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 |
|---|---|---|---|---|---|
| Analog-Friendly Predictive Coding without Activation Derivatives Francesco Innocenti Published: 2026-09-26Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-26 | cs.LG | ai-safety, cslg, preprint | - | - |
| AnchorRep: Defending LLMs Against Cross-Model Adversarial Transfer via Representation Repulsion Avi Mendelson, Gal Wertheizer, Rom Himelstein, Tomer Peretz Published: 2026-09-26Area: cs.LGCitations: - Tags: adversarial-robustness, ai-safety, cslg, preprint | 2026-09-26 | cs.LG | adversarial-robustness, ai-safety, cslg, preprint | - | - |
| A Solvable Theory of Pre-training Data Poisoning: Regime-Dependent Scaling Exponents Cengiz Pehlevan, Indranil Halder, Rastri Dey Published: 2026-09-26Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-26 | cs.LG | ai-safety, cslg, preprint | - | - |
| Beyond Token Savings: A Systematic Study of Context Compression in LLM Agents Akiho Kawada, Neeraja J. Yadwadkar, Prasoon Sinha, Ritul Satish Published: 2026-09-26Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-26 | cs.LG | ai-safety, cslg, preprint | - | - |
| Bison: Cross-Dataset Learning for Unseen-Compound Perturbation Prediction Chang Yu, Jiangbin Zheng, Jingbo Zhou, Kasra Ghorbani Published: 2026-09-26Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-26 | cs.LG | ai-safety, cslg, preprint | - | - |
| Black-Box Auditing of Epistemic Reliability in Multi-Agent Debate Distillation Derui Wang, Jason Xue, Liming Zhu, Rayne Holland Published: 2026-09-26Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-26 | cs.LG | ai-safety, cslg, preprint | - | - |
| Continual Learning via Self-Probe Gradients Dongkyu Cho, Rumi Chunara, Sungmin Cha Published: 2026-09-26Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-26 | cs.LG | ai-safety, cslg, preprint | - | - |
| DiffPTS: Rethinking Diffusion ELBO for Probabilistic Time Series Forecasting Dongyuan Li, Hangchen Liu, Haotong Jiang, Renhe Jiang Published: 2026-09-26Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-26 | cs.LG | ai-safety, cslg, preprint | - | - |
| DP-Rec: Towards Dynamic Patching for Efficient Long-Sequence Recommendation Akshat Shreemali, Dwipam Katariya, James Montgomery, Juan Manuel Origgi Published: 2026-09-26Area: cs.LGCitations: 15 Tags: ai-safety, cslg, preprint | 2026-09-26 | cs.LG | ai-safety, cslg, preprint | E10 / R8 (93%) | 15 |
| Efficient Message Passing for Partial Differential Equation Priors Anna Kazachkova, Leonhard Hennicke, Rainer Schlosser, Ralf Herbrich Published: 2026-09-26Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-26 | cs.LG | ai-safety, cslg, preprint | - | - |
| Emergent One-Third Scaling Law as Attention Tries to Concentrate Jeff Gore, Sara Kangaslahti, Yizhou Liu Published: 2026-09-26Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-26 | cs.LG | ai-safety, cslg, preprint | E8 / R5 (91%) | - |
| Getting Motif-ated: Controllable AI Compositions from Injected Motif Prompts Chao Peter Yang, Cynthia Rudin, Simon Mak, Stephen Ni-Hahn Published: 2026-09-26Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-26 | cs.LG | ai-safety, cslg, preprint | - | - |
| Intuition vectors Daniel C. McNamee, Shahar Haim Published: 2026-09-26Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-26 | cs.LG | ai-safety, cslg, preprint | - | - |
| Logic Gate Networks and Lookup Table Networks as Lightweight Hardware Classifiers for Inter-patient ECG Arrhythmia Classification Achiel Colpaert, Lars Keuninckx, Paul Detterer, Piet Wambacq Published: 2026-09-26Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-26 | cs.LG | ai-safety, cslg, preprint | - | - |
| 艁ukasiewicz Neural Networks Extended: Residual Architectures and Crystallization Strategies for Interpretable Rule Extraction Carlos Leandro Published: 2026-09-26Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-26 | cs.LG | ai-safety, cslg, preprint | - | - |
| Measurement Boundaries in LLM Financial Agent Evaluation: Fixed-Tape Execution and Multi-Defect Auditing Weicheng Xue Published: 2026-09-26Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint, safety-evaluation | 2026-09-26 | cs.LG | ai-safety, cslg, preprint, safety-evaluation | - | - |
| Mind the Spike: Mechanisms and Brittleness of Visual Massive Activations in Large Vision-Language Models Christian Gagn茅, Fr茅d茅ric Precioso, Jonas Ngnaw茅, Sabyasachi Sahoo Published: 2026-09-26Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-26 | cs.LG | ai-safety, cslg, preprint | - | - |
| Not Every Term Adds New Structure: Sobolev Novelty for Symbolic Regression Boxiao Wang, Chen Li, Jian Cheng, Kai Li Published: 2026-09-26Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-26 | cs.LG | ai-safety, cslg, preprint | - | - |
| Optimizing H-Graph Hybridization for Diffusion-Guided RRT Omer Talmi Published: 2026-09-26Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-26 | cs.LG | ai-safety, cslg, preprint | - | - |
| Phase Space Attention:A Hairer Lift Circumvents the Single-Layer Induction Obstruction Kingsuk Maitra, Shagun Sood Morteza Hosseini, Suman Gunnala, Vikram Gupta Published: 2026-09-26Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-26 | cs.LG | ai-safety, cslg, preprint | - | - |
| REALM: Regime-Switching, Explainable, and Activation-Induced Linear Models Jia Li, Sen Na, Xiaoran Cheng Published: 2026-09-26Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-26 | cs.LG | ai-safety, cslg, preprint | E8 / R6 (93%) | - |
| Refreshing Less, Selecting Better: Reusing Stale Gradient Features for Efficient Influence-Based Data Selection Jianchang Su, Wei Zhang, Yifan Zhang Published: 2026-09-26Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-26 | cs.LG | ai-safety, cslg, preprint | - | - |
| Relative Generalization Invariance of LLM Pretraining Chao Du, Fengzhuo Zhang, Ivor Tsang, Jianliang He Published: 2026-09-26Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-26 | cs.LG | ai-safety, cslg, preprint | - | - |
| Rethinking Training-Inference Mismatch in LLM Reinforcement Learning: Where It Arises and How to Correct It Kaixiang Zhao, Porter Jenkins, Shangzhe Li, Taylor W. Killian Published: 2026-09-26Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-26 | cs.LG | ai-safety, cslg, preprint | - | - |
| Rondo: Unsupervised Discovery of Recurring Temporal Structure Ankith Chandra, Thomas Pl枚tz, Yingtian Shi Published: 2026-09-26Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-26 | cs.LG | ai-safety, cslg, preprint | - | - |
| SoFT: Soft Targets for Generalizable LLM Fine-Tuning Guijia Zhang, Haochen Shi, Haoran Li, Haoyu Huang Published: 2026-09-26Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-26 | cs.LG | ai-safety, cslg, preprint | - | - |
| Spectral Reversal: Counteracting Singular Value Bias for Graph Prompting Hanxu Yang, Xiaodong He, Yuhuan Zhao, Zhao Kang Published: 2026-09-26Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-26 | cs.LG | ai-safety, cslg, preprint | E6 / R6 (92%) | - |
| STAMP: Predicting Out-of-Distribution Generalization without Target Data Md Kawsher Mahbub, Milon Biswas Published: 2026-09-26Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-26 | cs.LG | ai-safety, cslg, preprint | - | - |
| Superposed Inference for Hyperdimensional Computing Nilesh Prasad Pandey, Quanling Zhao, Tajana Rosing, Ye Tian Published: 2026-09-26Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-26 | cs.LG | ai-safety, cslg, preprint | - | - |
| The Extender: A Log-Structured Transformer Jakob Eriksson Published: 2026-09-26Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-09-26 | cs.LG | ai-safety, cslg, preprint | - | - |