Lujun Li

57 papers A* 21B 3Misc 3Journal 22Unranked 8
YearRankTypeTitle / Venue / Authors
2026 A* conf
Outlier Matters: Efficient Long-to-Short Reasoning via Outlier-Guided Model Merging.
AAAI
Qiyuan Zhu, Dezhi Li, Lujun Li, Xiaoyu Qin, Wei Li, Hao Gu, Hua Xu, Sirui Han, Yike Guo
2026 A* conf
Sub-MoE: Efficient Mixture-of-Expert LLMs Compression via Subspace Expert Merging.
AAAI
Lujun Li, Qiyuan Zhu, Jiacheng Wang, Xiaoyu Qin, Wei Li, Hao Gu, Sirui Han, Yike Guo
2025 J jnl
BTC-LLM: Efficient Sub-1-Bit LLM Quantization via Learnable Transformation and Binary Codebook.
CoRR
Hao Gu, Lujun Li, Zheyu Wang, Bei Liu, Qiyuan Zhu, Sirui Han, Yike Guo
2025 — conf
BayesKD: Bayesian Knowledge Distillation for Compact LLMs in Constrained Fine-tuning Scenarios.
ACL (Findings)
Wei Li, Lujun Li, Mark G. Lee, Shengjie Sun, Lei Zhang, Wei Xue, Yike Guo
2025 A* conf
Can Compressed LLMs Truly Act? An Empirical Evaluation of Agentic Capabilities in LLM Compression.
ICML
Peijie Dong, Zhenheng Tang, Xiang Liu, Lujun Li, Xiaowen Chu, Bo Li
2025 J jnl
Can Compressed LLMs Truly Act? An Empirical Evaluation of Agentic Capabilities in LLM Compression.
CoRR
Peijie Dong, Zhenheng Tang, Xiang Liu, Lujun Li, Xiaowen Chu, Bo Li
2025 A* conf
Delta Decompression for MoE-based LLMs Compression.
ICML
Hao Gu, Wei Li, Lujun Li, Qiyuan Zhu, Mark G. Lee, Shengjie Sun, Wei Xue, Yike Guo
2025 J jnl
Delta Decompression for MoE-based LLMs Compression.
CoRR
Hao Gu, Wei Li, Lujun Li, Qiyuan Zhu, Mark G. Lee, Shengjie Sun, Wei Xue, Yike Guo
2025 A* conf
MoE-SVD: Structured Mixture-of-Experts LLMs Compression via Singular Value Decomposition.
ICML
Wei Li, Lujun Li, Hao Gu, You-Liang Huang, Mark G. Lee, Shengjie Sun, Wei Xue, Yike Guo
2025 A* conf
Outlier-Aware Model Merging for Efficient Multitask Inference.
ACM Multimedia
Qiyuan Zhu, Lujun Li, Dezhi Li, Jiacheng Liu, Pengyu Cheng, Yucheng Xu, Sirui Han, Yike Guo
2025 A* conf
ParZC: Parametric Zero-Cost Proxies for Efficient NAS.
AAAI
Peijie Dong, Lujun Li, Zhenheng Tang, Xiang Liu, Zimian Wei, Qiang Wang, Xiaowen Chu
2025 A* conf
STBLLM: Breaking the 1-Bit Barrier with Structured Binary LLMs.
ICLR
Peijie Dong, Lujun Li, Yuedong Zhong, Dayou Du, Ruibo Fan, Yuhan Chen, Zhenheng Tang, Qiang Wang, Wei Xue, Yike Guo, Xiaowen Chu
2025 J jnl
Sub-MoE: Efficient Mixture-of-Expert LLMs Compression via Subspace Expert Merging.
CoRR
Lujun Li, Qiyuan Zhu, Jiacheng Wang, Wei Li, Hao Gu, Sirui Han, Yike Guo
2024 A* conf
Adaptive Layer Sparsity for Large Language Models via Activation Correlation Assessment.
NeurIPS
Wei Li, Lujun Li, Mark G. Lee, Shengjie Sun
2024 — conf
AttnZero: Efficient Attention Discovery for Vision Transformers.
ECCV (5)
Lujun Li, Zimian Wei, Peijie Dong, Wenhan Luo, Wei Xue, Qifeng Liu, Yike Guo
2024 — conf
Auto-DAS: Automated Proxy Discovery for Training-Free Distillation-Aware Architecture Search.
ECCV (5)
Haosen Sun, Lujun Li, Peijie Dong, Zimian Wei, Shitong Shao
2024 — conf
Auto-GAS: Automated Proxy Discovery for Training-Free Generative Architecture Search.
ECCV (5)
Lujun Li, Haosen Sun, Shiwen Li, Peijie Dong, Wenhan Luo, Wei Xue, Qifeng Liu, Yike Guo
2024 A* conf
Auto-Prox: Training-Free Vision Transformer Architecture Search via Automatic Proxy Discovery.
AAAI
Zimian Wei, Peijie Dong, Zheng Hui, Anggeng Li, Lujun Li, Menglong Lu, Hengyue Pan, Dongsheng Li
2024 A* conf
DetKDS: Knowledge Distillation Search for Object Detectors.
ICML
Lujun Li, Yufan Bao, Peijie Dong, Chuanguang Yang, Anggeng Li, Wenhan Luo, Qifeng Liu, Wei Xue, Yike Guo
2024 A* conf
Discovering Sparsity Allocation for Layer-wise Pruning of Large Language Models.
NeurIPS
Lujun Li, Peijie Dong, Zhenheng Tang, Xiang Liu, Qiang Wang, Wenhan Luo, Wei Xue, Qifeng Liu, Xiaowen Chu, Yike Guo
2024 — conf
LPZero: Language Model Zero-cost Proxy Search from Zero.
EMNLP (Findings)
Peijie Dong, Lujun Li, Xiang Liu, Zhenheng Tang, Xuebo Liu, Qiang Wang, Xiaowen Chu
2024 J jnl
LPZero: Language Model Zero-cost Proxy Search from Zero.
CoRR
Peijie Dong, Lujun Li, Xiang Liu, Zhenheng Tang, Xuebo Liu, Qiang Wang, Xiaowen Chu
2024 J jnl
NoRA: Nested Low-Rank Adaptation for Efficient Fine-Tuning Large Models.
CoRR
Cheng Lin, Lujun Li, Dezhi Li, Jie Zou, Wei Xue, Yike Guo
2024 J jnl
ParZC: Parametric Zero-Cost Proxies for Efficient NAS.
CoRR
Peijie Dong, Lujun Li, Xinglin Pan, Zimian Wei, Xiang Liu, Qiang Wang, Xiaowen Chu
2024 A* conf
Pruner-Zero: Evolving Symbolic Pruning Metric From Scratch for Large Language Models.
ICML
Peijie Dong, Lujun Li, Zhenheng Tang, Xiang Liu, Xinglin Pan, Qiang Wang, Xiaowen Chu
2024 J jnl
Pruner-Zero: Evolving Symbolic Pruning Metric from scratch for Large Language Models.
CoRR
Peijie Dong, Lujun Li, Zhenheng Tang, Xiang Liu, Xinglin Pan, Qiang Wang, Xiaowen Chu
2024 J jnl
STBLLM: Breaking the 1-Bit Barrier with Structured Binary LLMs.
CoRR
Peijie Dong, Lujun Li, Dayou Du, Yuhan Chen, Zhenheng Tang, Qiang Wang, Wei Xue, Wenhan Luo, Qifeng Liu, Yike Guo, Xiaowen Chu
2024 A* conf
SasWOT: Real-Time Semantic Segmentation Architecture Search WithOut Training.
AAAI
Chendi Zhu, Lujun Li, Yuli Wu, Zhengxing Sun
2024 — conf
TVT: Training-Free Vision Transformer Search on Tiny Datasets.
ICPR (5)
Zimian Wei, Hengyue Pan, Lujun Li, Peijie Dong, Dongsheng Li
2024 A* conf
UniADS: Universal Architecture-Distiller Search for Distillation Gap.
AAAI
Liming Lu, Zhenghan Chen, Xiaoyu Lu, Yihang Rao, Lujun Li, Shuchao Pang
2024 J jnl
You Know What I'm Saying: Jailbreak Attack via Implicit Reference.
CoRR
Tianyu Wu, Lingrui Mei, Ruibin Yuan, Lujun Li, Wei Xue, Yike Guo
2023 — conf
A
CVPR Workshops
Lujun Li, Anggeng Li
2023 J jnl
Auto-Prox: Training-Free Vision Transformer Architecture Search via Automatic Proxy Discovery.
CoRR
Zimian Wei, Lujun Li, Peijie Dong, Zheng Hui, Anggeng Li, Menglong Lu, Hengyue Pan, Zhiliang Tian, Dongsheng Li
2023 A* conf
Automated Knowledge Distillation via Monte Carlo Tree Search.
ICCV
Lujun Li, Peijie Dong, Zimian Wei, Ya Yang
2023 J jnl
Catch-Up Distillation: You Only Need to Train Once for Accelerating Sampling.
CoRR
Shitong Shao, Xu Dai, Shouyi Yin, Lujun Li, Huanran Chen, Yang Hu
2023 Misc conf
DMFormer: Closing the gap Between CNN and Vision Transformers.
ICASSP
Zimian Wei, Hengyue Pan, Lujun Li, Menglong Lu, Xin Niu, Peijie Dong, Dongsheng Li
2023 A* conf
DisWOT: Student Architecture Search for Distillation WithOut Training.
CVPR
Peijie Dong, Lujun Li, Zimian Wei
2023 J jnl
DisWOT: Student Architecture Search for Distillation WithOut Training.
CoRR
Peijie Dong, Lujun Li, Zimian Wei
2023 A* conf
EMQ: Evolving Training-free Proxies for Automated Mixed Precision Quantization.
ICCV
Peijie Dong, Lujun Li, Zimian Wei, Xin Niu, Zhiliang Tian, Hengyue Pan
2023 J jnl
EMQ: Evolving Training-free Proxies for Automated Mixed Precision Quantization.
CoRR
Peijie Dong, Lujun Li, Zimian Wei, Xin Niu, Zhiliang Tian, Hengyue Pan
2023 J jnl
GP-NAS-ensemble: a model for NAS Performance Prediction.
CoRR
Kunlong Chen, Liu Yang, Yitian Chen, Kunjin Chen, Yidan Xu, Lujun Li
2023 A* conf
KD-Zero: Evolving Knowledge Distiller for Any Teacher-Student Pairs.
NeurIPS
Lujun Li, Peijie Dong, Anggeng Li, Zimian Wei, Ya Yang
2023 B conf
MENAS: Multi-trial Evolutionary Neural Architecture Search with Lottery Tickets.
ICIP
Zimian Wei, Hengyue Pan, Lujun Li, Peijie Dong, Xin Niu, Dongsheng Li
2023 A* conf
NORM: Knowledge Distillation via N-to-One Representation Matching.
ICLR
Xiaolong Liu, Lujun Li, Chao Li, Anbang Yao
2023 J jnl
NORM: Knowledge Distillation via N-to-One Representation Matching.
CoRR
Xiaolong Liu, Lujun Li, Chao Li, Anbang Yao
2023 Misc conf
Progressive Meta-Pooling Learning for Lightweight Image Classification Model.
ICASSP
Peijie Dong, Xin Niu, Zhiliang Tian, Lujun Li, Xiaodong Wang, Zimian Wei, Hengyue Pan, Dongsheng Li
2023 J jnl
Progressive Meta-Pooling Learning for Lightweight Image Classification Model.
CoRR
Peijie Dong, Xin Niu, Zhiliang Tian, Lujun Li, Xiaodong Wang, Zimian Wei, Hengyue Pan, Dongsheng Li
2023 Misc conf
RD-NAS: Enhancing One-Shot Supernet Ranking Ability Via Ranking Distillation From Zero-Cost Proxies.
ICASSP
Peijie Dong, Xin Niu, Lujun Li, Zhiliang Tian, Xiaodong Wang, Zimian Wei, Hengyue Pan, Dongsheng Li
2023 J jnl
RD-NAS: Enhancing One-shot Supernet Ranking Ability via Ranking Distillation from Zero-cost Proxies.
CoRR
Peijie Dong, Xin Niu, Lujun Li, Zhiliang Tian, Xiaodong Wang, Zimian Wei, Hengyue Pan, Dongsheng Li
2023 J jnl
TVT: Training-Free Vision Transformer Search on Tiny Datasets.
CoRR
Zimian Wei, Hengyue Pan, Lujun Li, Peijie Dong, Zhiliang Tian, Xin Niu, Dongsheng Li
2022 A* conf
Activation Modulation and Recalibration Scheme for Weakly Supervised Semantic Segmentation.
AAAI
Jie Qin, Jie Wu, Xuefeng Xiao, Lujun Li, Xingang Wang
2022 B conf
Boosting Online Feature Transfer via Separable Feature Fusion.
IJCNN
Lujun Li, Shiuan-Ni Liang, Ya Yang, Zhe Jin
2022 J jnl
Prior-Guided One-shot Neural Architecture Search.
CoRR
Peijie Dong, Xin Niu, Lujun Li, Linzhen Xie, Wenbin Zou, Tian Ye, Zimian Wei, Hengyue Pan
2022 — conf
Self-Regulated Feature Learning via Teacher-free Feature Distillation.
ECCV (26)
Lujun Li
2022 B conf
Teacher-free Distillation via Regularizing Intermediate Representation.
IJCNN
Lujun Li, Shiuan-Ni Liang, Ya Yang, Zhe Jin
2021 J jnl
Activation Modulation and Recalibration Scheme for Weakly Supervised Semantic Segmentation.
CoRR
Jie Qin, Jie Wu, Xuefeng Xiao, Lujun Li, Xingang Wang
2021 J jnl
Improving One-Shot NAS with Shrinking-and-Expanding Supernet.
Pattern Recognit.
Yiming Hu, Xingang Wang, Lujun Li, Qingyi Gu