papers

Publications (6)

cs.CL2026

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…

cs.LG2023

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…

cs.CL2026

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…

cs.LG2024

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,…

cs.CL2026

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…

#full-duplex spoken language models#modality interference#hierarchical parameter separation#semantic alignment
cs.AI2026

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…