huangd1999

AgentCoder

This Repo is the official implementation of AgentCoder and AgentCoder+.

EffiBench

EffiBench: Benchmarking the Efficiency of Automatically Generated Code

BORT

Two Heads are Better than One: Robust Learning Meets Multi-branch Models

SOAP

This is the official implementation of the paper: Self-Optimization Improves the Efficiency of Code Generation

CodeCoT

This repo provide a CoT text to code dataset, which can increase 3\% human eval performace in Llama model.

KAT

This is the official implementation repository for the paper titled "KAT: Towards Building More Robust Models with Kolmogorov–Arnold Networks-Based Adversarial Training"

BackdoorBench

cceval

CrossCodeEval: A Diverse and Multilingual Benchmark for Cross-File Code Completion (NeurIPS 2023)

clash-freenode

订阅地址🚀 免费共享♻️ 定期更新✨ 科学上网🌈 请勿滥用🚫一键订阅📪

FeatureMapPruning

[ICLR'24] Code for our ICLR 2024 paper 'Adversarial Feature Map Pruning for Backdoor'

FuzzingTransformerPrograms

huangd1999.github.io

Github Pages template for academic personal websites, forked from mmistakes/minimal-mistakes

huangd1999_backup.github.io

ICCV23-Towards-Building-More-Robust-Models-with-Frequency-Bias

[ICCV'23] The official PyTorch implementation of our ICCV 2023 paper: 'Towards Building More Robust Models with Frequency Bias'.

LLMDebugger

LDB: A Large Language Model Debugger via Verifying Runtime Execution Step by Step

SWE-agent

SWE-agent takes a GitHub issue and tries to automatically fix it, using GPT-4, or your LM of choice. It solves 12.29% of bugs in the SWE-bench evaluation set and takes just 1.5 minutes to run.

tree-of-thoughts

Plug in and Play Implementation of Tree of Thoughts: Deliberate Problem Solving with Large Language Models that Elevates Model Reasoning by atleast 70%