collaborators

8 papers

cs.CL2026

ReFusion: A Diffusion Large Language Model with Parallel Autoregressive Decoding

Jia-Nan Li, Jian Guan, Wei Wu +1

Autoregressive models (ARMs) are hindered by slow sequential inference. While masked diffusion models (MDMs) offer a parallel alternative, they suffer from critical drawbacks: high…

cs.AI2025

EduFlow: Advancing MLLMs' Problem-Solving Proficiency through Multi-Stage, Multi-Perspective Critique

Chenglin Zhu, Tao Zhang, Chong Li +3

Multimodal large language models (MLLMs) still perform poorly on scientific tasks, particularly those requiring multi-step and interpretable reasoning. Their limitations include in…

cs.CL2025

Data Efficacy for Language Model Training

Yalun Dai, Yangyu Huang, Xin Zhang +6

Data is fundamental to the training of language models (LM). Recent research has been dedicated to data efficiency, which aims to maximize performance by selecting a minimal or opt…

cs.CL2025

Efficient Medical VIE via Reinforcement Learning

Lijun Liu, Ruiyang Li, Zhaocheng Liu +5

Visual Information Extraction (VIE) converts unstructured document images into structured formats like JSON, critical for medical applications such as report analysis and online co…

cs.AI2025

K12Vista: Exploring the Boundaries of MLLMs in K-12 Education

Chong Li, Chenglin Zhu, Tao Zhang +3

Multimodal large language models have demonstrated remarkable reasoning capabilities in various visual tasks. However, their abilities in K12 scenarios are still systematically und…

cs.CL2025

Enhancing Low-Resource Minority Language Translation with LLMs and Retrieval-Augmented Generation for Cultural Nuances

Chen-Chi Chang, Chong-Fu Li, Chu-Hsuan Lee +1

This study investigates the challenges of translating low-resource languages by integrating Large Language Models (LLMs) with Retrieval-Augmented Generation (RAG). Various model co…