collaborators

6 papers

cs.CV2026

EVL-MCoT: Enhanced Vision-Language Multi-CoT for Harmful Meme Detection

Hao Yang, Jin Wang, Xuejie Zhang

MEMEs are widely used on the internet and often carry strong elements of sarcasm or irony. Understanding their hidden meanings typically requires a joint interpretation of text and…

cs.CL2026

SAPO: Self-Adaptive Process Optimization Makes Small Reasoners Stronger

Kaiyuan Chen, Guangmin Zheng, Jin Wang +2

Existing self-evolution methods overlook the influence of fine-grained reasoning steps, which leads to the reasoner-verifier gap. The computational inefficiency of Monte Carlo (MC)…

cs.CL2025

Sample-aware Adaptive Structured Pruning for Large Language Models

Jun Kong, Xinge Ma, Jin Wang +1

Large language models (LLMs) have achieved outstanding performance in natural language processing, but enormous model sizes and high computational costs limit their practical deplo…

cs.CV2025

Vision-aware Multimodal Prompt Tuning for Uploadable Multi-source Few-shot Domain Adaptation

Kuanghong Liu, Jin Wang, Kangjian He +2

Conventional multi-source domain few-shot adaptation (MFDA) faces the challenge of further reducing the load on edge-side devices in low-resource scenarios. Considering the native…

cs.CL2025

Multi-Attribute Multi-Grained Adaptation of Pre-Trained Language Models for Text Understanding from Bayesian Perspective

You Zhang, Jin Wang, Liang-Chih Yu +2

Current neural networks often employ multi-domain-learning or attribute-injecting mechanisms to incorporate non-independent and identically distributed (non-IID) information for te…

cs.LG2025

Data-Free Black-Box Federated Learning via Zeroth-Order Gradient Estimation

Xinge Ma, Jin Wang, Xuejie Zhang

Federated learning (FL) enables decentralized clients to collaboratively train a global model under the orchestration of a central server without exposing their individual data. Ho…