / R10 (96%) | - |
| Cross-Benchmark Transfer from RL on Agentic Coding Tasks Edwin Chen, Logan Ritchie, Sushant Mehta Published: 2026-10-01Area: cs.LGCitations: 15 Tags: ai-safety, cslg, preprint | 2026-10-01 | cs.LG | ai-safety, cslg, preprint | E13 / R15 (96%) | 15 |
| Detect, Explain, Interpret: An End-to-End Benchmark for Time Series Anomaly Detection, Explainability and Interpretability J茅r茅mie Fourmann, Jules Barbe, Magali Parrino, Paul Boniol Published: 2026-10-01Area: cs.LGCitations: - Tags: ai-safety, cslg, interpretability, preprint | 2026-10-01 | cs.LG | ai-safety, cslg, interpretability, preprint | E10 / R6 (90%) | - |