arXiv Computer Science @arxiv_cs@qoto.org

Quantifying and Attributing Polarization to Annotator Groups https://arxiv.org/abs/2602.06055 #cs.CL

Denoising diffusion networks for normative modeling in neuroimaging https://arxiv.org/abs/2602.04886 #stat.ML #cs.LG #cs.AI #cs.CE

Templated Assembly Theory: An Extension of the Canonical Assembly Index with Block-Compressed Template https://arxiv.org/abs/2602.04889 #cs.FL

Doc2Spec: Synthesizing Formal Programming Specifications from Natural Language via Grammar Induction https://arxiv.org/abs/2602.04892 #cs.PL #cs.AI #cs.SE

A Causal Perspective for Enhancing Jailbreak Attack and Defense https://arxiv.org/abs/2602.04893 #cs.LG #cs.AI #cs.CR

Extracting Recurring Vulnerabilities from Black-Box LLM-Generated Software https://arxiv.org/abs/2602.04894 #cs.CR #cs.AI

Privacy Amplification Persists under Unlimited Synthetic Data Release https://arxiv.org/abs/2602.04895 #stat.ML #cs.CR #cs.DS #cs.LG

Steering Externalities: Benign Activation Steering Unintentionally Increases Jailbreak Risk for Large Language Models https://arxiv.org/abs/2602.04896 #cs.CR #cs.AI

Semantic-level Backdoor Attack against Text-to-Image Diffusion Models https://arxiv.org/abs/2602.04898 #cs.CR #cs.AI

Phantom Transfer: Data-level Defences are Insufficient Against Data Poisoning https://arxiv.org/abs/2602.04899 #cs.CR #cs.AI

Evaluating Kubernetes Performance for GenAI Inference: From Automatic Speech Recognition to LLM Summarization https://arxiv.org/abs/2602.04900 #cs.ET #cs.AI #cs.DC

HybridQuestion: Human-AI Collaboration for Identifying High-Impact Research Questions https://arxiv.org/abs/2602.03849 #cs.HC #cs.AI #cs.CL #cs.LG

WebAccessVL: Making an Accessible Web via Violation-Conditioned VLM https://arxiv.org/abs/2602.03850 #cs.HC #cs.AI #cs.CV

Gamification-Based Learning Method for Hijaiyah Letters https://arxiv.org/abs/2602.03851 #cs.HC

Perceptions of AI-CBT: Trust and Barriers in Chinese Postgrads https://arxiv.org/abs/2602.03852 #cs.HC #cs.AI #cs.CY

On-Demand Lecture Watching System Using Various Actions of Student Characters to Maintain Concentration https://arxiv.org/abs/2602.03853 #cs.HC

From Expectation To Experience: A Before And After Survey Of Public Opinion On Autonomous Cars In Saudi Arabia https://arxiv.org/abs/2602.03854 #cs.HC #cs.CY

Overcoming Barriers to Computational Reproducibility https://arxiv.org/abs/2602.03863 #cs.DL

Have Large Language Models Enhanced the Way Civil & Environmental Engineers Write? A Quantitative Analysis of Scholarly Communication over 25 Years https://arxiv.org/abs/2602.03864 #cs.DL

PaperX: A Unified Framework for Multimodal Academic Presentation Generation with Scholar DAG https://arxiv.org/abs/2602.03866 #cs.DL #cs.AI