Yuanze Lin's picture

3 2

Yuanze Lin

YuanzeLin

AI & ML interests

Multimodal Large Language Models; Diffusion Models

Recent Activity

upvoted a paper 23 days ago

SpatialThinker: Reinforcing 3D Reasoning in Multimodal LLMs via Spatial Rewards

authored a paper 6 months ago

Text-Driven Image Editing via Learnable Regions

authored a paper 6 months ago

DreamPolisher: Towards High-Quality Text-to-3D Generation via Geometric Diffusion

View all activity

Organizations

None yet

upvoted a paper 23 days ago

SpatialThinker: Reinforcing 3D Reasoning in Multimodal LLMs via Spatial Rewards

Paper • 2511.07403 • Published 30 days ago • 13

upvoted 2 papers 6 months ago

Olympus: A Universal Task Router for Computer Vision Tasks

Paper • 2412.09612 • Published Dec 12, 2024 • 4

IllumiCraft: Unified Geometry and Illumination Diffusion for Controllable Video Generation

Paper • 2506.03150 • Published Jun 3 • 21