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 |
|---|---|---|---|---|---|
| Multi-Agent Coordination via Support-Preserving Distillation Chanmi Lee, Sangmin Lee, Sung-eui Yoon, Youngju Na Published: 2026-10-07Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-10-07 | cs.LG | ai-safety, cslg, preprint | E8 / R7 (92%) | - |
| Multi-Agent Coordination via Support-Preserving Distillation Chanmi Lee, Sangmin Lee, Sung-eui Yoon, Youngju Na Published: 2026-10-07Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-10-07 | cs.LG | ai-safety, cslg, preprint | E8 / R7 (92%) | - |
| Multimodal LLMs Can Learn to Read Brain Signals: A Vision--Language Model for Unified Multi-Task EEG Decoding Maryam M. Shanechi, Omid Sharafi, Parastoo Azizeddin Published: 2026-10-07Area: cs.LGCitations: 63 Tags: ai-safety, cslg, preprint | 2026-10-07 | cs.LG | ai-safety, cslg, preprint | E10 / R9 (89%) | 63 |
| Node-level Graph Neural Architecture Search Framework Baisong Liu, Chengbin Peng, Lintao Yanga, Pietro Li貌 Published: 2026-10-07Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-10-07 | cs.LG | ai-safety, cslg, preprint | E10 / R9 (91%) | - |
| Nullify: Null-Space Activation Steering for Training-Free LLM Unlearning Dejing Dou, Lemao Liu, Qiang Huang, Rui Qian Published: 2026-10-07Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-10-07 | cs.LG | ai-safety, cslg, preprint | E10 / R9 (92%) | - |
| Optimizing Large Language Models with Chained LMOs Kaan Ozkara, Sungyoon Kim, Youngsuk Park Published: 2026-10-07Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-10-07 | cs.LG | ai-safety, cslg, preprint | E8 / R7 (93%) | - |
| Phase-HDC: Replacing Optimizer History with Gradient Thresholds in Discrete Phase Learning Ahmed Nebli Published: 2026-10-07Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-10-07 | cs.LG | ai-safety, cslg, preprint | E7 / R6 (90%) | - |
| Q-Learning with Scalar Adjoint Matching Changyeon Kim, Jaehyuk Kim, Jinwoo Shin, Jungwoo Park Published: 2026-10-07Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-10-07 | cs.LG | ai-safety, cslg, preprint | E8 / R6 (93%) | - |
| Rethinking the Tradeoff Between Temporal Encoding and Nonlinear Computation in Spiking Language Models Changzeng Fu, Hanfei Liu, Shiqi Zhao, Shuchang Feng Published: 2026-10-07Area: cs.LGCitations: 15 Tags: ai-safety, cslg, preprint | 2026-10-07 | cs.LG | ai-safety, cslg, preprint | E8 / R7 (94%) | 15 |
| RollVerify: Bridging Efficiency and Accuracy in Long-Tail Rollout Reinforcement Learning Dahua Lin, Jinru Tan, Kaihuan Liang, Ningyi Xu Published: 2026-10-07Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-10-07 | cs.LG | ai-safety, cslg, preprint | E8 / R7 (92%) | - |
| Safe on Average, Unsafe in the Tail: When Is the Episodic-Cost Tail Controllable? Cody Fleming, Samuel Tetteh Published: 2026-10-07Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-10-07 | cs.LG | ai-safety, cslg, preprint | E23 / R11 (94%) | - |
| SemanticFold: Latent Sequence Compression SeparatesLanguage Modeling, Decodability, and Reasoning Mingyan Liu, Min Huang Published: 2026-10-07Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-10-07 | cs.LG | ai-safety, cslg, preprint | E13 / R11 (94%) | - |
| Shared Geometry As A Rosetta Stone: Cross-Modal Alignment Without Paired Data Daniel Cremers, Dominik Schnaus, Phillip Isola, Thomas Dag猫s Published: 2026-10-07Area: cs.LGCitations: 45 Tags: ai-safety, alignment-training, cslg, preprint | 2026-10-07 | cs.LG | ai-safety, alignment-training, cslg, preprint | E10 / R7 (93%) | 45 |
| Shared Geometry As A Rosetta Stone: Cross-Modal Alignment Without Paired Data Daniel Cremers, Dominik Schnaus, Phillip Isola, Thomas Dag猫s Published: 2026-10-07Area: cs.LGCitations: 15 Tags: ai-safety, alignment-training, cslg, preprint | 2026-10-07 | cs.LG | ai-safety, alignment-training, cslg, preprint | E9 / R7 (92%) | 15 |
| Shared Low-rank Basis Factorization for Data-free Mixture-of-Experts Compression Hisashi Kashima, Jiahe Shao, Kyohei Atarashi, Qibin Zhao Published: 2026-10-07Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-10-07 | cs.LG | ai-safety, cslg, preprint | E9 / R9 (90%) | - |
| Stationary Bias and Extrapolation in Nonlinear Two-Timescale Stochastic Approximation A. Ch. Madhusudanarao, Rahul Singh Published: 2026-10-07Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-10-07 | cs.LG | ai-safety, cslg, preprint | E9 / R5 (91%) | - |
| Stream-Based Active Learning with Cooperative Neural Networks for Data-Efficient Partial Inverse Design: An Automotive Glass Run Channel Case Study Agung Nugraha, Gian Antariksa, Heungjun Im, Hyerin Kwon Published: 2026-10-07Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-10-07 | cs.LG | ai-safety, cslg, preprint | E7 / R6 (95%) | - |
| Temporal Predictive Multiplicity: Equally Accurate Time Series Models Yield Different Forecast Trajectories Emanuele Albini, Francesca Toni, Francesco Leofante, Saumitra Mishra Published: 2026-10-07Area: cs.LGCitations: 25 Tags: ai-safety, cslg, preprint | 2026-10-07 | cs.LG | ai-safety, cslg, preprint | E8 / R8 (92%) | 25 |
| TRACE: A Governance Framework for Measuring Explainability Debt in Production AI Systems Harish Kant Pathak Published: 2026-10-07Area: cs.LGCitations: 28 Tags: ai-safety, cslg, preprint | 2026-10-07 | cs.LG | ai-safety, cslg, preprint | E12 / R6 (93%) | 28 |
| Training Parallel Speculative Draft Models by Directly Minimizing Expected Decoding Rounds Changxiao Cai, Yunxiao Zhao Published: 2026-10-07Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-10-07 | cs.LG | ai-safety, cslg, preprint | E7 / R6 (93%) | - |
| Unrolled Flow Models for Reasoning Faissal Izermine, Hanru Bai, Oscar Davis, T. Konstantin Rusch Published: 2026-10-07Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-10-07 | cs.LG | ai-safety, cslg, preprint | E10 / R8 (91%) | - |
| Visible Reasoning Is Not a Universal Optimizer: Persona- and Thinking-Dependent Effects in Analytics Code Generation Bhawani Shankar Leelar, Davin Hill, Pawan Chorasiya, Robert E. Tillman Published: 2026-10-07Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-10-07 | cs.LG | ai-safety, cslg, preprint | E11 / R11 (94%) | - |
| Accelerating the Development of PLGA In Situ Forming Depots Through AI-Driven Multi-Objective Optimization Bahar Yeniad, Brigitte A. G. Lamers, Christine Allen, Gary Tom Published: 2026-10-06Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-10-06 | cs.LG | ai-safety, cslg, preprint | - | - |
| Algorithmic Scratchpads and Curriculum Staging for Arithmetic Reasoning in Tiny Transformers Sourabh Kasliwal Published: 2026-10-06Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-10-06 | cs.LG | ai-safety, cslg, preprint | E12 / R11 (92%) | - |
| Atom-JEPA: Joint-Embedding Predictive Architecture for 3D Atomistic Systems Fran莽ois R J Cornet, Kasper Helverskov Petersen, Mikkel Jordahn, Mikkel N. Schmidt Published: 2026-10-06Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-10-06 | cs.LG | ai-safety, cslg, preprint | - | - |
| Complementary Feature Domains: Information Preservation Does Not Imply Predictive-Contribution Preservation Farouk Ganiyu-Adewumi, Timothy Oladunni Published: 2026-10-06Area: cs.LGCitations: 13 Tags: ai-safety, cslg, preprint | 2026-10-06 | cs.LG | ai-safety, cslg, preprint | E10 / R7 (92%) | 13 |
| Conditional Accuracy Profiles: Diagnosing LLM Judges across Deployment Conditions Bin Liu, Chuanbo Hu, Mindi Ruan, Minglei Yin Published: 2026-10-06Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-10-06 | cs.LG | ai-safety, cslg, preprint | E13 / R7 (95%) | - |
| Consistent Distribution Matching for Data-Free Diffusion Distillation Lele Wang, Purang Abolmaesumi, Qi Yan, Renjie Liao Published: 2026-10-06Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-10-06 | cs.LG | ai-safety, cslg, preprint | E7 / R7 (91%) | - |
| Convex-Concave Reinforcement Learning Dhawal Gupta, Philip Thomas, Scott Niekum, Shripad V. Deshmukh Published: 2026-10-06Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-10-06 | cs.LG | ai-safety, cslg, preprint | E9 / R8 (93%) | - |
| CurveTQ: Rotation-Free Trellis Quantization of LLM Weights via Curvature-Weighted Search Guanhua Ding, Jack Liu, Ruichao Li, Zi Wang Published: 2026-10-06Area: cs.LGCitations: 15 Tags: ai-safety, cslg, preprint | 2026-10-06 | cs.LG | ai-safety, cslg, preprint | E13 / R10 (93%) | 15 |