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 |
|---|---|---|---|---|---|
| Iterative tensor network transformations for element-wise evaluation of elementary and filtering functions Dieter Jaksch, Pia Siegl, Tomohiro Hashizume, Xiao Wang Published: 2026-08-17Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint, safety-evaluation | 2026-08-17 | cs.LG | ai-safety, cslg, preprint, safety-evaluation | E8 / R6 (94%) | - |
| Learning to Unlearn: Machine Unlearning via Learning the Unlearning Behaviors Hang Zhang, Kaifeng Zhang, Kai Ming Ting, Weijie Xu Published: 2026-08-17Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-08-17 | cs.LG | ai-safety, cslg, preprint | E8 / R6 (90%) | - |
| Learn What's Left, Not What's Mastered: Saturation Aware Advantage Reweighting for Multi-Reward Policy Optimization Haichao Zhang, Haozheng Luo, Jie Ni, Nuno Vasconcelos Published: 2026-08-17Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-08-17 | cs.LG | ai-safety, cslg, preprint | E8 / R7 (91%) | - |
| NICE: Scale-Stable Perturbations for Graph Neural Network Explanations via Noise Corruption Chengqi Zhang, Jun Yin, Ming Cheng, Ruochen Liu Published: 2026-08-17Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-08-17 | cs.LG | ai-safety, cslg, preprint | E7 / R5 (95%) | - |
| NICE: Scale-Stable Perturbations for Graph Neural Network Explanations via Noise Corruption Chengqi Zhang, Jun Yin, Ming Cheng, Ruochen Liu Published: 2026-08-17Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-08-17 | cs.LG | ai-safety, cslg, preprint | E10 / R7 (93%) | - |
| OceanDepths: A Global Dataset of Paired Subsurface and Surface Ocean Observations Antonino Ian Ferola, Diego Fernandez Prieto, Elisa Carli, Marie-Helene Rio Published: 2026-08-17Area: cs.LGCitations: 37 Tags: ai-safety, cslg, preprint | 2026-08-17 | cs.LG | ai-safety, cslg, preprint | E13 / R16 (91%) | 37 |
| OceanDepths: A Global Dataset of Paired Subsurface and Surface Ocean Observations Antonino Ian Ferola, Diego Fernandez Prieto, Elisa Carli, Marie-Helene Rio Published: 2026-08-17Area: cs.LGCitations: 37 Tags: ai-safety, cslg, preprint | 2026-08-17 | cs.LG | ai-safety, cslg, preprint | E10 / R12 (93%) | 37 |
| OceanLight: Efficient Global Ocean Forecasting via Geometry-Adaptive Unstructured Mesh Representation Hongze Leng, Junqiang Song, Junxing Zhu, Qingye Min Published: 2026-08-17Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-08-17 | cs.LG | ai-safety, cslg, preprint | E10 / R8 (92%) | - |
| PertMind: Eliciting Emergent Biological Reasoning in LLM via Reinforcement Learning on Cellular Perturbation Data Hanbo Huang, Haohuai He, Jiafei Wu, Jiahui Guan Published: 2026-08-17Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-08-17 | cs.LG | ai-safety, cslg, preprint | E13 / R12 (93%) | - |
| Position: Fairness Failure in Generative Models is an Evaluation Problem Jean-Yves Franceschi, Mariia Vladimirova, Thibaut Issenhuth Published: 2026-08-17Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint, safety-evaluation | 2026-08-17 | cs.LG | ai-safety, cslg, preprint, safety-evaluation | E2 / R6 (91%) | - |
| Proteus: Incremental Memory Activation for Long-Context Sequence Modeling Aaron Courville, Ali Behrouz, Reza Bayat, Vahab Mirrokni Published: 2026-08-17Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-08-17 | cs.LG | ai-safety, cslg, preprint | E8 / R8 (91%) | - |
| Q-Learning With World Models Chelsea Finn, Dorsa Sadigh, Perry Dong, Yueru Jia Published: 2026-08-17Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-08-17 | cs.LG | ai-safety, cslg, preprint | E8 / R8 (91%) | - |
| RagGAD: Rationale-Aware Conditional Gaussian Mixture Normalizing Flow for Unsupervised Graph Anomaly Detection Jing Zhao, Junxin Lu, Shiliang Sun Published: 2026-08-17Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-08-17 | cs.LG | ai-safety, cslg, preprint | E8 / R7 (92%) | - |
| RetroMPA: A Molecular Property-Aware Auxiliary Framework for Enhancing Retrosynthesis Prediction Fan Xiao, Huayang Huang, Mianzhi Liu, Wenbo Liu Published: 2026-08-17Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-08-17 | cs.LG | ai-safety, cslg, preprint | E13 / R11 (92%) | - |
| Task Specialization Fine-Tuning for Contextual Reinforcement Learning Cathy Wu, Han Zheng, Jianan Zhou, Jie Zhang Published: 2026-08-17Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-08-17 | cs.LG | ai-safety, cslg, preprint | E8 / R6 (92%) | - |
| Understanding and Stabilizing Deep Q-Learning via Controlled Bootstrapping and Regulated Value Dynamics Bozhou Chen, Hanyu Liu, Wenxin Li, Xionghui Yang Published: 2026-08-17Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-08-17 | cs.LG | ai-safety, cslg, preprint | E10 / R7 (93%) | - |
| UniTAC: Universal Task-Aware Compression via Weighted Distortion Measures Harish Viswanathan, Homa Esfahanizadeh, Jinfeng Du, Matin Mortaheb Published: 2026-08-17Area: cs.LGCitations: 29 Tags: ai-safety, cslg, preprint | 2026-08-17 | cs.LG | ai-safety, cslg, preprint | E10 / R8 (86%) | 29 |
| Would this change your answer? Evaluating Explanations of LLM Behavior In The Wild with Counterfactual Experiments Adam Karvonen, Euan Ong, Samuel Marks, Subhash Kantamneni Published: 2026-08-17Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-08-17 | cs.LG | ai-safety, cslg, preprint | E8 / R8 (92%) | - |
| Amortised Post-Hoc Explanation with Exact Preservation for Dynamic Graph Anomaly Detectors Hamida Seba, Iyad Assaad Nekka, Karima Amrouche, Walid Khaled Hidouci Published: 2026-08-16Area: cs.LGCitations: 20 Tags: ai-safety, cslg, preprint | 2026-08-16 | cs.LG | ai-safety, cslg, preprint | E15 / R8 (91%) | 20 |
| Feasible and Novel Synthetic Population Generation with Tabular and Sequential Travel Attributes Bilal Farooq, Farbod Abbasi, Zachary Patterson Published: 2026-08-16Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-08-16 | cs.LG | ai-safety, cslg, preprint | E11 / R11 (96%) | - |
| FirstDiff: One-Step Diffusion-Based Anomaly Detection for Multivariate Time Series via Initial Noise Prediction Ali Boudaghi, Alireza Nemati, Hadi Zare Published: 2026-08-16Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-08-16 | cs.LG | ai-safety, cslg, preprint | E10 / R9 (93%) | - |
| FluxBin: Flexible LUT-based Ultra-low-bit LLM Inference by Algorithm-Kernel Synergy Chenchen Ding, Haobo Liu, He Xiao, Junyu Chen Published: 2026-08-16Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-08-16 | cs.LG | ai-safety, cslg, preprint | E9 / R7 (95%) | - |
| GraniKV: Asymmetric Granularity KV-Cache Paging for Multi-Agent Systems with Long Shared Prefix Jinhyun Jeon, Sungjoo Yoo Published: 2026-08-16Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-08-16 | cs.LG | ai-safety, cslg, preprint | E11 / R10 (94%) | - |
| Information Geometry of Message Passing Alex Ledbetter, 陌smail 艦en枚z, Kyrylo Yemets, Mykola Lukashchuk Published: 2026-08-16Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-08-16 | cs.LG | ai-safety, cslg, preprint | E10 / R5 (93%) | - |
| Layers Matter: Why Continual Learning Regularization Should Be Layer-Adaptive Ahmed Anwar, Andreas Dengel, Brian B. Moser, Federico Raue Published: 2026-08-16Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-08-16 | cs.LG | ai-safety, cslg, preprint | E8 / R6 (94%) | - |
| Not All Attention Is Equal: A Quantitative Survey of the EEI Trade-off Aditya Singh Published: 2026-08-16Area: cs.LGCitations: 63 Tags: ai-safety, cslg, preprint | 2026-08-16 | cs.LG | ai-safety, cslg, preprint | E59 / R36 (93%) | 63 |
| Optimal Lower Bounds for Networked Information Aggregation Ambar Pal Published: 2026-08-16Area: cs.LGCitations: 2 Tags: ai-safety, cslg, preprint | 2026-08-16 | cs.LG | ai-safety, cslg, preprint | E7 / R4 (93%) | 2 |
| PL-Guard: Probabilistic Logic Reasoning for LLM Guardrails Erman Acar, Giovanni Sileno, Satchit Chatterji, Shihan Wang Published: 2026-08-16Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-08-16 | cs.LG | ai-safety, cslg, preprint | E8 / R6 (92%) | - |
| Routing Divergence Is Not Evidence of Behavioral Influence in Same-Weight MoE Self-Distillation Cedric Caruzzo, Donggeun Yoo, Tae Soo Kim Published: 2026-08-16Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-08-16 | cs.LG | ai-safety, cslg, preprint | E14 / R9 (92%) | - |
| Sparse Prototype Code Underlies Classification and Prediction Across Modalities Daniel D. Lee, Haim Sompolinsky, Yehonatan Avidan Published: 2026-08-16Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-08-16 | cs.LG | ai-safety, cslg, preprint | E8 / R6 (90%) | - |