ZhangZicong

zhangzico

7

·

AI & ML interests

ML theory, model merging

Recent Activity

upvoted a paper 3 days ago

EvoSafeHarness: Evolving Model- and Domain-Specific Harnesses for Securing Agents

upvoted a paper 5 months ago

World-R1: Reinforcing 3D Constraints for Text-to-Video Generation

upvoted a paper over 1 year ago

ColorBench: Can VLMs See and Understand the Colorful World? A Comprehensive Benchmark for Color Perception, Reasoning, and Robustness

View all activity

Organizations

upvoted a paper 3 days ago

EvoSafeHarness: Evolving Model- and Domain-Specific Harnesses for Securing Agents

Paper • 2609.05903 • Published 9 days ago • 58

upvoted a paper 5 months ago

World-R1: Reinforcing 3D Constraints for Text-to-Video Generation

Paper • 2604.24764 • Published Apr 27 • 121

upvoted 5 papers over 1 year ago

ColorBench: Can VLMs See and Understand the Colorful World? A Comprehensive Benchmark for Color Perception, Reasoning, and Robustness

Paper • 2504.10514 • Published Apr 10, 2025 • 48

How Instruction and Reasoning Data shape Post-Training: Data Quality through the Lens of Layer-wise Gradients

Paper • 2504.10766 • Published Apr 14, 2025 • 40

Missing Premise exacerbates Overthinking: Are Reasoning Models losing Critical Thinking Skill?

Paper • 2504.06514 • Published Apr 9, 2025 • 39

C3PO: Critical-Layer, Core-Expert, Collaborative Pathway Optimization for Test-Time Expert Re-Mixing

Paper • 2504.07964 • Published Apr 10, 2025 • 62

Improved Visual-Spatial Reasoning via R1-Zero-Like Training

Paper • 2504.00883 • Published Apr 1, 2025 • 67