arXiv Computer Science @arxiv_cs@qoto.org

Universal Asymptotics for Jensen--Shannon Divergence under Shuffling https://arxiv.org/abs/2602.09029 #math.IT #cs.IT

Scaling GraphLLM with Bilevel-Optimized Sparse Querying https://arxiv.org/abs/2602.09038 #cs.DB #cs.AI

Efficient Distance Pruning for Process Suffix Comparison in Prescriptive Process Monitoring https://arxiv.org/abs/2602.09039 #cs.DB #cs.AI

DSFlow: Dual Supervision and Step-Aware Architecture for One-Step Flow Matching Speech Synthesis https://arxiv.org/abs/2602.09041 #eess.AS #cs.SD #cs.AI

The SJTU X-LANCE Lab System for MSR Challenge 2025 https://arxiv.org/abs/2602.09042 #eess.AS #cs.SD

Feasible Static Workspace Optimization of Tendon Driven Continuum Robot based on Euclidean norm https://arxiv.org/abs/2602.09046 #cs.RO

RuleFlow : Generating Reusable Program Optimizations with LLMs https://arxiv.org/abs/2602.09051 #cs.SE #cs.AI

An adaptive perfectly matched layer finite element method for acoustic-elastic interaction in periodic structures https://arxiv.org/abs/2602.09055 #math.NA #cs.NA

AVERE: Improving Audiovisual Emotion Reasoning with Preference Optimization https://arxiv.org/abs/2602.07054 #cs.LG #cs.CV #cs.HC

Theory of Space: Can Foundation Models Construct Spatial Beliefs through Active Exploration? https://arxiv.org/abs/2602.07055 #cs.AI #cs.CL #cs.LG

PersonaPlex: Voice and Role Control for Full Duplex Conversational Speech Models https://arxiv.org/abs/2602.06053 #cs.CL

What Is Novel? A Knowledge-Driven Framework for Bias-Aware Literature Originality Evaluation https://arxiv.org/abs/2602.06054 #cs.CL

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