Junzhuo Li

25 papers A* 5Journal 14Unranked 6
YearRankTypeTitle / Venue / Authors
2026 A* conf
Deconstructing Pre-training: Knowledge Attribution Analysis in MoE and Dense Models.
AAAI
Bo Wang, Junzhuo Li, Hong Chen, Yuanlin Chu, Yuxuan Fan, Xuming Hu
2026 J jnl
Deconstructing Pre-training: Knowledge Attribution Analysis in MoE and Dense Models.
CoRR
Bo Wang, Junzhuo Li, Hong Chen, Yuanlin Chu, Yuxuan Fan, Xuming Hu
2026 J jnl
Optimal Expert-Attention Allocation in Mixture-of-Experts: A Scalable Law for Dynamic Model Design.
CoRR
Junzhuo Li, Peijie Jiang, Changxin Tian, Jia Liu, Zhiqiang Zhang, Xuming Hu
2025 — conf
Capturing Nuanced Preferences: Preference-Aligned Distillation for Small Language Models.
ACL (Findings)
Yanggan Gu, Junzhuo Li, Sirui Huang, Xin Zou, Zhenghua Li, Xuming Hu
2025 J jnl
Capturing Nuanced Preferences: Preference-Aligned Distillation for Small Language Models.
CoRR
Yanggan Gu, Junzhuo Li, Sirui Huang, Xin Zou, Zhenghua Li, Xuming Hu
2025 — conf
Decoding Knowledge Attribution in Mixture-of-Experts: A Framework of Basic-Refinement Collaboration and Efficiency Analysis.
ACL (1)
Junzhuo Li, Bo Wang, Xiuze Zhou, Peijie Jiang, Jia Liu, Xuming Hu
2025 J jnl
Decoding Knowledge Attribution in Mixture-of-Experts: A Framework of Basic-Refinement Collaboration and Efficiency Analysis.
CoRR
Junzhuo Li, Bo Wang, Xiuze Zhou, Peijie Jiang, Jia Liu, Xuming Hu
2025 A* conf
Dynamic Expert Specialization: Towards Catastrophic Forgetting-Free Multi-Domain MoE Adaptation.
EMNLP
Junzhuo Li, Bo Wang, Xiuze Zhou, Xuming Hu
2025 J jnl
Dynamic Expert Specialization: Towards Catastrophic Forgetting-Free Multi-Domain MoE Adaptation.
CoRR
Junzhuo Li, Bo Wang, Xiuze Zhou, Xuming Hu
2025 — conf
Exploring Engineering Undergraduate's Critical Thinking Patterns in AI-Enhanced Learning: A TCSA Method.
ICBL
Dongchen Pan, Taotao Long, Xiaomeng Zhu, Junzhuo Li
2025 A* conf
Internal Chain-of-Thought: Empirical Evidence for Layer-wise Subtask Scheduling in LLMs.
EMNLP
Zhipeng Yang, Junzhuo Li, Siyu Xia, Xuming Hu
2025 J jnl
Internal Chain-of-Thought: Empirical Evidence for Layer-wise Subtask Scheduling in LLMs.
CoRR
Zhipeng Yang, Junzhuo Li, Siyu Xia, Xuming Hu
2025 J jnl
LoTA-QAF: Lossless Ternary Adaptation for Quantization-Aware Fine-Tuning.
CoRR
Junyu Chen, Junzhuo Li, Zhen Peng, Wenjie Wang, Yuxiang Ren, Long Shi, Xuming Hu
2025 J jnl
Unveiling Instruction-Specific Neurons & Experts: An Analytical Framework for LLM's Instruction-Following Capabilities.
CoRR
Junyan Zhang, Yubo Gao, Yibo Yan, Jungang Li, Zhaorui Hou, Sicheng Tao, Shuliang Liu, Song Dai, Yonghua Hei, Junzhuo Li, Xuming Hu
2024 J jnl
The Fine Line: Navigating Large Language Model Pretraining with Down-streaming Capability Analysis.
CoRR
Chen Yang, Junzhuo Li, Xinyao Niu, Xinrun Du, Songyang Gao, Haoran Zhang, Zhaoliang Chen, Xingwei Qu, Ruibin Yuan, Yizhi Li, Jiaheng Liu, Stephen W. Huang, Shawn Yue, Wenhu Chen, Jie Fu, Ge Zhang
2023 A* conf
DEPN: Detecting and Editing Privacy Neurons in Pretrained Language Models.
EMNLP
Xinwei Wu, Junzhuo Li, Minghui Xu, Weilong Dong, Shuangzhi Wu, Chao Bian, Deyi Xiong
2023 J jnl
DEPN: Detecting and Editing Privacy Neurons in Pretrained Language Models.
CoRR
Xinwei Wu, Junzhuo Li, Minghui Xu, Weilong Dong, Shuangzhi Wu, Chao Bian, Deyi Xiong
2023 A* conf
Language Representation Projection: Can We Transfer Factual Knowledge across Languages in Multilingual Language Models?
EMNLP
Shaoyang Xu, Junzhuo Li, Deyi Xiong
2023 J jnl
Language Representation Projection: Can We Transfer Factual Knowledge across Languages in Multilingual Language Models?
CoRR
Shaoyang Xu, Junzhuo Li, Deyi Xiong
2023 — conf
Tab-CQA: A Tabular Conversational Question Answering Dataset on Financial Reports.
ACL (industry)
Chuang Liu, Junzhuo Li, Deyi Xiong
2023 J jnl
Urban Resident Travel Survey Method Based on Cellular Signaling Data.
ISPRS Int. J. Geo Inf.
Junzhuo Li, Wenyong Li, Guan Lian
2022 J jnl
FewFedWeight: Few-shot Federated Learning Framework across Multiple NLP Tasks.
CoRR
Weilong Dong, Xinwei Wu, Junzhuo Li, Shuangzhi Wu, Chao Bian, Deyi Xiong
2022 — conf
KaFSP: Knowledge-Aware Fuzzy Semantic Parsing for Conversational Question Answering over a Large-Scale Knowledge Base.
ACL (1)
Junzhuo Li, Deyi Xiong
2022 J jnl
Swing Distillation: A Privacy-Preserving Knowledge Distillation Framework.
CoRR
Junzhuo Li, Xinwei Wu, Weilong Dong, Shuangzhi Wu, Chao Bian, Deyi Xiong
2020 — conf
MDPeQA: A Pediatric Question Answering System Based on Multiple Data Sources.
CLSW
Junzhuo Li, Hongying Zan, Yingjie Yan, Kunli Zhang