“The PDF is super slow to render, I guess because it contains commands from programmatically generated figures. It gives it a kind of an academic-paper-feel I miss these days. https://arxiv.org/pdf/2405.20519”
Diffusion On Syntax Trees For Program Synthesis
Large language models generate code one token at a time. Their autoregressive generation process lacks the feedback of observing the program's output. Training LLMs to suggest edits directly can be challenging due to the scarcity of rich edit data. To address these problems, we propose neural diffusion models that operate on syntax trees of any context-free grammar. Similar to image diffusion models, our method also inverts ``noise'' applied to syntax trees. Rather than generating code sequentially, we iteratively edit it while preserving syntactic validity, which makes it easy to combine this neural model with search. We apply our approach to inverse graphics tasks, where our model learns to convert images into programs that produce those images. Combined with search, our model is able to write graphics programs, see the execution result, and debug them to meet the required specifications. We additionally show how our system can write graphics programs for hand-drawn sketches.
候选层:至少 2 个不同的人、在 2 个不同月份提到过,还没到主书架的 3 人 3 个月。没有做立场标注,所以只写“被提及”。
HN 书评
推荐在前,同类按时间 · 每篇最多保留 20 条,统计用全部提及“This was a very cool paper about using diffusion language models and beam search: https://arxiv.org/html/2405.20519v1 Just looking at all of the amazing tools and workflows that people have made with ComfyUI and stuff makes me wonder what we could do with diffusion LMs. It seems diffusion models are much more easily hackable than LLMs.”
- Diffusion on Syntax Trees for Program Synthesis ↗23B1 · 2024-06-04 · 2 分