Zhuokai Zhao's picture

2 6 1

Zhuokai Zhao

zhuokai

·

https://zhuokai-zhao.com/

AI & ML interests

Data-Efficient Learning, LLM Reasoning and Safety, Active Learning, Recommender System

Recent Activity

upvoted a paper 13 days ago

ViCrit: A Verifiable Reinforcement Learning Proxy Task for Visual Perception in VLMs

upvoted a paper 20 days ago

MORSE-500: A Programmatically Controllable Video Benchmark to Stress-Test Multimodal Reasoning

new activity 2 months ago

meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8:Quantizer: Running into an error with quantization "TypeError: 'dict' object is not callable"

View all activity

Organizations

upvoted a paper 13 days ago

ViCrit: A Verifiable Reinforcement Learning Proxy Task for Visual Perception in VLMs

Paper • 2506.10128 • Published 18 days ago • 22

upvoted a paper 20 days ago

MORSE-500: A Programmatically Controllable Video Benchmark to Stress-Test Multimodal Reasoning

Paper • 2506.05523 • Published 24 days ago • 33

upvoted a paper 3 months ago

ShieldAgent: Shielding Agents via Verifiable Safety Policy Reasoning

Paper • 2503.22738 • Published Mar 26 • 17

upvoted a paper 9 months ago

Quantifying Generalization Complexity for Large Language Models

Paper • 2410.01769 • Published Oct 2, 2024 • 14

upvoted 2 papers 12 months ago

AgentPoison: Red-teaming LLM Agents via Poisoning Memory or Knowledge Bases

Paper • 2407.12784 • Published Jul 17, 2024 • 52

MJ-Bench: Is Your Multimodal Reward Model Really a Good Judge for Text-to-Image Generation?

Paper • 2407.04842 • Published Jul 5, 2024 • 57