activity
20242026
collaborators

5 papers

cs.AI2026

LoCA: Forward-Only LLM Tuning after One-Shot Calibration with Local Credit Assignment

Linhan Xia, Rui Liu, Zhaofeng Zhang +3

Parameter-efficient post-training reduces the number of trainable parameters, but still requires repeated end-to-end backpropagation through the frozen backbone. Every adaptation s…

cs.AI2026

Evolving in the Agent Jungle via History-Informed Opponent Awareness

Zhaofeng Zhang, Linhan Xia, Rui Liu +3

Learning to adapt strategies through interaction is a key step toward more general and autonomous LLM agents. Existing approaches typically achieve behavioral adaptation by revisin…

cs.LG2025

FRAM: Frobenius-Regularized Assignment Matching with Mixed-Precision Computing

Binrui Shen, Yuan Liang, Shengxin Zhu

Graph matching, typically formulated as a Quadratic Assignment Problem (QAP), seeks to establish node correspondences between two graphs. To address the NP-hardness of QAP, some ex…

math.OC2025

Adaptive Softassign via Hadamard-Equipped Sinkhorn

Binrui Shen, Qiang Niu, Shengxin Zhu

Softassign is a pivotal method in graph matching and other learning tasks. Many softassign-based algorithms exhibit performance sensitivity to a parameter in the softassign. Howeve…

math.CO2024

CSGO: Constrained-Softassign Gradient Optimization For Large Graph Matching

Binrui Shen, Qiang Niu, Shengxin Zhu

Graph matching aims to find correspondences between two graphs. This paper integrates several well-known graph matching algorithms into a framework: the constrained gradient method…