7 papers
EdgeBench: Unveiling Scaling Laws of Learning from Real-World Environments
Deyao Zhu, Xin Zhou, Shengling Qin +44
Pretraining scaling laws reveal that model capability improves predictably with data and compute. But learning from real world environments after deployment remains far less unders…
LP-SFT: Local-Preserving Supervised Fine-Tuning via Multimodal Entropy Structure
Yueyang Wang, Baolong Bi, Shuo Lu +2
Supervised fine-tuning (SFT) is the standard approach for adapting pretrained language models to downstream domains, yet it often improves target-domain behavior at the cost of deg…
HE-SNR: Uncovering Latent Logic via Entropy for Guiding Mid-Training on SWE-bench
Yueyang Wang, Jiawei Fu, Baolong Bi +2
SWE-bench has emerged as the premier benchmark for evaluating Large Language Models on complex software engineering tasks. While these capabilities are fundamentally acquired durin…
Discovering Invariant Neighborhood Patterns for Heterophilic Graphs
Jinluan Yang, Ruihao Zhang, Zhengyu Chen +4
This paper studies the problem of distribution shifts on non-homophilous graphs Mosting existing graph neural network methods rely on the homophilous assumption that nodes from the…
A Graph-Retrieval-Augmented Generation Framework Enhances Decision-Making in the Circular Economy
Yang Zhao, Chengxiao Dai, Dusit Niyato +7
Large language models (LLMs) hold promise for sustainable manufacturing, but often hallucinate industrial codes and emission factors, undermining regulatory and investment decision…
Boundaries of the bounded hyperbolic components of polynomials
Yan Gao, Xiaoguang Wang, Yueyang Wang
In this paper, we study the local connectivity and Hausdorff dimension for the boundaries of the bounded hyperbolic components in the space of polynomials of degree…