TradingAgents: Multi-Agents LLM Financial Trading Framework

分享一些好用的 Dify DSL 工作流程，自用、学习两相宜。 Sharing some Dify workflows.

Parallel Continuous Chain-of-Thought with Jacobi Iteration. Accepted to EMNLP 2025.

This is the official code of DeepSearch paper!

Rokkaku is Hugo theme that put emphasis on readability of Japanese and long sentences.

复现大模型相关算法及一些学习记录

[ICLR 2025 Oral] Block Diffusion: Interpolating Between Autoregressive and Diffusion Language Models

Mixture-of-Recursions: Learning Dynamic Recursive Depths for Adaptive Token-Level Computation (NeurIPS 2025)

An Easy-to-use LLM Logical Reasoning Ability Evaluation Framework

A framework for few-shot evaluation of language models.

🤖Auto Tutor: 一键批量发送套磁邮件

VERL 可视化、PRM、LLM-as-a-Judge

datasets from the paper "Towards Understanding Sycophancy in Language Models"

Command helper for slurm system. Act as if you are on compute node.

Fuzzy String Matching in Python

A very simple GRPO implement for reproducing r1-like LLM thinking.

📚LeetCUDA: Modern CUDA Learn Notes with PyTorch for Beginners🐑, 200+ CUDA Kernels, Tensor Cores, HGEMM, FA-2 MMA.🎉

非吳拼上海話輸入方案 · 非吴拼上海话输入方案

Training Sparse Autoencoders on Language Models

Repo for the paper "Detecting Logical Fallacies: From Quiz to Climate Change News" (2021)

A central, open resource for data and tools related to chain-of-thought reasoning in large language models. Developed @ Samwald research group: https://samwald.info/

800,000 step-level correctness labels on LLM solutions to MATH problems

This is the repository of HaluEval, a large-scale hallucination evaluation benchmark for Large Language Models.

STREET: a multi-task and multi-step reasoning dataset

Official repository for ACL 2025 paper "ProcessBench: Identifying Process Errors in Mathematical Reasoning"

gpt-oss-120b and gpt-oss-20b are two open-weight language models by OpenAI