cd/entity/Huangjie ZhengĀ· homeā€ŗ entitiesā€ŗ Huangjie Zheng
grep -l @huangjie zheng /news/*.json | wc -l ā†’ 1

Huangjie Zheng

mentions 1 type Person feed RSS

// recent coverage 1 mentions

00:00
2026-07-16
machinelearning.apple.com
large-language-models

Embarrassingly Simple Self-Distillation Improves Code Generation

Simple self-distillation (SSD) improves LLM code generation by fine-tuning models on their own sampled outputs, boosting Qwen3-30B-Instruct from 42.4% to 55.3% pass@1 on LiveCodeBench v6, with gains cā€¦

// co-occurs with top 7 entities
Apple 1 Qwen3-30B-Instruct 1 LiveCodeBench v6 1 Qwen 1 Llama 1 Ruixiang Zhang 1 Richard He Bai 1
// topics top 5 topics
large language models 1 machine learning 1 artificial intelligence 1 ai research 1 natural language processing 1