activity
20162024
most citedIdeal charge density wave order in the high-field state of superconducting YBCO

108 citations · 118 across the 8 of their papers we have counts for

collaborators

8 papers

cs.CL2024

Comments as Natural Logic Pivots: Improve Code Generation via Comment Perspective

Yijie Chen, Yijin Liu, Fandong Meng +3

Code generation aims to understand the problem description and generate corresponding code snippets, where existing works generally decompose such complex tasks into intermediate s…

cs.CL2024

Accelerating Inference in Large Language Models with a Unified Layer Skipping Strategy

Yijin Liu, Fandong Meng, Jie Zhou

Recently, dynamic computation methods have shown notable acceleration for Large Language Models (LLMs) by skipping several layers of computations through elaborate heuristics or ad…

cs.CL20237 cited

Improving Translation Faithfulness of Large Language Models via Augmenting Instructions

Yijie Chen, Yijin Liu, Fandong Meng +3

Large Language Models (LLMs) present strong general capabilities, and a current compelling challenge is stimulating their specialized capabilities, such as machine translation, thr…

cs.CL20232 cited

Instruction Position Matters in Sequence Generation with Large Language Models

Yijin Liu, Xianfeng Zeng, Fandong Meng +1

Large language models (LLMs) are capable of performing conditional sequence generation tasks, such as translation or summarization, through instruction fine-tuning. The fine-tuning…

cs.CL20231 cited

Towards Multiple References Era -- Addressing Data Leakage and Limited Reference Diversity in NLG Evaluation

Xianfeng Zeng, Yijin Liu, Fandong Meng +1

N-gram matching-based evaluation metrics, such as BLEU and chrF, are widely utilized across a range of natural language generation (NLG) tasks. However, recent studies have reveale…

cs.LG2023

BranchNorm: Robustly Scaling Extremely Deep Transformers

Yijin Liu, Xianfeng Zeng, Fandong Meng +1

Recently, DeepNorm scales Transformers into extremely deep (i.e., 1000 layers) and reveals the promising potential of deep scaling. To stabilize the training of deep models, DeepNo…