Digital Red Queen: Adversarial Program Evolution in Core War with LLMs

📰 Must-read papers and blogs on Speculative Decoding ⚡️

s1: Simple test-time scaling

Simple RL training for reasoning

Fully open reproduction of DeepSeek-R1

Fine-tuning & Reinforcement Learning for LLMs. 🦥 Train OpenAI gpt-oss, DeepSeek, Qwen, Llama, Gemma, TTS 2x faster with 70% less VRAM.

This is the repository that contains the source code for the Self-Evaluation Guided MCTS for online DPO.

这是一款提高ChatGPT的数据安全能力和效率的插件。并且免费共享大量创新功能，如：自动刷新、保持活跃、数据安全、取消审计、克隆对话、言无不尽、净化页面、展示大屏、拦截跟踪、日新月异、明察秋毫等。让我们的AI体验无比安全、顺畅、丝滑、高效、简洁。

Official repository of the paper "Sign Language Translation with Sentence Embedding Supervision" ACL 2024

JailbreakBench: An Open Robustness Benchmark for Jailbreaking Language Models [NeurIPS 2024 Datasets and Benchmarks Track]

scalable and robust tree-based speculative decoding algorithm

Any model. Any hardware. Zero compromise. Built with @ziglang / @openxla / MLIR / @bazelbuild

Minimum Bayes Risk Decoding for Hugging Face Transformers

Ask GPT to run a command

The dataset of WMT22 Metrics Shared Task extended with annotations of 28 types of Chinese Multiword Expressions (MWEs).

TextGrad: Automatic ''Differentiation'' via Text -- using large language models to backpropagate textual gradients. Published in Nature.

Haste: a fast, simple, and open RNN library

Official repository of the xLSTM.

Structured Outputs

Official code and data of "3AM: An Ambiguity-Aware Multi-Modal Machine Translation Dataset"

This code repository is for the accepted ACL2022 paper "On Vision Features in Multimodal Machine Translation". We provide the details and scripts for the proposed probing tasks. We hope the code co…

The FLORES+ Machine Translation Benchmark

Imported from mdict analysis

Repository of all mined assets including sprites, news items, sound files, translations, and 3D Assets for Pokemon GO.

Tool to query the Pokémon corpus