Peijun Qing
Ph.D. Student, Computer Science · Dartmouth College
I am a second-year Ph.D. student in Computer Science at Dartmouth, advised by Prof. Soroush Vosoughi and co-advised by Prof. Saeed Hassanpour. Previously, I received my bachelor's degree from Xidian University, where I worked on knowledge-augmented large language models.
My research centers on the behavior of language models, with a current focus on LLM alignment. I have also worked on improving the robustness and efficiency of LLMs and on optimizing complex reasoning. I am drawn to simple, scalable methods that hold up against the messiness of real-world problems.
Publications
Selected work · *equal contribution
-
Cluster-R1: Large Reasoning Models Are Instruction-following Clustering Agents
arXiv preprint arXiv:2603.23518
-
Tailoring Memory Granularity for Multi-Hop Reasoning over Long Contexts
Findings of the Association for Computational Linguistics: EACL, 2026
-
AlphaLoRA: Assigning LoRA Experts Based on Layer Training Quality
Conference on Empirical Methods in Natural Language Processing, 2024
-
Prompt Space: Optimizing Few-shot Reasoning Success with Large Language Models
North American Chapter of the Association for Computational Linguistics, 2023
-
GammaE: Gamma Embeddings for Logical Queries on Knowledge Graphs
Conference on Empirical Methods in Natural Language Processing, 2022 · Oral Presentation
News
- 2026 New preprint: Cluster-R1 — Large Reasoning Models as Instruction-following Clustering Agents.
- 2026 Tailoring Memory Granularity for Multi-Hop Reasoning over Long Contexts accepted to EACL Findings 2026.
- Oct 2024 One paper accepted to EMNLP 2024. Many thanks to my co-authors!
- Sep 2023 Started my Ph.D. journey at Dartmouth College.
Teaching
- Graduate Teaching Assistant Artificial Intelligence — CS 76 / 276 Dartmouth College · Fall 2024
Service
Reviewer: NeurIPS 2024 · ICLR 2025 · AISTATS 2025 · ICASSP 2025.