Maosong Sun

发表

Experiential Co-Learning of Software-Developing Agents

Zhiyuan Liu, Weize Chen, Wei Liu, 2023, ACL.

CPT: Color-based Prompt Tuning for pre-trained vision-language models

Zhengyan Zhang, Zhiyuan Liu, Yuan Yao, 2024, AI Open.

RepoAgent: An LLM-Powered Open-Source Framework for Repository-level Code Documentation Generation

Yankai Lin, Yujia Qin, Yining Ye, 2024, ArXiv.

MatPlotAgent: Method and Evaluation for LLM-Based Agentic Scientific Data Visualization

Zhenghao Liu, Xin Cong, Maosong Sun, 2024, ArXiv.

Tell Me More! Towards Implicit User Intention Understanding of Language Model Driven Agents

Zhiyuan Liu, Yankai Lin, Yujia Qin, 2024, ArXiv.

Investigate-Consolidate-Exploit: A General Strategy for Inter-Task Agent Self-Evolution

Zhiyuan Liu, Yankai Lin, Yujia Qin, 2024, ArXiv.

Iterative Experience Refinement of Software-Developing Agents

Weize Chen, Cheng Qian, Yufan Dang, 2024, ArXiv.

Advancing LLM Reasoning Generalists with Preference Trees

Zhenghao Liu, Yankai Lin, Ning Ding, 2024, ArXiv.

GitAgent: Facilitating Autonomous Agent with GitHub by Tool Extension

Zhiyuan Liu, Yankai Lin, Yujia Qin, 2023, ArXiv.

Ouroboros: Speculative Decoding with Large Model Enhanced Drafting

Chaojun Xiao, Zhiyuan Liu, Weilin Zhao, 2024, arXiv.org.

ProSparse: Introducing and Enhancing Intrinsic Activation Sparsity within Large Language Models

Zhengyan Zhang, Zhiyuan Liu, Shengding Hu, 2024, arXiv.org.

ReLU2 Wins: Discovering Efficient Activation Functions for Sparse LLMs

Chaojun Xiao, Zhengyan Zhang, Yankai Lin, 2024, ArXiv.

Removing Backdoors in Pre-trained Models by Regularized Continual Pre-training

Yujia Qin, Biru Zhu, Ming Gu, 2023, Transactions of the Association for Computational Linguistics.

Unified View of Grokking, Double Descent and Emergent Abilities: A Perspective from Circuits Competition

Zhiyuan Liu, Shengding Hu, Maosong Sun, 2024, ArXiv.

MiniCPM: Unveiling the Potential of Small Language Models with Scalable Training Strategies

Yuan Yao, Shengding Hu, Guoyang Zeng, 2024, ArXiv.

InfLLM: Training-Free Long-Context Extrapolation for LLMs with an Efficient Context Memory

Chaojun Xiao, Zhengyan Zhang, Zhiyuan Liu, 2024, 2402.04617.

DebugBench: Evaluating Debugging Capability of Large Language Models

Zhiyuan Liu, Yankai Lin, Yujia Qin, 2024, ArXiv.

Fine-Grained Legal Argument-Pair Extraction via Coarse-Grained Pre-training

Chaojun Xiao, Yuan Yao, Zhiyuan Liu, 2024, LREC.

Scaling Large-Language-Model-based Multi-Agent Collaboration

Weize Chen, Cheng Qian, Yufan Dang, 2024, ArXiv.

UltraEval: A Lightweight Platform for Flexible and Comprehensive Evaluation for LLMs

Shengding Hu, Chaoqun He, Zhiyuan Liu, 2024, ArXiv.

OlympiadBench: A Challenging Benchmark for Promoting AGI with Olympiad-Level Bilingual Multimodal Scientific Problems

Zhiyuan Liu, Shengding Hu, Jinyi Hu, 2024, ACL.

∞Bench: Extending Long Context Evaluation Beyond 100K Tokens

Zhiyuan Liu, Shengding Hu, Yingfa Chen, 2024, ArXiv.

ChatDev: Communicative Agents for Software Development

Yusheng Su, Weize Chen, Cheng Qian, 2023, ACL.

Text Style Transfer via Learning Style Instance Supported Latent Space

Zhenghao Liu, Maosong Sun, Xiaoyuan Yi, 2020, IJCAI.

FastFiD: Improve Inference Efficiency of Open Domain Question Answering via Sentence Selection

Xu Han, Maosong Sun, Yufei Huang, 2024, ACL.

Relation-aware deep neural network enables more efficient biomedical knowledge acquisition from massive literature

Yuan Yao, Zheni Zeng, Maosong Sun, 2024, AI Open.