Zhou

kzhou35

https://kevinz-01.github.io/

Kevinz-01

AI & ML interests

AI agent and responsible AI

Recent Activity

updated a dataset 25 days ago

kzhou35/misalignment-indicators-bloom-rollouts

published a model 27 days ago

kzhou35/sft_qwen3_8_5mini_summary

published a dataset about 1 month ago

kzhou35/misalignment-indicators-bloom-rollouts

View all activity

Organizations

None yet

upvoted a paper 2 months ago

Length Value Model: Scalable Value Pretraining for Token-Level Length Modeling

Paper • 2604.27039 • Published Apr 29 • 26

upvoted a paper 9 months ago

Presenting a Paper is an Art: Self-Improvement Aesthetic Agents for Academic Presentations

Paper • 2510.05571 • Published Oct 7, 2025 • 15

upvoted a paper about 1 year ago

SafeKey: Amplifying Aha-Moment Insights for Safety Reasoning

Paper • 2505.16186 • Published May 22, 2025 • 7

upvoted a collection about 1 year ago

SafeKey

Models and data for the SafeKey paper. • 7 items • Updated Jun 6, 2025 • 2

upvoted 2 papers over 1 year ago

Multimodal Inconsistency Reasoning (MMIR): A New Benchmark for Multimodal Reasoning Models

Paper • 2502.16033 • Published Feb 22, 2025 • 18

The Hidden Risks of Large Reasoning Models: A Safety Assessment of R1

Paper • 2502.12659 • Published Feb 18, 2025 • 7

upvoted a paper almost 2 years ago

Multimodal Situational Safety

Paper • 2410.06172 • Published Oct 8, 2024 • 12