Haokun Lin

Haokun Lin

Auto-generated profile, based on publicly available information

Haokun Lin

Institute of Automation, Chinese Academy of Sciences

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 January 2024
Verified
Conference Paper
Open access
PDF file
RLRuikang Liu
Ruikang Liu
HBHaoli Bai
Haoli Bai
HLHaokun Lin
Haokun Lin
YLYuening Li
Yuening Li
HGHan Gao
Han Gao
YCYuan Chun
Yuan Chun
Ruikang Liu, Haoli Bai, Haokun Lin, Yuening Li, Han Gao, Zhengzhuo Xu, Lu Hou, Jun Yao, Chun Yuan. Findings of the Association for Computational Linguistics ACL 2024. 2024.

27 May 2024 in Preprints.org
Verified
Preprint
Open access
PDF file
YZYingtao Zhang
Yingtao Zhang
HBHaoli Bai
Haoli Bai
HLHaokun Lin
Haokun Lin
JZJialin Zhao
Jialin Zhao
LHLu Hou
Lu Hou
Carlo Vittorio CannistraciCarlo Vittorio Cannistraci
Carlo Vittorio Cannistraci
With the rapid growth of large language models (LLMs), there is increasing demand for memory and computation in LLMs. Recent efforts on post-training pruning of LLMs aim to reduce the model size and computation requirements, yet the performance is still sub-optimal. In this paper, we present a plug-and-play solution for post-training pruning of LLMs. The proposed solution has two innovative components: 1) Relative Importance and Activations (RIA), a new pruning metric that jointly considers the weight and activations efficiently on LLMs; and 2) Channel Permutation, a new approach to maximally preserve important weights under N:M sparsity. The two proposed components can be readily combined to further enhance the N:M semi-structured pruning of LLMs. Our empirical experiments show that RIA alone can already surpass all existing post-training pruning methods on prevalent LLMs, e.g., LLaMA ranging from 7B to 65B. Furthermore, N:M semi-structured pruning with channel permutation can even outperform the original LLaMA2-70B on zero-shot tasks, together with practical speed-up on specific hardware. Our code is available at: https://github.com/biomedical-cybernetics/Relative-importance-and-activation-pruning

18 August 2025 in IEEE Transactions on Multimedia
Verified
Journal Article
Closed access
YZYinan Zhou
Yinan Zhou
YWYaxiong Wang
Yaxiong Wang
HLHaokun Lin
Haokun Lin
CMChen Ma
Chen Ma
LZLi Zhu
Li Zhu
Zhedong ZhengZhedong Zheng
Zhedong Zheng
Composed Image Retrieval (CIR) aims to search an image of interest using a combination of a reference image and modification text as the query. Despite recent advancements, this task remains challenging due to limited training data and laborious triplet annotation processes. To address this issue, this paper proposes to synthesize the training triplets to augment the training resource for the CIR problem. Specifically, we commence by training a modification text generator exploiting large-scale multimodal models and scale up the CIR learning throughout both the pretraining and fine-tuning stages. During pretraining, we leverage the trained generator to directly create Modification Text-oriented Synthetic Triplets (MTST) conditioned on pairs of images. For fine-tuning, we first synthesize reverse modification text to connect the target image back to the reference image. Subsequently, we devise a two-hop alignment strategy to incrementally close the semantic gap between the multimodal pair and the target image. We initially learn an implicit prototype utilizing both the original triplet and its reversed version in a cycle manner, followed by combining the implicit prototype feature with the modification text to facilitate accurate alignment with the target image. Extensive experiments validate the efficacy of the generated triplets and confirm that our proposed methodology attains competitive recall on both the CIRR and FashionIQ benchmarks. Codes and datasets will be made publicly accessible.

1 November 2026 in IEEE Transactions on Circuits and Systems for Video Technology
Verified
Journal Article
Closed access
LYLianwei Yang
Lianwei Yang
HLHaokun Lin
Haokun Lin
TZTianchen Zhao
Tianchen Zhao
YWYichen Wu
Yichen Wu
HZHongyu Zhu
Hongyu Zhu
QGQingyi Gu
Qingyi Gu

10 April 2026 in IEEE Transactions on Circuits and Systems for Video Technology
Verified
Journal Article
Closed access
ZWZhiwu Wang
Zhiwu Wang
YWYichen Wu
Yichen Wu
RWRenzhen Wang
Renzhen Wang
HLHaokun Lin
Haokun Lin
QWQuanziang Wang
Quanziang Wang
DMDeyu Meng
Deyu Meng
Class-Incremental Learning (CIL) aims to prevent catastrophic forgetting of previously learned classes while sequentially incorporating new ones. Few-shot CIL (FSCIL) presents a more challenging setting by introducing novel classes with only a few labeled examples, which significantly increases the risk of overfitting beyond the standard challenges faced in CIL. While catastrophic forgetting has been extensively studied, overfitting in FSCIL, especially when using large foundation models, has received comparatively limited attention. To fill this gap, we propose Singular Value Fine-tuning for FSCIL (SVFCL) and compare it with existing Parameter Efficient Fine-Tuning (PEFT) methods like prompt tuning and Low-Rank Adaptation (LoRA). Specifically, SVFCL applies singular value decomposition to the foundation model weights. For each task, the singular vectors are kept fixed while only the singular values are fine-tuned, and the updated singular values are subsequently merged to obtain the adapted model. This simple yet effective approach not only alleviates the problem of catastrophic forgetting but also mitigates overfitting more effectively by significantly reducing the number of trainable parameters. The effectiveness of SVFCL is validated through extensive experiments on four benchmark datasets, accompanied by thorough ablation studies and in-depth discussions.

25 August 2026 in Machine Intelligence Research
Verified
Journal Article
Open access
PDF file
HLHaokun Lin
Haokun Lin
HXHaobo Xu
Haobo Xu
YWYichen Wu
Yichen Wu
ZGZiyu Guo
Ziyu Guo
RZRenrui Zhang
Renrui Zhang
ZSZhenan Sun
Zhenan Sun
Recent advances in diffusion large language models (dLLMs) have introduced a promising alternative to autoregressive (AR) LLMs for natural language generation tasks, leveraging full attention and denoising-based decoding strategies. However, the deployment of these models on edge devices remains challenging due to their massive parameter scale and high resource demands. While post-training quantization (PTQ) has emerged as a widely adopted technique for compressing AR LLMs, its applicability to dLLMs remains largely unexplored. In this work, we present the first systematic study on quantizing diffusion-based language models. We begin by identifying the presence of activation outliers, characterized by abnormally large activation values that dominate the dynamic range. These outliers pose a key challenge to low-bit quantization, as they make it difficult to preserve precision for the majority of values. More importantly, we implement state-of-the-art PTQ methods and conduct a comprehensive evaluation across multiple task types and model variants. Our analysis is structured along four key dimensions: bit-width, quantization method, task category, and model type. Through this multi-perspective evaluation, we offer that practical insights into the quantization behavior of dLLMs under different configurations. We hope that our findings provide a foundation for future research in efficient dLLM deployment. Our code is publicly available at https://github.com/MessiX77/QDLM .