Han-Bit Kang

hbkang

AI & ML interests

Recent Activity

updated a collection 8 days ago

cool-papers

upvoted a paper 8 days ago

Differential Transformer

upvoted a paper 9 days ago

BLIP3-KALE: Knowledge Augmented Large-Scale Dense Captions

View all activity

Organizations

None yet

hbkang's activity

upvoted a paper 8 days ago

Differential Transformer

Paper • 2410.05258 • Published Oct 7 • 166

upvoted a paper 9 days ago

BLIP3-KALE: Knowledge Augmented Large-Scale Dense Captions

Paper • 2411.07461 • Published 15 days ago • 21

upvoted a paper 13 days ago

Acoustic Volume Rendering for Neural Impulse Response Fields

Paper • 2411.06307 • Published 17 days ago • 5

upvoted a paper 23 days ago

Learning Video Representations without Natural Videos

Paper • 2410.24213 • Published 26 days ago • 14

upvoted 2 papers about 1 month ago

DAWN: Dynamic Frame Avatar with Non-autoregressive Diffusion Framework for Talking Head Video Generation

Paper • 2410.13726 • Published Oct 17 • 10

Meissonic: Revitalizing Masked Generative Transformers for Efficient High-Resolution Text-to-Image Synthesis

Paper • 2410.08261 • Published Oct 10 • 49

upvoted a paper about 2 months ago

FAN: Fourier Analysis Networks

Paper • 2410.02675 • Published Oct 3 • 24

upvoted 3 papers 3 months ago

Open-MAGVIT2: An Open-Source Project Toward Democratizing Auto-regressive Visual Generation

Paper • 2409.04410 • Published Sep 6 • 23

The VoxCeleb Speaker Recognition Challenge: A Retrospective

Paper • 2408.14886 • Published Aug 27 • 8

CSGO: Content-Style Composition in Text-to-Image Generation

Paper • 2408.16766 • Published Aug 29 • 17

upvoted a paper 5 months ago

Grokfast: Accelerated Grokking by Amplifying Slow Gradients

Paper • 2405.20233 • Published May 30 • 6

upvoted a paper 7 months ago

COCONut: Modernizing COCO Segmentation

Paper • 2404.08639 • Published Apr 12 • 27

upvoted a paper 9 months ago

EMO: Emote Portrait Alive - Generating Expressive Portrait Videos with Audio2Video Diffusion Model under Weak Conditions

Paper • 2402.17485 • Published Feb 27 • 189

upvoted 7 papers 10 months ago

Scalable High-Resolution Pixel-Space Image Synthesis with Hourglass Diffusion Transformers

Paper • 2401.11605 • Published Jan 21 • 22

StreamDiffusion: A Pipeline-level Solution for Real-time Interactive Generation

Paper • 2312.12491 • Published Dec 19, 2023 • 69

Synthesizing Moving People with 3D Control

Paper • 2401.10889 • Published Jan 19 • 12

Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data

Paper • 2401.10891 • Published Jan 19 • 59