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 |
|---|---|---|---|---|---|
| ScreenASR-Bench: A Tiered Benchmark for Speech Recognition with Visual Context Mengxiao Zhu, Mingwei Fu, Shen Huang, Shidong Shang Published: 2026-10-12Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-10-12 | cs.AI | ai-safety, csai, preprint | - | - |
| Separating Prompt Harmfulness from Interaction Safety via Partial Generation Amit Awekar, Jahnavi Kumar, Ram Vikas Mishra, Shashank Aggarwal Published: 2026-10-12Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-10-12 | cs.AI | ai-safety, csai, preprint | - | - |
| SFT Leaves a Reproducible Signature in Activation Geometry: Calibrating Post-Training Interpretability Against Run-to-Run Noise Chenqian Le, Jiayi Cheng, Michael Yue, Runhao Li Published: 2026-10-12Area: cs.AICitations: - Tags: ai-safety, csai, interpretability, preprint | 2026-10-12 | cs.AI | ai-safety, csai, interpretability, preprint | - | - |
| Size Generalization for Diffusion Routing Solvers Barak Itzchak Davidovitch, Eli Meirom, Ethan Fetaya, Gal Chechik Published: 2026-10-12Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-10-12 | cs.AI | ai-safety, csai, preprint | - | - |
| SLDBench v2: Active Scaling Law Discovery Haorui Chen, Haowei Lin, Jinxin Liu, Lingbei Meng Published: 2026-10-12Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-10-12 | cs.LG | ai-safety, cslg, preprint | - | - |
| SLEM: Spectrum-Aware Latent Expert Merging Bedionita Soro, Bruno Andreis, Dohyeon Kim, Sung Ju Hwang Published: 2026-10-12Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-10-12 | cs.LG | ai-safety, cslg, preprint | - | - |
| SLS-Bench: A Benchmark for Incident Log Summarization with Synthetic Observability Data Markus Spanring, Martin Flechl, Valerii Iakovlev Published: 2026-10-12Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-10-12 | cs.AI | ai-safety, csai, preprint | - | - |
| Social Priors: Descriptions of AI Users Shape How Language Models Trust and Cooperate Ashton Anderson, George Eilender, Harsh Kumar Published: 2026-10-12Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-10-12 | cs.LG | ai-safety, cslg, preprint | - | - |
| SonicWorld: Source-Centric Latent Dynamics for Spatial Audio Reasoning Chenlong Wei, Hanling Wang, Mingjin Lou, Sheldon Yu Published: 2026-10-12Area: cs.SDCitations: - Tags: ai-safety, cssd, preprint | 2026-10-12 | cs.SD | ai-safety, cssd, preprint | - | - |
| SPLICE: Sparse Physics Library Identification and Compositional Expansion Guillaume Doquet, Jesse Read, Lucas Thil, Rim Kaddah Published: 2026-10-12Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-10-12 | cs.LG | ai-safety, cslg, preprint | - | - |
| StableJudge: A Lightweight Adversarial Defense Framework for LLM-as-a-Judge Anning Hu, Junchi Yan, Shengchao Hu, Yangyu Li Published: 2026-10-12Area: cs.CRCitations: - Tags: adversarial-robustness, ai-safety, cscr, preprint | 2026-10-12 | cs.CR | adversarial-robustness, ai-safety, cscr, preprint | - | - |
| StartLux-Decision: AutoThink Decision Models with Reinforcement Learning for Calibrated Deliberative Decisions Chuan-Wei Kuo, Guanhua Chen, Jia Pan, Ngai Wong Published: 2026-10-12Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-10-12 | cs.CL | ai-safety, cscl, preprint | - | - |
| Structural Baselines Matter for Agent Failure Detection and Attribution Ramesh Arvind Naagarajan, Stefan Streif Published: 2026-10-12Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-10-12 | cs.AI | ai-safety, csai, preprint | - | - |
| StructZO: Structured Zeroth-Order Optimization for Memory-Efficient LLM Fine-Tuning Jia Li, Xuanlin Yang, Zhouchen Lin Published: 2026-10-12Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-10-12 | cs.LG | ai-safety, cslg, preprint | - | - |
| Superintelligence and the Triple Risk of an AI Race Leonard Dung, Matthew Rendall, Max Hellrigel-Holderbaum Published: 2026-10-12Area: cs.CYCitations: - Tags: ai-safety, cscy, preprint | 2026-10-12 | cs.CY | ai-safety, cscy, preprint | - | - |
| SuPER-Mamba: Surprisal Prioritization for Extended-Context Routing in Mamba Gayan K Kulatilleke, Zhetong Zhang Published: 2026-10-12Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-10-12 | cs.CL | ai-safety, cscl, preprint | - | - |
| TabGift: A Context-Efficient Foundation Model for Tabular Data Generation Han-Jia Ye, Jun-Peng Jiang, Yu-Sheng Li Published: 2026-10-12Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-10-12 | cs.LG | ai-safety, cslg, preprint | - | - |
| The Agent Knew: Internal States Forecast Unauthorized Actions and Stop Them, and the Lies That Follow Arya Fayyazi, Massoud Pedram, Mehdi Kamal Published: 2026-10-12Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-10-12 | cs.AI | ai-safety, csai, preprint | - | - |
| The belief-action gap in language model agents Angelos Nalmpantis, Ayse Sila Okcu, Mario Giulianelli, Niall Dalton Published: 2026-10-12Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-10-12 | cs.LG | ai-safety, cslg, preprint | - | - |
| The Format is the Filter: Scoring Format Fixes What an LLM Judge Can Express Jack Ji, Jekaterina Novikova, Jithin Pradeep, Lovedeep Gondara Published: 2026-10-12Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-10-12 | cs.AI | ai-safety, csai, preprint | - | - |
| The Sharp Directions Are Against You: Curvature Analysis of Activation Steering Arya Fayyazi, Erfan Baghaei Potraghloo, Massoud Pedram, Parsa Razmara Published: 2026-10-12Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-10-12 | cs.AI | ai-safety, csai, preprint | - | - |
| The Value of Being Wrong: Self-Mined Visual In-Context Learning from Errors Shu Zhao, Tan Yu Published: 2026-10-12Area: cs.CVCitations: - Tags: ai-safety, cscv, preprint | 2026-10-12 | cs.CV | ai-safety, cscv, preprint | - | - |
| Thinking Outside the Bots: Human Ideas in AI's Semantic Blind Spots Are Not Inferior Adam E. Green, Angela L. Duckworth, Benjamin Lira, Dan R. Johnson Published: 2026-10-12Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-10-12 | cs.CL | ai-safety, cscl, preprint | - | - |
| Towards a Benchmark for Fire Safety Code Interpretation in the Hong Kong AEC Industry Emmanuele Chersoni, Hok Ming Adeline Chan, Le Qiu, Zhuan Anne Zhang Published: 2026-10-12Area: cs.CECitations: - Tags: ai-safety, csce, preprint | 2026-10-12 | cs.CE | ai-safety, csce, preprint | - | - |
| Towards Cost-Efficient Video Dataset Construction with Large Language Models Jan Van den Stock, Jonathan Adams, Joost Vennekens, Mohammed Shabot Published: 2026-10-12Area: cs.CVCitations: - Tags: ai-safety, cscv, preprint | 2026-10-12 | cs.CV | ai-safety, cscv, preprint | - | - |
| Towards Modality-Agnostic Seizure Classification: A Unified Deep Learning Framework for Heterogeneous EEG and Intracranial EEG Signals Muhammad Aslam Jarwar, M Uma, Qurat-Ul-Ain Mastoi, Ramya Sundaram Published: 2026-10-12Area: cs.LGCitations: - Tags: ai-safety, cslg, preprint | 2026-10-12 | cs.LG | ai-safety, cslg, preprint | - | - |
| Towards Resilience: Slice-Driven Orchestration of Mobile IoMT in 6G-Edge-Continuum Erkki Harjula, Hafiz Faheem Shahid, Muhammad Zeeshan Published: 2026-10-12Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-10-12 | cs.AI | ai-safety, csai, preprint | - | - |
| Trace-to-Architecture: Capability Bottleneck Diagnosis for Harness Revision Guojiang Zhao, Jiajun Sun, Jianrui Shi, Jiayuan Ma Published: 2026-10-12Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-10-12 | cs.AI | ai-safety, csai, preprint | - | - |
| Transparency as Answerability: Role-Dependent Information Flow Modeling Lili Jiang, Mattias Br盲nnstr枚m, Themis Dimitra Xanthopoulou Published: 2026-10-12Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-10-12 | cs.AI | ai-safety, csai, preprint | - | - |
| Transparent Information Flow Modeling for Role-Aware AI Act Assessment Lili Jiang, Mattias Br盲nnstr枚m, Themis Dimitra Xanthopoulou Published: 2026-10-12Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-10-12 | cs.AI | ai-safety, csai, preprint | - | - |