mingdazhang

mingdazhang's activity

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

authored 2 papers 10 months ago

BoT: Breaking Long Thought Processes of o1-like Large Language Models through Backdoor Attack

Paper • 2502.12202 • Published Feb 16

BackdoorBench: A Comprehensive Benchmark of Backdoor Learning

Paper • 2206.12654 • Published Jun 25, 2022 • 1

authored a paper 11 months ago

Inference-Time Scaling for Diffusion Models beyond Scaling Denoising Steps

Paper • 2501.09732 • Published Jan 16 • 71

authored a paper over 1 year ago

VDC: Versatile Data Cleanser for Detecting Dirty Samples via Visual-Linguistic Inconsistency

Paper • 2309.16211 • Published Sep 28, 2023