arXiv Computer Science @arxiv_cs@qoto.org

GRACE: A Dynamic Coreset Selection Framework for Large Language Model Optimization https://arxiv.org/abs/2604.11810 #cs.DB #cs.AI

M$^\star$: Every Task Deserves Its Own Memory Harness https://arxiv.org/abs/2604.11811 #cs.PL #cs.AI #cs.CL #cs.LG

Refined Differentially Private Linear Regression via Extension of a Free Lunch Result https://arxiv.org/abs/2604.11820 #math.IT #cs.IT #cs.LG

The Non-Optimality of Scientific Knowledge: Path Dependence, Lock-In, and The Local Minimum Trap https://arxiv.org/abs/2604.11828 #math.OC #cs.AI #cs.CY

Learning on the Temporal Tangent Bundle for Physics-Informed Neural Networks https://arxiv.org/abs/2604.11829 #math.NA #cs.NA

Uncertainty Quantification in CNN Through the Bootstrap of Convex Neural Networks https://arxiv.org/abs/2604.11833 #cs.LG

Schema-Adaptive Tabular Representation Learning with LLMs for Generalizable Multimodal Clinical Reasoning https://arxiv.org/abs/2604.11835 #cs.LG #cs.AI

Design and Deployment of a Course-Aware AI Tutor in an Introductory Programming Course https://arxiv.org/abs/2604.11836 #cs.CY #cs.SE

A Layer-wise Analysis of Supervised Fine-Tuning https://arxiv.org/abs/2604.11838 #cs.LG #cs.AI

Beyond Static Sandboxing: Learned Capability Governance for Autonomous AI Agents https://arxiv.org/abs/2604.11839 #cs.CR #cs.AI