Daniil Cherniavskii's picture

2

Daniil Cherniavskii

Danchern

·

https://www.dcherniavskii.com/

danchern97

AI & ML interests

None yet

Recent Activity

upvoted a paper 13 days ago

Reward-Guided Speculative Decoding for Efficient LLM Reasoning

reacted to YerbaPage's post with 👍 2 months ago

We propose MGDebugger, a hierarchical bottom-up LLM code debugger 🔥 that can fix bugs from low-level syntax errors to high-level algorithmic flaws. It achieves an ⭐️ 18.9% improvement in accuracy over seed generations in HumanEval and a ⭐️ 97.6% repair success rate in HumanEvalFix. Paper available at https://arxiv.org/abs/2410.01215. Code and demo available at https://github.com/YerbaPage/MGDebugger.

upvoted a collection 4 months ago

LLM Reasoning Papers

View all activity

Organizations

models

None public yet

datasets

None public yet