12 9 5

Ho Kei Cheng PRO

hkchengrex

https://hkchengrex.com/

AI & ML interests

None yet

Recent Activity

upvoted a paper 14 days ago

CFG-Zero*: Improved Classifier-Free Guidance for Flow Matching Models

upvoted a paper 18 days ago

Tokenize Image as a Set

new activity 24 days ago

hkchengrex/MMAudio:Runtime error

View all activity

Organizations

None yet

hkchengrex's activity

upvoted a paper 14 days ago

CFG-Zero*: Improved Classifier-Free Guidance for Flow Matching Models

Paper • 2503.18886 • Published 15 days ago • 20

upvoted a paper 18 days ago

Tokenize Image as a Set

Paper • 2503.16425 • Published 19 days ago • 15

New activity in hkchengrex/MMAudio 24 days ago

Runtime error

#15 opened 24 days ago by

CzanCzan

ZeroGPU: No CUDA GPUs are available

#3 opened 4 months ago by

hkchengrex

authored a paper 25 days ago

The Curse of Conditions: Analyzing and Improving Optimal Transport for Conditional Flow-Based Generation

Paper • 2503.10636 • Published 26 days ago • 3

upvoted a paper 25 days ago

The Curse of Conditions: Analyzing and Improving Optimal Transport for Conditional Flow-Based Generation

Paper • 2503.10636 • Published 26 days ago • 3

commented a paper 25 days ago

The Curse of Conditions: Analyzing and Improving Optimal Transport for Conditional Flow-Based Generation

Paper • 2503.10636 • Published 26 days ago • 3 •

liked a dataset about 1 month ago

Loie/VGGSound

Viewer • Updated Mar 26, 2023 • 1 • 1.8k • 32

upvoted a paper about 1 month ago

TheoremExplainAgent: Towards Multimodal Explanations for LLM Theorem Understanding

Paper • 2502.19400 • Published Feb 26 • 46

New activity in hkchengrex/MMAudio about 1 month ago

WHY DID IT START DOING THE TALKING BEN BURPS FOR NO REASON AT ALL

#14 opened about 1 month ago by

jerrythejohnson

Why do videos get much bigger by processing them?

#13 opened about 1 month ago by

KurtWoloch

upvoted a paper about 2 months ago

SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features

Paper • 2502.14786 • Published Feb 20 • 140

updated a Space about 2 months ago

638

MMAudio — generating synchronized audio from video/text

🔊

Create audio from videos or text prompts

New activity in hkchengrex/MMAudio 3 months ago

iframe

#9 opened 3 months ago by

Hamed744

upvoted a paper 3 months ago

Reconstruction vs. Generation: Taming Optimization Dilemma in Latent Diffusion Models

Paper • 2501.01423 • Published Jan 2 • 41

liked 2 datasets 3 months ago

deepghs/gelbooru_full

Preview • Updated 5 days ago • 8.33k • 43

deepghs/sankaku_full

Updated Jan 3 • 4.79k • 74

New activity in hkchengrex/MMAudio 3 months ago

Add model card

#1 opened 3 months ago by

nielsr

updated a model 4 months ago

hkchengrex/MMAudio

Updated Dec 24, 2024 • 61

authored a paper 4 months ago

Taming Multimodal Joint Training for High-Quality Video-to-Audio Synthesis

Paper • 2412.15322 • Published Dec 19, 2024 • 18