Ming Li

MingLiiii's activity

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

authored a paper about 1 month ago

Understanding the Thinking Process of Reasoning Models: A Perspective from Schoenfeld's Episode Theory

Paper • 2509.14662 • Published Sep 18 • 13

upvoted a paper about 1 month ago

Understanding the Thinking Process of Reasoning Models: A Perspective from Schoenfeld's Episode Theory

Paper • 2509.14662 • Published Sep 18 • 13

commented a paper about 1 month ago

Understanding the Thinking Process of Reasoning Models: A Perspective from Schoenfeld's Episode Theory

Paper • 2509.14662 • Published Sep 18 • 13 •

2

upvoted 2 papers 3 months ago

Beyond Pass@1: Self-Play with Variational Problem Synthesis Sustains RLVR

Paper • 2508.14029 • Published Aug 19 • 118

VisR-Bench: An Empirical Study on Visual Retrieval-Augmented Generation for Multilingual Long Document Understanding

Paper • 2508.07493 • Published Aug 10 • 8

upvoted 2 papers 4 months ago

Skip a Layer or Loop it? Test-Time Depth Adaptation of Pretrained LLMs

Paper • 2507.07996 • Published Jul 10 • 34

MusiXQA: Advancing Visual Music Understanding in Multimodal Large Language Models

Paper • 2506.23009 • Published Jun 28 • 10

upvoted a paper 5 months ago

Where to find Grokking in LLM Pretraining? Monitor Memorization-to-Generalization without Test

Paper • 2506.21551 • Published Jun 26 • 28

upvoted 3 papers 7 months 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 • 48

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

Paper • 2504.10766 • Published Apr 14 • 40

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

Paper • 2504.06514 • Published Apr 9 • 39

upvoted a paper 8 months ago

CoSTAast: Cost-Sensitive Toolpath Agent for Multi-turn Image Editing

Paper • 2503.10613 • Published Mar 13 • 79

updated a dataset 8 months ago

MingLiiii/Layer_Gradient

Preview • Updated Mar 1 • 36

published a dataset 8 months ago

MingLiiii/Layer_Gradient

Preview • Updated Mar 1 • 36

upvoted a paper about 1 year ago

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

Paper • 2410.23743 • Published Oct 31, 2024 • 63

authored 3 papers over 1 year ago

From Quantity to Quality: Boosting LLM Performance with Self-Guided Data Selection for Instruction Tuning

Paper • 2308.12032 • Published Aug 23, 2023 • 1

Reflection-Tuning: Data Recycling Improves LLM Instruction-Tuning

Paper • 2310.11716 • Published Oct 18, 2023 • 5

Superfiltering: Weak-to-Strong Data Filtering for Fast Instruction-Tuning

Paper • 2402.00530 • Published Feb 1, 2024 • 1

updated 2 datasets almost 2 years ago

umd-zhou-lab/sRecycled_Wiz70

Viewer • Updated Dec 21, 2023 • 46.6k • 9 • 2

umd-zhou-lab/sRecycled_Alpaca

Viewer • Updated Dec 21, 2023 • 37.1k • 10 • 2