Qingyu Zhang

Qingyu Zhang

Master Student of Computer Science and Technology

Institute of Software Chinese Academy of Sciences

I’m Qingyu Zhang, a second-year master’s student at Chinese Information Processing Laboratory in the Institute of Software Chinese Academy of Sciences. My current research focuses on AI sales and customer-service agents, especially reliable multi-turn interaction and evaluation in real-world business scenarios. I am also actively exploring User Agents for realistic evaluation and multi-turn interaction.

My internship experience spans foundation-model pretraining at Baichuan Intelligence, post-training and dialogue optimization at Meituan, and building user agents for evaluation and multi-turn training at ByteDance. Along the way, I have worked on AI-Salesman for reliable LLM-driven telemarketing, ShortGPT for layer pruning and model efficiency, and open-source toolkits such as AutoAlign and ShortX.

Interests
  • LLM Long Context
  • LLM Compression & Efficiency
  • LLM Post-training
Education

  • M.S. in Computer Science and Technology, 2024 - Present

    Institute of Software, CAS

  • B.S. in Computer Science and Technology, 2020 - 2024

    College of Computer and Data Science, Fuzhou University

News

  • Jul, 2026 One paper “ShortOPD” is released on arXiv as first author.
  • Dec, 2025 One paper “AI-Salesman” is accepted by AAAI 2026 as first author.
  • Nov, 2025 Open-sourced ShortX project, a unified pruning toolkit for AI models.
  • Jun, 2025 Contributed to AutoAlign project, an open-source toolkit for automated LLM alignment.
  • May, 2025 One paper “ShortV” is accepted by ICCV 2025.
  • May, 2025 One paper “ShortGPT” is accepted by ACL Findings 2025.

Experience

Algorithm Intern · ByteDance Jan 2026 – Present · Beijing, China
  • Led the R&D of a User Agent framework supporting multi-turn evaluation needs across business lines, with over 80% of the generated evaluation data being business-usable.
  • Exploring viable paradigms for applying the User Agent to multi-turn RL for Sales Agents.
Algorithm Intern · Meituan Dec 2024 – Jan 2026 · Beijing, China
  • Led the R&D of an RL-based dialogue optimization system for large models, building the full pipeline of training, inference, and evaluation.
  • Deployed in a live business environment, increasing core business conversion rate by 10%~20%.
  • Published as first author (AI-Salesman, AAAI, 2026).
Foundation Model Intern · Baichuan Intelligence Jan 2024 – Oct 2024 · Beijing, China
  • Investigated Transformer redundancy and proposed a layer-based pruning method (ShortGPT, ACL Findings, 2025).
  • Researched the lower bounds of RoPE Base (Base of RoPE Bounds Context Length, NeurIPS, 2024).
  • Proposed a variant of the “Needle in a Haystack” evaluation method (Patent Granted).
Research Intern · Institute of Software, Chinese Academy of Sciences Oct 2023 – Sep 2024 · Beijing, China
  • Adapted and optimized SFT/DPO algorithms for the Megatron framework (ACL Demo, 2025).
  • Implemented large-scale distributed training on Ascend 910b using the ModelLink framework.

Publications

ShortOPD: Recovering Pruned LLMs with Short-to-Long On-Policy Distillation
Qingyu Zhang, Qianhao Yuan, Hongyu Lin, Yaojie Lu, Xianpei Han, Le Sun, Xiang Li, Ming Xu, Jiarui Li, Xiuyin Zhao (2026). ShortOPD: Recovering Pruned LLMs with Short-to-Long On-Policy Distillation. arXiv preprint.

PDF Cite

AI-Salesman: Towards Reliable Large Language Model Driven Telemarketing
Qingyu Zhang, Chunlei Xin, Xuanang Chen, Yaojie Lu, Hongyu Lin, Xianpei Han, Le Sun, Qing Ye, Qianlong Xie, Xingxing Wang (2026). AI-Salesman: Towards Reliable Large Language Model Driven Telemarketing. In AAAI 2026.

PDF Cite

AutoAlign: Automated Alignment for Large Language Models
Xinyu Lu, Dong Xu, Chunkang Zhang, Xinyan Guan, Junxiang Wang, Qingyu Zhang, Pengbo Wang, Yingzhi Mao, Hao Xiang, Xueru Wen, Zichao Li, Yaojie Lu, Hongyu Lin, Le Sun, Xianpei Han (2025). AutoAlign: Automated Alignment for Large Language Models. In ACL Demo 2025.

PDF Cite Code

ShortV: Efficient Multimodal Large Language Models by Freezing Visual Tokens in Ineffective Layers
Qianhao Yuan, Qingyu Zhang, Yanjiang Liu, Jiawei Chen, Yaojie Lu, Hongyu Lin, Jia Zheng, Xianpei Han, Le Sun (2025). ShortV: Efficient Multimodal Large Language Models by Freezing Visual Tokens in Ineffective Layers. In ICCV 2025.

PDF Cite

ShortGPT: Layers in Large Language Models are More Redundant Than You Expect
Xin Men, Mingyu Xu, Qingyu Zhang, Qianhao Yuan, Bingning Wang, Hongyu Lin, Yaojie Lu, Xianpei Han, Weipeng Chen (2025). ShortGPT: Layers in Large Language Models are More Redundant Than You Expect. In ACL Findings 2025.

PDF Cite

See all publications

Projects

Last updated on Nov 16, 2025
ShortX
ShortX

A unified pruning toolkit for AI models. Currently includes ShortGPT and ShortV for efficient layer pruning.

ShortGPT-Paper ShortV-Paper Code
Last updated on Nov 16, 2025
AutoAlign - Automated Alignment Toolkit for LLMs
AutoAlign - Automated Alignment Toolkit for LLMs

An open-source toolkit for automated alignment of Large Language Models. I was responsible for adapting and optimizing SFT/DPO algorithms for the Megatron framework.

Paper Code
Last updated on Aug 4, 2025
Inference Acceleration for the 70B LLaMA-2 Large Language Model
Inference Acceleration for the 70B LLaMA-2 Large Language Model

As a coaching assistant for the ASC24 Student Supercomputer Challenge, I helped the team optimize the inference performance of the LLaMA-2-70B model using efficient frameworks like vLLM and designed data parallelism strategies to significantly reduce latency.

Last updated on Nov 16, 2025
Training the 10-Billion Parameter Yuan-1.0 LLM
Training the 10-Billion Parameter Yuan-1.0 LLM

As a key member of the ASC23 team, I trained a 10B-level large language model using the DeepSpeed-Megatron framework, combining tensor, pipeline, and data parallelism. Our work won the First Prize.

Awards

  • Jun, 2024 Honored as an Outstanding Graduate at Fuzhou University.
  • May, 2023 Won the First Prize in the 10th ASC Student Supercomputer Challenge.
  • Nov, 2022 Won the First Prize in the 13th National College Student Mathematics Competition.

Contact