4 14 12

Jiawei Liu

ganler

https://jw-liu.xyz/

AI & ML interests

Simplifying the making of great software.

Articles

BigCodeBench: Benchmarking Large Language Models on Solving Practical and Challenging Programming Tasks

Jun 18

• 38

StarCoder2-Instruct: Fully Transparent and Permissive Self-Alignment for Code Generation

Apr 29

• 73

Organizations

ganler's activity

upvoted a paper 7 days ago

Learning Code Preference via Synthetic Evolution

Paper • 2410.03837 • Published 29 days ago • 1

upvoted an article 9 days ago

Article

Accelerating LLM Inference: Fast Sampling with Gumbel-Max Trick

•

9 days ago

• 8

upvoted a paper 13 days ago

Evaluating Language Models for Efficient Code Generation

Paper • 2408.06450 • Published Aug 12 • 1

upvoted a paper 4 months ago

Agentless: Demystifying LLM-based Software Engineering Agents

Paper • 2407.01489 • Published Jul 1 • 42

upvoted an article 4 months ago

Article

BigCodeBench: Benchmarking Large Language Models on Solving Practical and Challenging Programming Tasks

Jun 18

• 38

upvoted an article 6 months ago

Article

StarCoder2-Instruct: Fully Transparent and Permissive Self-Alignment for Code Generation

Apr 29

• 73

upvoted a paper 6 months ago

XFT: Unlocking the Power of Code Instruction Tuning by Simply Merging Upcycled Mixture-of-Experts

Paper • 2404.15247 • Published Apr 23 • 3

upvoted a paper 8 months ago

StarCoder 2 and The Stack v2: The Next Generation

Paper • 2402.19173 • Published Feb 29 • 134

upvoted 3 papers 11 months ago

NeuRI: Diversifying DNN Generation via Inductive Rule Inference

Paper • 2302.02261 • Published Feb 4, 2023 • 3

Purple Llama CyberSecEval: A Secure Coding Benchmark for Language Models

Paper • 2312.04724 • Published Dec 7, 2023 • 20

Is Your Code Generated by ChatGPT Really Correct? Rigorous Evaluation of Large Language Models for Code Generation

Paper • 2305.01210 • Published May 2, 2023 • 4

upvoted a collection 11 months ago

ise-uiuc's Papers

Collection

7 items • Updated Mar 31 • 7

upvoted a paper 11 months ago

Magicoder: Source Code Is All You Need

Paper • 2312.02120 • Published Dec 4, 2023 • 79

upvoted a paper 12 months ago

Relax: Composable Abstractions for End-to-End Dynamic Machine Learning

Paper • 2311.02103 • Published Nov 1, 2023 • 16