Starred repositories
🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.
Open-source deep-learning framework for exploring, building and deploying AI weather/climate workflows.
Image-native typed decisions with shared visual encoding and Qwen3-VL
Open multimodal decision models, 0.8B to 27B, for text, images and video. Decide with probabilities over your own candidates and locate with bounding boxes, in place of generated text. Free API, ON…
LLM-authored task-specific Jev harnesses with optional full-trajectory reward reflection and GEPA evolution.
A nano replica of Jev: parallel decisions, dynamic candidates, and an end-to-end training pipeline.
Self-evolving cognitive decision engine & TypeSafe Jev alternative. Deliberative decision flywheel ('explore first, crystallize later' System 2→1) with 100% option-order invariance. Typed probabili…
Official implementation of GUI-R1 : A Generalist R1-Style Vision-Language Action Model For GUI Agents
QuantBot(AI 量化机器人)的全量源码。基于 **Go+React + TypeScript + Vite** 构建,通过 **Wails** 与 Go 后端通信,提供 A 股量化交易的图形界面:六维判势、多因子选股、AI 智能体决策、策略回测、实时活动、审计日志等。
[EMNLP'23, ACL'24] To speed up LLMs' inference and enhance LLM's perceive of key information, compress the prompt and KV-Cache, which achieves up to 20x compression with minimal performance loss.
Implementation of Speculative Sampling as described in "Accelerating Large Language Model Decoding with Speculative Sampling" by Deepmind
[ICML 2026 Outstanding Paper] Minimalist RL for Diffusion LLMs. 89.1% on GSM8K.
[ICLR 2024] Official implementation of "TimeMixer: Decomposable Multiscale Mixing for Time Series Forecasting"
Code for our paper "VisionTS: Visual Masked Autoencoders Are Free-Lunch Zero-Shot Time Series Forecasters".
Free English to Chinese Dictionary Database
Official code repository for paper "VisionTS++: Cross-Modal Time Series Foundation Model with Continual Pre-trained Visual Backbones"
xhcoding / emacs-libvterm
Forked from akermu/emacs-libvtermEmacs libvterm integration
[GCPR 2026 Oral] Unlocking Pretrained Vision Transformers for Time Series Classification
Experimental code for wavelet GPT and Fourier series expression
WavSpA: Wavelet Space Attention for Enhancing Transformer's Long Sequence Learning
Unofficial mirror. Eat is developed at https://codeberg.org/akib/emacs-eat
[ICLR 2024] Official implementation of " 🦙 Time-LLM: Time Series Forecasting by Reprogramming Large Language Models"
An offical implementation of PatchTST: "A Time Series is Worth 64 Words: Long-term Forecasting with Transformers."
ekto42 / GPT4TS
Forked from DAMO-DI-ML/NeurIPS2023-One-Fits-AllThe official code for "One Fits All: Power General Time Series Analysis by Pretrained LM (NeurIPS 2023 Spotlight)"
The official implementation of "TS-Agent: Reinforcement Learning Empowered LLM Agents for Financial Time Series Forecasting"