activity
20242026
collaborators

7 papers

cs.LG2026

On the Vulnerability of Parameter-Level Defenses to Model Merging

Kuangpu Guo, Qingyan Zheng, Jian Liang +4

The training-free integration of expert models via model merging has exposed significant security risks, enabling free-riders to combine specialized models without authorization. R…

cs.LG2026

Stay Unique, Stay Efficient: Preserving Model Personality in Multi-Task Merging

Kuangpu Guo, Aijing Yu, Jian Liang +4

Model merging has emerged as a promising paradigm for enabling multi-task capabilities without additional training. However, traditional basic merging methods often experience perf…

cs.LG2026

Understanding and Mitigating Spurious Signal Amplification in Test-Time Reinforcement Learning for Math Reasoning

Yongcan Yu, Lingxiao He, Jian Liang +5

Test-time reinforcement learning (TTRL) always adapts models at inference time via pseudo-labeling, leaving it vulnerable to spurious optimization signals from label noise. Through…

cs.LG2025

Reassessing the Role of Supervised Fine-Tuning: An Empirical Study in VLM Reasoning

Yongcan Yu, Lingxiao He, Shuo Lu +10

Recent advances in vision-language models (VLMs) reasoning have been largely attributed to the rise of reinforcement Learning (RL), which has shifted the community's focus away fro…

cs.CV2025

Cooperative Pseudo Labeling for Unsupervised Federated Classification

Kuangpu Guo, Lijun Sheng, Yongcan Yu +3

Unsupervised Federated Learning (UFL) aims to collaboratively train a global model across distributed clients without sharing data or accessing label information. Previous UFL work…

cs.LG2025

Personalized Federated Learning via Dual-Prompt Optimization and Cross Fusion

Yuguang Zhang, Kuangpu Guo, Zhihe Lu +2

Federated learning (FL) enables collaborative model training across decentralized clients without sharing local data, but is challenged by heterogeneity in data, computation, and c…