Shaobo (Steven) Wang

NCFM. Official PyTorch implementation of the paper "Dataset Distillation with Neural Characteristic Function: A Minmax Perspective" (NCFM) in CVPR 2025 (Full Score, Highlight).

Awesome-HITWH-Resources-Sharing. Awesome Resource Sharing Project for HITWH-CS

Awesome-Dataset-Reduction. A curated list of awesome papers on dataset reduction, including dataset distillation (dataset condensation) and dataset pruning (coreset selection).

Data-Whisperer. Code for ACL 2025 Main paper "Data Whisperer: Efficient Data Selection for Task-Specific LLM Fine-Tuning via Few-Shot In-Context Learning".

OPUS. Code for ICML 2026 Oral paper "OPUS: Towards Efficient and Principled Data Selection in Large Language Model Pre-training in Every Iteration."

AutoGnothi. Official PyTorch code for ICLR 2025 paper "Gnothi Seauton: Empowering Faithful Self-Interpretability in Black-Box Models"

ArtisticCloudBlog. Artistic Neural Style Transfer Software for DIY Stylized images and videos creations.

VideoCompressa. Code for VideoCompressa: Data-Efficient Video Understanding via Joint Temporal Compression and Spatial Reconstruction

EssenceBench. Official PyTorch implementation of the paper "Rethinking LLM Evaluation: Can We Evaluate LLMs with 200× Less Data" (EssenceBench) in ICLR 2026.

Socratic-Zero. Socratic-Zero is a fully autonomous framework that generates high-quality training data for mathematical reasoning

nn-visualizer. PyTorch implementation for "Visualizing the Emergence of Intermediate Visual Patterns in DNNs", NeurIPS 2021

Q-tuning. Code for paper Q-Tuning: Winning the Pruning Gamble: A Unified Approach to Joint Sample and Token Pruning for Efficient Supervised Fine-Tuning

Unveiling-Induction-Heads. PyTorch implementation for "Unveiling Induction Heads: Provable Training Dynamics and Feature Learning in Transformers", NeurIPS 2024

InfoUtil. Official PyTorch implementation of the paper "Grounding and Enhancing Informativeness and Utility in Dataset Distillation" (InfoUtil) in ICLR 2026.

gszfwsb. homepage

easy-rl. 强化学习中文教程（蘑菇书），在线阅读地址：https://datawhalechina.github.io/easy-rl/

Awesome-In-Context-Learning. Paper List for In-context Learning 🌷

Awesome-Dataset-Distillation. A curated list of awesome papers on dataset distillation and related applications.