hjkim

hojie11's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes

upvoted a paper 1 day ago

OS-Genesis: Automating GUI Agent Trajectory Construction via Reverse Task Synthesis

Paper • 2412.19723 • Published 8 days ago • 63

upvoted 3 papers 2 days ago

PERSE: Personalized 3D Generative Avatars from A Single Portrait

Paper • 2412.21206 • Published 4 days ago • 14

Explanatory Instructions: Towards Unified Vision Tasks Understanding and Zero-shot Generalization

Paper • 2412.18525 • Published 11 days ago • 59

Bringing Objects to Life: 4D generation from 3D objects

Paper • 2412.20422 • Published 6 days ago • 32

upvoted 11 papers 4 days ago

Toward Robust Hyper-Detailed Image Captioning: A Multiagent Approach and Dual Evaluation Metrics for Factuality and Coverage

Paper • 2412.15484 • Published 15 days ago • 14

Revisiting In-Context Learning with Long Context Language Models

Paper • 2412.16926 • Published 13 days ago • 27

Large Motion Video Autoencoding with Cross-modal Video VAE

Paper • 2412.17805 • Published 11 days ago • 23

Ensembling Large Language Models with Process Reward-Guided Tree Search for Better Complex Reasoning

Paper • 2412.15797 • Published 15 days ago • 15

DepthLab: From Partial to Complete

Paper • 2412.18153 • Published 11 days ago • 33

Fourier Position Embedding: Enhancing Attention's Periodic Extension for Length Generalization

Paper • 2412.17739 • Published 12 days ago • 37

VideoMaker: Zero-shot Customized Video Generation with the Inherent Force of Video Diffusion Models

Paper • 2412.19645 • Published 8 days ago • 13

From Elements to Design: A Layered Approach for Automatic Graphic Design Composition

Paper • 2412.19712 • Published 8 days ago • 14

Orient Anything: Learning Robust Object Orientation Estimation from Rendering 3D Models

Paper • 2412.18605 • Published 10 days ago • 17

1.58-bit FLUX

Paper • 2412.18653 • Published 10 days ago • 63

HuatuoGPT-o1, Towards Medical Complex Reasoning with LLMs

Paper • 2412.18925 • Published 10 days ago • 82

upvoted 4 papers 15 days ago

DI-PCG: Diffusion-based Efficient Inverse Procedural Content Generation for High-quality 3D Asset Creation

Paper • 2412.15200 • Published 15 days ago • 9

UIP2P: Unsupervised Instruction-based Image Editing via Cycle Edit Consistency

Paper • 2412.15216 • Published 15 days ago • 5

LeviTor: 3D Trajectory Oriented Image-to-Video Synthesis

Paper • 2412.15214 • Published 15 days ago • 15

No More Adam: Learning Rate Scaling at Initialization is All You Need

Paper • 2412.11768 • Published 19 days ago • 41

upvoted a paper 16 days ago

Prompting Depth Anything for 4K Resolution Accurate Metric Depth Estimation

Paper • 2412.14015 • Published 17 days ago • 12