papers

Publications (13)

cs.CV2022

Activation Template Matching Loss for Explainable Face Recognition

Huawei Lin, Haozhe Liu, Qiufu Li +1

Can we construct an explainable face recognition network able to learn a facial part-based feature like eyes, nose, mouth and so forth, without any manual annotation or additionals…

cs.CL2024

Token-wise Influential Training Data Retrieval for Large Language Models

Huawei Lin, Jikai Long, Zhaozhuo Xu +1

Given a Large Language Model (LLM) generation, how can we identify which training data led to this generation? In this paper, we proposed RapidIn, a scalable framework adapting to…

cs.CV2025

VTBench: Evaluating Visual Tokenizers for Autoregressive Image Generation

Huawei Lin, Tong Geng, Zhaozhuo Xu +1

Autoregressive (AR) models have recently shown strong performance in image generation, where a critical component is the visual tokenizer (VT) that maps continuous pixel inputs to…

cs.CL2026

DebiasRAG: A Tuning-Free Path to Fair Generation in Large Language Models through Retrieval-Augmented Generation

Rui Chu, Bingyin Zhao, Thanh Quoc Hung Le +6

Large language models (LLMs) have achieved unprecedented success due to their exceptional generative capabilities. However, because they depend on knowledge encapsulated from train…

cs.CL2025

UniGuardian: A Unified Defense for Detecting Prompt Injection, Backdoor Attacks and Adversarial Attacks in Large Language Models

Huawei Lin, Yingjie Lao, Tong Geng +2

Large Language Models (LLMs) are vulnerable to attacks like prompt injection, backdoor attacks, and adversarial attacks, which manipulate prompts or models to generate harmful outp…

cs.AI2026

MUSE-Autoskill: Self-Evolving Agents via Skill Creation, Memory, Management, and Evaluation

Huawei Lin, Peng Li, Jie Song +2

Large language model (LLM) agents rely on reusable skills to solve complex tasks, but existing skill creation approaches often treat skills as isolated, static artifacts, limiting…

cs.CV2022

Research on Gender-related Fingerprint Features

Yong Qi, Yanping Li, Huawei Lin +2

Fingerprint is an important biological feature of human body, which contains abundant gender information. At present, the academic research of fingerprint gender characteristics is…

cs.LG2025

ALinFiK: Learning to Approximate Linearized Future Influence Kernel for Scalable Third-Party LLM Data Valuation

Yanzhou Pan, Huawei Lin, Yide Ran +5

Large Language Models (LLMs) heavily rely on high-quality training data, making data valuation crucial for optimizing model performance, especially when working within a limited bu…

cs.LG2026

Randomized Antipodal Search Done Right for Data Pareto Improvement of LLM Unlearning

Ziwen Liu, Huawei Lin, Yide Ran +5

Large language models (LLMs) sometimes memorize undesirable knowledge, which must be removed after deployment. Prior work on machine unlearning has focused largely on optimization…

cs.CV2026

DMin: Scalable Training Data Influence Estimation for Diffusion Models

Huawei Lin, Yingjie Lao, Weijie Zhao

Identifying the training data samples that most influence a generated image is a critical task in understanding diffusion models (DMs), yet existing influence estimation methods ar…

cs.LG2025

Online Gradient Boosting Decision Tree: In-Place Updates for Efficient Adding/Deleting Data

Huawei Lin, Jun Woo Chung, Yingjie Lao +1

Gradient Boosting Decision Tree (GBDT) is one of the most popular machine learning models in various applications. However, in the traditional settings, all data should be simultan…

cs.CL2026

RapidUn: Influence-Driven Parameter Reweighting for Efficient Large Language Model Unlearning

Guoshenghui Zhao, Huawei Lin, Weijie Zhao

Removing specific data influence from large language models (LLMs) remains challenging, as retraining is costly and existing approximate unlearning methods are often unstable. The…

cs.AI2025

Agent-Omni: Test-Time Multimodal Reasoning via Model Coordination for Understanding Anything

Huawei Lin, Yunzhi Shi, Tong Geng +3

Multimodal large language models (MLLMs) have shown strong capabilities but remain limited to fixed modality pairs and require costly fine-tuning with large aligned datasets. Build…