Pengxiang Li's picture

Pengxiang Li

pengxiang

·

pixeli

AI & ML interests

Video generation, Image editing, AD

Recent Activity

upvoted a paper 1 day ago

UI-TARS: Pioneering Automated GUI Interaction with Native Agents

upvoted a paper 6 days ago

Inference-Time Scaling for Diffusion Models beyond Scaling Denoising Steps

upvoted a paper 10 days ago

SPAM: Spike-Aware Adam with Momentum Reset for Stable LLM Training

View all activity

Organizations

None yet

pengxiang's activity

commented a paper 16 days ago

InfiGUIAgent: A Multimodal Generalist GUI Agent with Native Reasoning and Reflection

Paper • 2501.04575 • Published 16 days ago • 23 •

commented a paper about 1 month ago

Mix-LN: Unleashing the Power of Deeper Layers by Combining Pre-LN and Post-LN

Paper • 2412.13795 • Published Dec 18, 2024 • 19 •

commented a paper about 2 months ago

DreamMix: Decoupling Object Attributes for Enhanced Editability in Customized Image Inpainting

Paper • 2411.17223 • Published Nov 26, 2024 • 5 •

New activity in diffusers/controlnet-canny-sdxl-1.0 over 1 year ago

Dynamically adjust the guidance scale for ControlNet XL

#8 opened over 1 year ago by

New activity in fusing/fill50k over 1 year ago

How to load it from local?

#1 opened over 1 year ago by