Skip To Main Content
Kin Wai on Muck Rack

Kin Wai

As seen in: arXiv, MDPI
Is this you? As a journalist, you can create a free Muck Rack account to customize your profile, list your contact preferences, and upload a portfolio of your best work. Claim your profile
Back to Kin Wai’s profile

Articles by Kin Wai

Computer Science > Machine Learning

|
By Kin Wai
| arXiv
Training data attribution for diffusion models aims to identify the training samples that influence a generated instance, but existing methods either require costly per-sample gradient computation or query-specific model optimization. Moreover, most methods attribute changes in a proxy loss rather than changes in the actual model's generative behavior.
Open in Who Shared Issue with article?

Computer Science > Sound

|
By Kin Wai
| arXiv
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Open in Who Shared View Duplicates (341) Issue with article?

Omni-C: Compressing Heterogeneous Modalities into a Single Dense Encoder

|
By Kin Wai, de Gusmao, Pedro Porto Buarque
| arXiv
Open in Who Shared Issue with article?

Concept-TRAK: Understanding how diffusion models learn concepts through concept-level attribution

|
By Kin Wai
| arXiv
Open in Who Shared Issue with article?

NSDF Bridging Humanities and AI through Collaboration

|
By Kin Wai
| zenodo.org
Skip to main Published May 15, 2025 | Version v1 Poster Open NSDF Bridging Humanities and AI through Collaboration Files Sutherlin_2025_NSDF_AHM_NSDF_Bridging_AI_and_Humanities_through_Collaboration.pdf Accept all cookies Accept only essential cookies
Open in Who Shared Issue with article?

SteerMusic: Enhanced Musical Consistency for Zero-shot Text-Guided and Personalized Music Editing

|
By Kin Wai, Charles Patrick
| arXiv
Open in Who Shared Issue with article?

FSSUAVL: A Discriminative Framework using Vision Models for Federated Self-Supervised Audio and Image Understanding

|
By Kin Wai
| arXiv
Open in Who Shared Issue with article?

[2410.06016] Variable Bitrate Residual Vector Quantization for Audio Coding

|
By Kin Wai
| arXiv
arXiv:2410.06016 (cs) View PDF HTML (experimental) Comments: Subjects: Sound (cs.SD); Machine Learning (cs.LG); Audio and Speech Processing (eess.AS) Cite as: arXiv:2410.06016 [cs.SD] (or arXiv:2410.06016v1 [cs.SD] for this version) https://doi.org/10.48550/arXiv.2410.06016 Submission history From: Yunkee Chae [ view email] [v1] Tue, 8 Oct 2024 13:18:24 UTC (18,132 KB) Bibliographic Tools Bibliographic Explorer Toggle Bibliographic Explorer () Litmaps Toggle Litmaps (What is Litmaps?)...
Open in Who Shared View Duplicates (30) Issue with article?

FedRepOpt: Gradient Re-parametrized Optimizers in Federated Learning

|
By Kin Wai, de Gusmao, Pedro Porto Buarque
| arXiv
Open in Who Shared Issue with article?

[2409.06096] Latent Diffusion Bridges for Unsupervised Musical Audio Timbre Transfer

|
By Kin Wai
| arXiv
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Open in Who Shared View Duplicates (404) Issue with article?

DisMix: Disentangling Mixtures of Musical Instruments for Source-level Pitch and Timbre Manipulation

|
By Kin Wai
| arXiv
Coming this September, the Forum is free, virtual, and open to all. Sign Up and Learn more.
Open in Who Shared View Duplicates (687) Issue with article?

[2406.15751] Improving Unsupervised Clean-to-Rendered Guitar Tone Transformation Using GANs and Integrated Unaligned Clean Data

|
By Kin Wai, Jyh-Shing Roger
| arXiv
Open in Who Shared Issue with article?

AudioRepInceptionNeXt: A lightweight single-stream architecture for efficient audio recognition

|
By Kin Wai
| arXiv
Open in Who Shared Issue with article?

MR-MT3: Memory Retaining Multi-Track Music Transcription to Mitigate Instrument Leakage

|
By Kin Wai, Kin Wai Cheuk, Wei-Hsiang Liao, Taemin Cho
| arXiv
Open in Who Shared Issue with article?

Timbre-Trap: A Low-Resource Framework for Instrument-Agnostic Music Transcription

|
By Kin Wai
| arXiv
[Submitted on 27 Sep 2023 ( v1 ), last revised 24 Jan 2024 (this version, v2)] Title:Timbre-Trap: A Low-Resource Framework for Instrument-Agnostic Music Transcription Download a PDF of the paper titled Timbre-Trap: A Low-Resource Framework for Instrument-Agnostic Music Transcription, by Frank Cwitkowitz and 6 other authors Download PDF HTML (experimental) Abstract:In recent years, research on music transcription has focused mainly on architecture design and instrument-specific data acquisition.
Open in Who Shared View Duplicates (688) Issue with article?

Coordinated Information Campaigns on Social Media: A Multifaceted Framework for Detection and Analysis

|
By Kin Wai, Adriana Iamnitchi
| arXiv
Open in Who Shared Issue with article?

AudioInceptionNeXt: TCL AI LAB Submission to EPIC-SOUND Audio-Based-Interaction-Recognition Challenge 2023

|
By Kin Wai
| arXiv
arXiv:2307.07265 (cs) Download a PDF of the paper titled AudioInceptionNeXt: TCL AI LAB Submission to EPIC-SOUND Audio-Based-Interaction-Recognition Challenge 2023, by Kin Wai Lau and 3 other authors Download PDF Submission history From: Kin Wai Lau [ view email] [v1] Fri, 14 Jul 2023 10:39:05 UTC (116 KB) Bibliographic Tools Bibliographic Explorer Toggle Bibliographic Explorer () Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code,...
Open in Who Shared View Duplicates (559) Issue with article?

Experimental evaluation of baselines for forecasting social media timeseries - EPJ Data Science

|
By Kin Wai
| epjdatascience.springeropen.com
Our objective is to assess how well different baselines can capture key properties of time series in the context of per-topic social media activity. To this end, we evaluate the baselines described above against real data and across a set of relevant performance metrics. 4.1 Experimental setup We evaluate performance in forecasting social media activity on two platforms, Twitter and YouTube, on a number of topics from three different geo-political contexts.
Open in Who Shared Issue with article?

MERP: A Music Dataset with Emotion Ratings and Raters’ Profile Information

|
By Kat R. Agres, Dorien Herremans, Kin Wai Cheuk, Kin Wai
| MDPI
This is an early access version, the complete PDF, HTML, and XML versions will be available soon. Open AccessArticle by En Yan Koh 1, Kin Wai Cheuk 1, Kwan Yee Heung 1, Kat R.
Open in Who Shared Issue with article?
Show More