Lujun Li

Orcid: 0000-0002-4329-2707

Affiliations:

Hong Kong University of Science and Technology, Hong Kong, SAR, China

According to our database¹, Lujun Li authored at least 43 papers between 2021 and 2025.

Collaborative distances:

Dijkstra number² of four.
Erdős number³ of four.

Timeline

Legend:

Book

In proceedings

Article

PhD thesis

Dataset

Other

Bibliography

2025

Sub-MoE: Efficient Mixture-of-Expert LLMs Compression via Subspace Expert Merging.

[BibT_eX]

[DOI]

CoRR, June, 2025

BTC-LLM: Efficient Sub-1-Bit LLM Quantization via Learnable Transformation and Binary Codebook.

[BibT_eX]

[DOI]

CoRR, June, 2025

Can Compressed LLMs Truly Act? An Empirical Evaluation of Agentic Capabilities in LLM Compression.

[BibT_eX]

[DOI]

CoRR, May, 2025

Delta Decompression for MoE-based LLMs Compression.

[BibT_eX]

[DOI]

CoRR, February, 2025

STBLLM: Breaking the 1-Bit Barrier with Structured Binary LLMs.

[BibT_eX]

[DOI]

Proceedings of the Thirteenth International Conference on Learning Representations, 2025

BayesKD: Bayesian Knowledge Distillation for Compact LLMs in Constrained Fine-tuning Scenarios.

[BibT_eX]

[DOI]

Proceedings of the Findings of the Association for Computational Linguistics, 2025

ParZC: Parametric Zero-Cost Proxies for Efficient NAS.

[BibT_eX]

[DOI]

Proceedings of the AAAI-25, Sponsored by the Association for the Advancement of Artificial Intelligence, February 25, 2025

2024

You Know What I'm Saying: Jailbreak Attack via Implicit Reference.

[BibT_eX]

[DOI]

CoRR, 2024

NoRA: Nested Low-Rank Adaptation for Efficient Fine-Tuning Large Models.

[BibT_eX]

[DOI]

CoRR, 2024

STBLLM: Breaking the 1-Bit Barrier with Structured Binary LLMs.

[BibT_eX]

[DOI]

CoRR, 2024

ParZC: Parametric Zero-Cost Proxies for Efficient NAS.

[BibT_eX]

[DOI]

CoRR, 2024

Adaptive Layer Sparsity for Large Language Models via Activation Correlation Assessment.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024, 2024

Discovering Sparsity Allocation for Layer-wise Pruning of Large Language Models.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024, 2024

TVT: Training-Free Vision Transformer Search on Tiny Datasets.

[BibT_eX]

[DOI]

Proceedings of the Pattern Recognition - 27th International Conference, 2024

DetKDS: Knowledge Distillation Search for Object Detectors.

[BibT_eX]

[DOI]

Proceedings of the Forty-first International Conference on Machine Learning, 2024

Pruner-Zero: Evolving Symbolic Pruning Metric From Scratch for Large Language Models.

[BibT_eX]

[DOI]

Proceedings of the Forty-first International Conference on Machine Learning, 2024

LPZero: Language Model Zero-cost Proxy Search from Zero.

[BibT_eX]

[DOI]

Proceedings of the Findings of the Association for Computational Linguistics: EMNLP 2024, 2024

Auto-DAS: Automated Proxy Discovery for Training-Free Distillation-Aware Architecture Search.

[BibT_eX]

[DOI]

Proceedings of the Computer Vision - ECCV 2024, 2024

AttnZero: Efficient Attention Discovery for Vision Transformers.

[BibT_eX]

[DOI]

Proceedings of the Computer Vision - ECCV 2024, 2024

Auto-GAS: Automated Proxy Discovery for Training-Free Generative Architecture Search.

[BibT_eX]

[DOI]

Proceedings of the Computer Vision - ECCV 2024, 2024

SasWOT: Real-Time Semantic Segmentation Architecture Search WithOut Training.

[BibT_eX]

[DOI]

Proceedings of the Thirty-Eighth AAAI Conference on Artificial Intelligence, 2024

Auto-Prox: Training-Free Vision Transformer Architecture Search via Automatic Proxy Discovery.

[BibT_eX]

[DOI]

Proceedings of the Thirty-Eighth AAAI Conference on Artificial Intelligence, 2024

UniADS: Universal Architecture-Distiller Search for Distillation Gap.

[BibT_eX]

[DOI]

Proceedings of the Thirty-Eighth AAAI Conference on Artificial Intelligence, 2024

2023

Auto-Prox: Training-Free Vision Transformer Architecture Search via Automatic Proxy Discovery.

[BibT_eX]

[DOI]

CoRR, 2023

TVT: Training-Free Vision Transformer Search on Tiny Datasets.

[BibT_eX]

[DOI]

CoRR, 2023

Catch-Up Distillation: You Only Need to Train Once for Accelerating Sampling.

[BibT_eX]

[DOI]

CoRR, 2023

GP-NAS-ensemble: a model for NAS Performance Prediction.

[BibT_eX]

[DOI]

CoRR, 2023

KD-Zero: Evolving Knowledge Distiller for Any Teacher-Student Pairs.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

NORM: Knowledge Distillation via N-to-One Representation Matching.

[BibT_eX]

[DOI]

Proceedings of the Eleventh International Conference on Learning Representations, 2023

MENAS: Multi-trial Evolutionary Neural Architecture Search with Lottery Tickets.

[BibT_eX]

[DOI]

Proceedings of the IEEE International Conference on Image Processing, 2023

Automated Knowledge Distillation via Monte Carlo Tree Search.

[BibT_eX]

[DOI]

Proceedings of the IEEE/CVF International Conference on Computer Vision, 2023

EMQ: Evolving Training-free Proxies for Automated Mixed Precision Quantization.

[BibT_eX]

[DOI]

Proceedings of the IEEE/CVF International Conference on Computer Vision, 2023

DMFormer: Closing the gap Between CNN and Vision Transformers.

[BibT_eX]

[DOI]

Proceedings of the IEEE International Conference on Acoustics, 2023

Progressive Meta-Pooling Learning for Lightweight Image Classification Model.

[BibT_eX]

[DOI]

Proceedings of the IEEE International Conference on Acoustics, 2023

RD-NAS: Enhancing One-Shot Supernet Ranking Ability Via Ranking Distillation From Zero-Cost Proxies.

[BibT_eX]

[DOI]

Proceedings of the IEEE International Conference on Acoustics, 2023

A<sup>2</sup>-Aug: Adaptive Automated Data Augmentation.

[BibT_eX]

[DOI]

Lujun Li

Anggeng Li

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023

DisWOT: Student Architecture Search for Distillation WithOut Training.

[BibT_eX]

[DOI]

Peijie Dong

Lujun Li

Zimian Wei

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023

2022

Prior-Guided One-shot Neural Architecture Search.

[BibT_eX]

[DOI]

CoRR, 2022

Teacher-free Distillation via Regularizing Intermediate Representation.

[BibT_eX]

[DOI]

Proceedings of the International Joint Conference on Neural Networks, 2022

Boosting Online Feature Transfer via Separable Feature Fusion.

[BibT_eX]

[DOI]

Proceedings of the International Joint Conference on Neural Networks, 2022

Self-Regulated Feature Learning via Teacher-free Feature Distillation.

[BibT_eX]

[DOI]

Lujun Li

Proceedings of the Computer Vision - ECCV 2022, 2022

Activation Modulation and Recalibration Scheme for Weakly Supervised Semantic Segmentation.

[BibT_eX]

[DOI]

Proceedings of the Thirty-Sixth AAAI Conference on Artificial Intelligence, 2022

2021

Improving One-Shot NAS with Shrinking-and-Expanding Supernet.

[BibT_eX]

[DOI]

Pattern Recognit., 2021

Lujun Li

Timeline

Legend:

Links

Online presence:

On csauthors.net:

Bibliography

Loading...