Hongyu Zhao

cindermond's activity

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

upvoted a paper 8 days ago

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

Paper • 2504.10514 • Published 14 days ago • 45

upvoted a paper 9 days ago

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

Paper • 2504.10766 • Published 10 days ago • 39

upvoted a paper 15 days ago

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

Paper • 2504.06514 • Published 16 days ago • 39

upvoted a paper about 1 month ago

R1-Zero's "Aha Moment" in Visual Reasoning on a 2B Non-SFT Model

Paper • 2503.05132 • Published Mar 7 • 57

upvoted 5 papers 6 months ago

What Happened in LLMs Layers when Trained for Fast vs. Slow Thinking: A Gradient Perspective

Paper • 2410.23743 • Published Oct 31, 2024 • 64

Diffusion Curriculum: Synthetic-to-Real Generative Curriculum Learning via Image-Guided Diffusion

Paper • 2410.13674 • Published Oct 17, 2024 • 17

BenTo: Benchmark Task Reduction with In-Context Transferability

Paper • 2410.13804 • Published Oct 17, 2024 • 20

Your Mixture-of-Experts LLM Is Secretly an Embedding Model For Free

Paper • 2410.10814 • Published Oct 14, 2024 • 52

WALL-E: World Alignment by Rule Learning Improves World Model-based LLM Agents

Paper • 2410.07484 • Published Oct 9, 2024 • 50

upvoted a paper over 1 year ago

In-Context Learning Creates Task Vectors

Paper • 2310.15916 • Published Oct 24, 2023 • 43