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 |
|---|---|---|---|---|---|
| Training-Free Hashing-Based Attention via Binary Principal Components Daohai Yu, Keyu Chen, Luxi Lin, Rongrong Ji Published: 2026-08-05Area: cs.LGCitations: 15 Tags: ai-safety, cslg, preprint | 2026-08-05 | cs.LG | ai-safety, cslg, preprint | E13 / R15 (90%) | 15 |
| Tropical Algebraic Geometry for Neuronal Representations: An Arakelov-Green Measure Based Descriptor for Graph Learning Qihuang Zhang, Shucheng Cao, Weihan Xu, Xuehai Zhou Published: 2026-08-05Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-08-05 | cs.LG | ai-safety, cslg, preprint | - | - |
| Why the Third Axis Is Freedom Michael Timothy Bennett Published: 2026-08-05Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-08-05 | cs.LG | ai-safety, cslg, preprint | E6 / R5 (93%) | - |
| Agentic Reinforcement Learning with Self-Distilled Reward Shaping Chao Wang, Chenshaodong, Guinan Chen, Jinghao Lin Published: 2026-08-04Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-08-04 | cs.LG | ai-safety, cslg, preprint | - | - |
| A Graph Signal Processing Perspective on Numerical Sequence Representations in LLM In-Context Learning Christopher J. Earls, Gurbir Arora, Jiajun Bao, Nicolas Boull茅 Published: 2026-08-04Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-08-04 | cs.LG | ai-safety, cslg, preprint | E11 / R7 (91%) | - |
| Approximate Speculative Decoding Wang Kang, Wenshuai Yao, Wenyong Zhou, Yizhe Chen Published: 2026-08-04Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-08-04 | cs.LG | ai-safety, cslg, preprint | - | - |
| A Theory of Conditional Collapse under Low-Rank Weight-Space Ablations: I. The Single-Block Theory and Synthetic Validation Abdallah Khemais Published: 2026-08-04Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-08-04 | cs.LG | ai-safety, cslg, preprint | - | - |
| A Theory of Conditional Collapse under Low-Rank Weight-Space Ablations: I. The Single-Block Theory and Synthetic Validation Abdallah Khemais Published: 2026-08-04Area: cs.LGCitations: 16 Tags: ai-safety, cslg, preprint | 2026-08-04 | cs.LG | ai-safety, cslg, preprint | E10 / R6 (91%) | 16 |
| Enhancing VLM Reward Models Through Structure-Aware Fine-Tuning Andreas Krause, Chenhao Li, Pyrros Koussios, Xin Chen Published: 2026-08-04Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-08-04 | cs.LG | ai-safety, cslg, preprint | - | - |
| FedCritic-MIMO: Communication-Efficient Serverless Federated Critic Learning for Massive-MIMO Resource Control in Open and Disaggregated 6G RANs Amin Farajzadeh, Melike Erol-Kantarci Published: 2026-08-04Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-08-04 | cs.LG | ai-safety, cslg, preprint | E12 / R8 (91%) | - |
| FinVerse: Financial Time-Series Benchmark Dongwan Kang, Hwanil Choi, Jaehoon Lee, Junhyeok Kang Published: 2026-08-04Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-08-04 | cs.LG | ai-safety, cslg, preprint | - | - |
| GENESIS: Towards Explainable Causal Discovery Abhinav Thorat, Harsh Vardhan Singh Chauhan, Niranjan Pedanekar, Ravi Kumar Kolla Published: 2026-08-04Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-08-04 | cs.LG | ai-safety, cslg, preprint | - | - |
| LaPrune: Controllable Differentiable Sparsity at Million Scale Jacek Tabor, Jakub Antczak, Joanna Wojciechowicz, 艁ukasz Struski Published: 2026-08-04Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-08-04 | cs.LG | ai-safety, cslg, preprint | E7 / R8 (93%) | - |
| Lightweight Chunk Selection for Mobile Retrieval-Augmented Generation Jiefu Chen, Renjie Hu, Sicong Chang, Wen Yu Published: 2026-08-04Area: cs.LGCitations: 39 Tags: ai-safety, cslg, preprint | 2026-08-04 | cs.LG | ai-safety, cslg, preprint | E10 / R10 (93%) | 39 |
| LiNC: Lightweight Noise Correction via Per-Sample Trust and Gaussian Mixture Modeling Abhishek Moturu, Anna Goldenberg, Babak Taati Published: 2026-08-04Area: cs.LGCitations: 26 Tags: ai-safety, cslg, preprint | 2026-08-04 | cs.LG | ai-safety, cslg, preprint | E7 / R5 (94%) | 26 |
| Out-Of-The-Loop Multi-Fidelity Bayesian Optimization Agustinus Kristiadi, Gustavo Sutter, Hao Wang, Luis Ricardez-Sandoval Published: 2026-08-04Area: cs.LGCitations: 15 Tags: ai-safety, cslg, preprint | 2026-08-04 | cs.LG | ai-safety, cslg, preprint | E7 / R5 (92%) | 15 |
| Pin Once, Swap Light: Subspace-Aligned Centroid-Residual Training for Efficient Ultra-LoRA Serving Huazheng Wang, Pengcheng Wang, Saurabh Bagchi, Xiang Li Published: 2026-08-04Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-08-04 | cs.LG | ai-safety, cslg, preprint | - | - |
| PLAN: Parallel Liquid-Inspired Approximation Network for Efficient Representation Learning in Flexible Job Shop Scheduling Anupam Trivedi, Dhivya Dharshini Kannan, Jieyi Bi, Jie Zhang Published: 2026-08-04Area: cs.LGCitations: 15 Tags: ai-safety, cslg, preprint | 2026-08-04 | cs.LG | ai-safety, cslg, preprint | E8 / R7 (90%) | 15 |
| PRISM: Powerful Time Series to Image (TS2I) Representations for Multivariate Anomaly Detection Kamil Faber, Mateusz Smendowski, Nathalie Japkowicz, Piotr Nawrocki Published: 2026-08-04Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-08-04 | cs.LG | ai-safety, cslg, preprint | - | - |
| Recurrent Residual Quantization: A Progressive Multi-Precision Representation for LLMs Bo Dong, Haihao Shen, Wenhua Cheng, Yu Luo Published: 2026-08-04Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-08-04 | cs.LG | ai-safety, cslg, preprint | E8 / R5 (91%) | - |
| Robust and Personalized Federated Learning for Aircraft-Engine Prognostics under Benign and Adversarial Client Heterogeneity Chinmoy Mitra, Md. Mehedi Hasan Nipu, Md. Rakibul Islam, M. F. Mridha Published: 2026-08-04Area: cs.LGCitations: 15 Tags: adversarial-robustness, ai-safety, cslg, preprint | 2026-08-04 | cs.LG | adversarial-robustness, ai-safety, cslg, preprint | E10 / R8 (94%) | 15 |
| Shorter Reasoning, Earlier Answers? An Evaluation of Reasoning Interfaces Andres Algaba, Francesca Carlon, Vincent Ginis Published: 2026-08-04Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint, safety-evaluation | 2026-08-04 | cs.LG | ai-safety, cslg, preprint, safety-evaluation | - | - |
| SJEPA: Learning Elegant Latent Dynamics with Hybrid Symbolic-Neural Predictors Yongchao Huang Published: 2026-08-04Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-08-04 | cs.LG | ai-safety, cslg, preprint | E6 / R6 (92%) | - |
| SMOPD: Multi-Reward Reinforcement Learning via Specialize-and-Merge Online Policy Distillation Guanjun Jiang, Haotian Zhou, Haoxuan Ma, Jiahua Bao Published: 2026-08-04Area: cs.LGCitations: 15 Tags: ai-safety, cslg, preprint | 2026-08-04 | cs.LG | ai-safety, cslg, preprint | E21 / R16 (91%) | 15 |
| Spatiotemporal Graph Transformer for Traffic Intelligence in Edge Computing Laha Ale, Letian Lin, Na Cao, Peng Yu Published: 2026-08-04Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-08-04 | cs.LG | ai-safety, cslg, preprint | E9 / R7 (93%) | - |
| Spend Bits Where Queries Look: KV Cache Vector Quantization with Attention-Preserving Transforms Amir Ziashahabi, Antonio Ortega, Eduardo Pavez, Salman Avestimehr Published: 2026-08-04Area: cs.LGCitations: 15 Tags: ai-safety, cslg, preprint | 2026-08-04 | cs.LG | ai-safety, cslg, preprint | E12 / R8 (90%) | 15 |
| SynEnergy: Anomaly Semantic-Guided Diffusion for Synthetic Energy Data Generation Dahai Yu, Guang Wang, Lin Jiang, Ravikumar Gelli Published: 2026-08-04Area: cs.LGCitations: 57 Tags: ai-safety, cslg, preprint | 2026-08-04 | cs.LG | ai-safety, cslg, preprint | E12 / R10 (92%) | 57 |
| Test-Time Scaling in Reasoning LLMs: Inference Regimes, Evaluation, and Reproducibility Amirhossein Samandar, Biyao Zhang, Debargha Ganguly, Jerry Peng Published: 2026-08-04Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint, safety-evaluation | 2026-08-04 | cs.LG | ai-safety, cslg, preprint, safety-evaluation | - | - |
| The Ignition Is Real, and It Lives at the Readout: Latent composition, difficulty-clocked ignition, and the interface-constituted commit in a recurrent-depth reasoner Simon Lam-Muir Published: 2026-08-04Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-08-04 | cs.LG | ai-safety, cslg, preprint | - | - |
| The Tell-Tale Trace: Detecting Reasoning Failures in LLMs Using Chain-of-Thought Dynamics Aishwarya Balwani, Shashwat Sourav Published: 2026-08-04Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-08-04 | cs.LG | ai-safety, cslg, preprint | - | - |