Siyuan Hu

h-siyuan's activity

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

upvoted a paper 7 days ago

The Image as Its Own Reward: Reinforcement Learning with Adversarial Reward for Image Generation

Paper • 2511.20256 • Published 7 days ago • 26

updated a Space 7 days ago

Running

2

AUI

🌖

2

Display a gallery of images

upvoted a paper 8 days ago

Computer-Use Agents as Judges for Generative User Interface

Paper • 2511.15567 • Published 13 days ago • 50

liked a Space 13 days ago

Running

2

AUI

🌖

2

Display a gallery of images

upvoted a paper 16 days ago

WEAVE: Unleashing and Benchmarking the In-context Interleaved Comprehension and Generation

Paper • 2511.11434 • Published 18 days ago • 44

upvoted a paper 20 days ago

Grounding Computer Use Agents on Human Demonstrations

Paper • 2511.07332 • Published 22 days ago • 103

upvoted a paper 28 days ago

VCode: a Multimodal Coding Benchmark with SVG as Symbolic Visual Representation

Paper • 2511.02778 • Published 28 days ago • 101

upvoted a paper about 2 months ago

Paper2Video: Automatic Video Generation from Scientific Papers

Paper • 2510.05096 • Published Oct 6 • 115

upvoted a paper 6 months ago

Paper2Poster: Towards Multimodal Poster Automation from Scientific Papers

Paper • 2505.21497 • Published May 27 • 109

upvoted 3 papers 9 months ago

Impossible Videos

Paper • 2503.14378 • Published Mar 18 • 61

TPDiff: Temporal Pyramid Video Diffusion Model

Paper • 2503.09566 • Published Mar 12 • 45

PhotoDoodle: Learning Artistic Image Editing from Few-Shot Pairwise Data

Paper • 2502.14397 • Published Feb 20 • 41

upvoted 4 papers 10 months ago

WorldGUI: Dynamic Testing for Comprehensive Desktop GUI Automation

Paper • 2502.08047 • Published Feb 12 • 28

TextAtlas5M: A Large-scale Dataset for Dense Text Image Generation

Paper • 2502.07870 • Published Feb 11 • 46

MakeAnything: Harnessing Diffusion Transformers for Multi-Domain Procedural Sequence Generation

Paper • 2502.01572 • Published Feb 3 • 21

Video-MMMU: Evaluating Knowledge Acquisition from Multi-Discipline Professional Videos

Paper • 2501.13826 • Published Jan 23 • 25

liked a Space 10 months ago

Running

33

UI-TARS

🌖

33

Find click coordinates on images based on instructions

updated a Space 12 months ago

Runtime error

Featured

240

ShowUI

💻

240

Generate clickable coordinates on a screenshot

New activity in showlab/ShowUI-2B 12 months ago

Reference VRAM usage

2

#8 opened 12 months ago by

av-codes

New activity in showlab/ShowUI about 1 year ago

[Solved] About user uploaded screenshot

2

#4 opened about 1 year ago by

marekb-sci