Long-RL: Scaling RL to Long Sequences

A High-Efficiency System of Large Language Model Based Search Agents

Survey: https://arxiv.org/pdf/2507.20198

Official Repo for SparseLLM: Global Pruning of LLMs (NeurIPS 2024)

TinyML and Efficient Deep Learning Computing | MIT 6.S965/6.5940

A deep learning framework that implements Early Exit strategies in Convolutional Neural Networks (CNNs) using Deep Q-Learning (DQN). This project enhances computational efficiency by dynamically determining the optimal exit point in a neural network for image classification tasks on CIFAR-10.

Official PyTorch implementation of the paper "Dataset Distillation via the Wasserstein Metric" (ICCV 2025).

Dynamic Attention Mask (DAM) generate adaptive sparse attention masks per layer and head for Transformer models, enabling long-context inference with lower compute and memory overhead without fine-tuning.

Task-Aware Dynamic Model Optimization for Multi-Task Learning (IEEE Access 2023)

Code for paper "Automated Design for Hardware-aware Graph Neural Networks on Edge Devices"