Comprehensive and timely academic information on federated learning (papers, frameworks, datasets, tutorials, workshops)

This is a collection of our NAS and Vision Transformer work.

Rigourous evaluation of LLM-synthesized code - NeurIPS 2023 & COLM 2024

An ultra fast cross-platform multiple screenshots module in pure Python using ctypes.

[EMNLP'25] s3 - ⚡ Efficient & Effective Search Agent Training via RL for RAG (Verifier-Powered RLVR for Search)

[ICLR 2024] Sheared LLaMA: Accelerating Language Model Pre-training via Structured Pruning

[ECCV 2020] Searching Efficient 3D Architectures with Sparse Point-Voxel Convolution

Easy-to-use data analysis / manipulation framework for humans

T-GATE: Temporally Gating Attention to Accelerate Diffusion Model for Free!

scalable and robust tree-based speculative decoding algorithm

Official repository for VisionZip (CVPR 2025)

[ICCV 2025] Official Implementation for "Lyra: An Efficient and Speech-Centric Framework for Omni-Cognition"

Vim plugin to suggest better movements

Training & evaluation library for text-based neural re-ranking and dense retrieval models built with PyTorch

[COLM 2024] TriForce: Lossless Acceleration of Long Sequence Generation with Hierarchical Speculative Decoding

Extend python lists operations using .NET's LINQ syntax for clean and fast coding.

An open-source python package for implementing and developing standard methods for calculating normalized metered energy consumption and avoided energy use.

Scaling Vision Pre-Training to 4K Resolution

[ECCV 2022] Official implementation of the paper "DeciWatch: A Simple Baseline for 10x Efficient 2D and 3D Pose Estimation"

Hash3D: Training-free Acceleration for 3D Generation