Publications (6)
Revisiting Chain-of-Thought Prompting: Zero-shot Can Be Stronger than Few-shot
Xiang Cheng, Chengyan Pan, Minjun Zhao +5
In-Context Learning (ICL) is an essential emergent ability of Large Language Models (LLMs), and recent studies introduce Chain-of-Thought (CoT) to exemplars of ICL to enhance the r…
Finding Materialized Models for Model Reuse
Minjun Zhao, Lu Chen, Keyu Yang +2
Materialized model query aims to find the most appropriate materialized model as the initial model for model reuse. It is the precondition of model reuse, and has recently attracte…
ADOPT: Adaptive Dependency-Guided Joint Prompt Optimization for Multi-Step LLM Pipelines
Minjun Zhao, Xinyu Zhang, Shuai Zhang +2
Multi-step LLM pipelines can solve complex tasks, but jointly optimizing prompts across steps remains challenging due to missing step-level supervision and inter-step dependency. W…
SparDL: Distributed Deep Learning Training with Efficient Sparse Communication
Minjun Zhao, Yichen Yin, Yuren Mao +3
Top-k sparsification has recently been widely used to reduce the communication volume in distributed deep learning. However, due to the Sparse Gradient Accumulation (SGA) dilemma,…
Hierarchical Acoustic-Semantic Modeling: Modality Separation and Semantic Coherence for Full-Duplex SLMs
Zhenyu Liu, Xuanyu Zhang, Yunxin Li +10
The paper identifies gradient conflicts between acoustic and semantic modeling as the cause of modality interference in full-duplex spoken language models and proposes Lychee-FD, a…
Process In-Context Learning: Enhancing Mathematical Reasoning via Dynamic Demonstration Insertion
Ang Gao, Changshuo Zhang, Xiao Zhang +4
In-context learning (ICL) has proven highly effective across diverse large language model (LLM) tasks. However, its potential for enhancing tasks that demand step-by-step logical d…