Quality follows upgrading
Category
arXiv:2603.10100v1 Announce Type: new Abstract: Modern CNNs' high computational demands hinder edge deployment, as traditional ``hard'' sparsity (skipping mathematical zeros) loses effectiveness in deep layers …
arXiv:2603.10101v1 Announce Type: new Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) has significantly advanced the reasoning capacity of Large Language Models (LLMs). However, RLVR solely …
arXiv:2603.10123v1 Announce Type: new Abstract: The ``Lost in the Middle'' phenomenon -- a U-shaped performance curve where LLMs retrieve well from the beginning and end …
arXiv:2603.10149v1 Announce Type: new Abstract: In the design of engineered components, rigorous vibration testing is essential for performance validation and identification of resonant frequencies and …
arXiv:2603.10156v1 Announce Type: new Abstract: Finetuning on domain-specific data is a well-established method for enhancing LLM performance on downstream tasks. Training on each dataset produces …
arXiv:2603.10180v1 Announce Type: new Abstract: The growing adoption of electronic health record (EHR) systems has provided unprecedented opportunities for predictive modeling to guide clinical decision …
arXiv:2603.10199v1 Announce Type: new Abstract: Policy Dual Averaging (PDA) offers a principled Policy Mirror Descent (PMD) framework that more naturally admits value function approximation than …
arXiv:2603.10225v1 Announce Type: new Abstract: Cross-entropy loss has long been the standard choice for training deep neural networks, yet it suffers from interpretability limitations, unbounded …
arXiv:2603.10250v1 Announce Type: new Abstract: A commonly used family of RL algorithms for diffusion policies conducts softmax reweighting over the behavior policy, which usually induces …
arXiv:2603.10254v1 Announce Type: new Abstract: Synthetic tabular data generation addresses data scarcity and privacy constraints in a variety of domains. Tabular Prior-Data Fitted Network (TabPFN), …
arXiv:2603.10261v1 Announce Type: new Abstract: We report the discovery and extraction of a compact hematopoietic algorithm from the single-cell foundation model scGPT, to our knowledge …
arXiv:2603.10277v1 Announce Type: new Abstract: In this paper, we propose a fast method for estimating the condition number of sparse matrices using graph neural networks …