RewardModelingBeyondBradleyTerry

kokoro-ruslan 开源

用 Ruslan 语料库训练俄语 Kokoro 语音模型

Kokoro Language Model Training Script for Russian (Ruslan Corpus)

vime 开源

用 vLLM 加速 LLM 强化学习后训练，采样更快、规模更大

An LLM post-training framework with vLLM for RL Scaling

aimet 开源

不重训模型，把已训练网络压到 4bit 还能保住精度

AIMET is a library that provides advanced quantization and compression techniques fo···

AgileRL 开源

让强化学习训练快 10 倍，超参自动调优，开箱即用

The complete post-training stack for LLMs, plus RL for any problem. SFT, DPO and mul···

LoongSage 开源

用验证过的配方，快速训出会调工具的智能体

A production-grade, high-efficiency Agentic RL framework for frontier LLMs with vali···

easevoice-trainer 开源

简单几步，训练你的专属语音克隆模型

EaseVoice Trainer is a simple and user-friendly voice cloning and speech model train···

nano-world-model 开源

用扩散强制训练世界模型，让机器人看懂视频并规划动作。

A Minimalist, Batteries-included Repository for Advancing World Model Science.

Matlab-GAN 开源

用 MATLAB 跑通多种 GAN，从入门到 CycleGAN 一步到位

MATLAB implementations of Generative Adversarial Networks -- from GAN to Pixel2Pixel···

SIM-CoT 开源

让模型在内部悄悄思考，推理更快更省token

[ICLR 2026] An official implementation of "SIM-CoT: Supervised Implicit Chain-of-Tho···