ganler (Jiawei Liu)

upvoted a paper 14 days ago

Self-rewarding correction for mathematical reasoning

Paper • 2502.19613 • Published 16 days ago • 77

upvoted a paper 16 days ago

SWE-RL: Advancing LLM Reasoning via Reinforcement Learning on Open Software Evolution

Paper • 2502.18449 • Published 17 days ago • 68

upvoted an article 27 days ago

Article

Blazing-Fast Code Editing via Multi-Layer Speculation

By

and 3 others •

27 days ago

• 15

upvoted a paper 4 months ago

SelfCodeAlign: Self-Alignment for Code Generation

Paper • 2410.24198 • Published Oct 31, 2024 • 24

upvoted an article 5 months ago

Article

Accelerating LLM Inference: Fast Sampling with Gumbel-Max Trick

By

•

Oct 24, 2024

• 10

upvoted a paper 8 months ago

Agentless: Demystifying LLM-based Software Engineering Agents

Paper • 2407.01489 • Published Jul 1, 2024 • 61

upvoted an article 9 months ago

Article

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

Jun 18, 2024

• 46

upvoted an article 11 months ago

Article

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

Apr 29, 2024

• 76

upvoted a paper 11 months ago

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

Paper • 2404.15247 • Published Apr 23, 2024 • 3

upvoted a paper about 1 year ago

StarCoder 2 and The Stack v2: The Next Generation

Paper • 2402.19173 • Published Feb 29, 2024 • 138

upvoted 3 papers over 1 year 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 • 3

upvoted a collection over 1 year ago

ise-uiuc's Papers

Collection

7 items • Updated Mar 31, 2024 • 7

upvoted 2 papers over 1 year ago

Magicoder: Source Code Is All You Need

Paper • 2312.02120 • Published Dec 4, 2023 • 82

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

Paper • 2311.02103 • Published Nov 1, 2023 • 21

Jiawei Liu

AI & ML interests

Organizations

ganler's activity

Self-rewarding correction for mathematical reasoning

SWE-RL: Advancing LLM Reasoning via Reinforcement Learning on Open Software Evolution

Blazing-Fast Code Editing via Multi-Layer Speculation

SelfCodeAlign: Self-Alignment for Code Generation

Accelerating LLM Inference: Fast Sampling with Gumbel-Max Trick

Agentless: Demystifying LLM-based Software Engineering Agents

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

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

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

StarCoder 2 and The Stack v2: The Next Generation

NeuRI: Diversifying DNN Generation via Inductive Rule Inference

Purple Llama CyberSecEval: A Secure Coding Benchmark for Language Models

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

ise-uiuc's Papers

Magicoder: Source Code Is All You Need

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