efficiency

PArallel Distributed Deep LEarning: Machine Learning Framework from Industrial Practice （『飞桨』核心框架，深度学习&机器学习高性能单机、分布式训练和跨平台部署）

💌A tiny (995KB) but mighty timer in **pure C** ! — almost no memory usage!❤️‍🔥 Supports clock, countdown, stopwatch, Pomodoro, and fully customizable tray animations (GIFs, CPU/Mem%) 💘 Don't be shy, join here🧸: https://discord.com/invite/W3tW2gtp6g

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

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

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

Official implementation of Würstchen: Efficient Pretraining of Text-to-Image Models

Official Implementation for the ACL 2026 paper "SARA: Selective and Adaptive Retrieval-augmented Generation with Context Compression"

[ICLR 2026 Oral] FlashVID: Efficient Video Large Language Models via Training-free Tree-based Spatiotemporal Token Merging

Official Pytorch Implementation of Length-Adaptive Transformer (ACL 2021)

Voice-driven writing, input, and cross-app work for your desktop.

A curated list of recent efficient video generation methods.

[NeurIPS 2025] VeriThinker: Learning to Verify Makes Reasoning Model Efficient

[ICLR 2026] Official code repository for "⚡️VisionTrim: Unified Vision Token Compression for Training-Free MLLM Acceleration"

[ICLR 2026] AgilePruner: An Empirical Study of Attention and Diversity for Adaptive Visual Token Pruning in Large Vision-Language Models

Light-MER for efficient multimodal emotion recognition with sub-1B MLLMs.

🥉 Codalab-Microsoft-COCO-Image-Captioning-Challenge 3rd place solution(06.30.21)

The official implementation of CVPR Workshop 2025 paper: Window Token Concatenation for Efficient Visual Large Language Models.