Junhan ZHU's picture

Open to Collab

Junhan ZHU

Alrightlone

·

https://alrightlone.github.io/

Alrightlone

AI & ML interests

Efficient AI

Recent Activity

upvoted a paper 2 days ago

PASA: A Principled Embedding-Space Watermarking Approach for LLM-Generated Text under Semantic-Invariant Attacks

upvoted a paper 25 days ago

Seedance 2.0: Advancing Video Generation for World Complexity

upvoted a paper 25 days ago

Qwen3.5-Omni Technical Report

View all activity

Organizations

None yet

authored 2 papers about 1 month ago

LVOmniBench: Pioneering Long Audio-Video Understanding Evaluation for Omnimodal LLMs

Paper • 2603.19217 • Published Mar 19 • 28

Cross-Resolution Diffusion Models via Network Pruning

Paper • 2604.05524 • Published Apr 7

authored a paper 7 months ago

OBS-Diff: Accurate Pruning For Diffusion Models in One-Shot

Paper • 2510.06751 • Published Oct 8, 2025 • 22