IEEE

ROCODE: Integrating Backtracking Mechanism and Program Analysis in Large Language Models for Code Generation

Abstract: Large language models (LLMs) have achieved impressive performance in code generation recently, offering programmers revolutionary assistance in software development. However, due to the auto ...
IEEE

Fuzzy-Assisted Contrastive Decoding Improving Code Generation of Large Language Models

Abstract: Large language models (LLMs) play a crucial role in intelligent code generation tasks. Most existing work focuses on pretraining or fine-tuning specialized code LLMs, e.g., CodeLlama.
GitHub

Masked Diffusion Models for Code Generation

MLX support on Apple Silicon is in progress. We will make necessary updates to the repository once it is available. However, the generation pattern and post-training strategies of dLLMs remain ...
Electrek

In a first, renewables generate more power than coal globally

Solar and wind power aren’t just keeping up with global electricity demand anymore – they’re pulling ahead. According to a new analysis from energy think tank Ember, solar and wind combined outpaced ...