Researcher — paper.dinq.me

2026 顶会论文

作者位次 #4/5ICLR 2026Poster· Computer Vision / 3D Rendering & Reconstruction

Sparkle: A Robust and Versatile Representation for Point Cloud-based Human Motion Capture

YIMING REN · YUJING SUN · Aoru Xue · Kwok Yan Lam · Yuexin Ma

可解释性多模态社会与人本OpenReview

作者位次 #8/8ICLR 2026Poster· Social Aspects / Privacy-preserving Statistics and Machine Learning

MOAI: Module-Optimizing Architecture for Non-Interactive Secure Transformer Inference

Linru Zhang · Xiangning Wang · Jun Jie Sim · Zhicong Huang · Jiahao Zhong · HUAXIONG WANG · Pu Duan · Kwok Yan Lam

安全效率与系统社会与人本OpenReview

作者位次 #4/5ICLR 2026Poster· Theory / Domain Adaptation and Transfer Learning

SumRA: Parameter Efficient Fine-tuning with Singular Value Decomposition and Summed Orthogonal Basis

Chin Yuen Kwok · Yongsen Zheng · Jia Qi Yip · Kwok Yan Lam · Ensiong Chng

强化学习与后训练效率与系统理论与学习动力学OpenReview

作者位次 #3/4ACL 2026Workshop· ACL System Demonstrations

Spectra: A Mechanistic Interpretability Library for Vision-Language Models

Clement Neo · Yongsen Zheng · Kwok Yan Lam · Luke Ong

摘要

Vision-Language Models (VLMs) have become increasingly important in AI applications, yet interpretability tools for these models lag behind those available for text-only language models. While libraries like TransformerLens have enabled significant progress in understanding language models, exist...

可解释性多模态检索与知识OpenReview 项目页

Kwok Yan Lam

获取完整研究档案

联系方式

2026 顶会论文

Sparkle: A Robust and Versatile Representation for Point Cloud-based Human Motion Capture

MOAI: Module-Optimizing Architecture for Non-Interactive Secure Transformer Inference

SumRA: Parameter Efficient Fine-tuning with Singular Value Decomposition and Summed Orthogonal Basis

Spectra: A Mechanistic Interpretability Library for Vision-Language Models

常见合作者