Yizhe Zhang

Yizhe Zhang

Staff Research Scientist at Apple MLR

Yizhe Zhang

About Me

I am a Staff Research Scientist at Apple MLR, primarily working on Natural Language Processing and Machine Learning. Before joining Apple, I have been at Meta AI and Microsoft Research, working on natural language generation and NLP pre-training. I received my Ph.D. and M.S. degrees from Duke University. Before that, I received my B.Sc. degree in Physics from Nanjing University, Kuang Yaming Honors School, in 2011.
News
Apr 2026
SSD Released Simple self-distillation boosts Qwen3-30B from 42.4% to 55.3% pass@1 on LiveCodeBench v6—no external verifiers or teachers needed. Paper GitHub GitHub stars
Feb 2026
LaDi-RL Released Latent reasoning + RL achieving 20.5 on AIME25 and 52.7 on LCB v6 for an 8B model with 2x faster reasoning. Surprisingly, RL for latent reasoning doesn't suffer from entropy/diversity collapse! Paper
Jan 2026
6 Papers Accepted to ICLR 2026 Our work on diffusion-based language models continues to advance, covering masked diffusion for code generation (DiffuCoder), latent diffusion for text reasoning (LaDiR), few-step diffusion for long text generation (FS-DFM), continuous augmentation for discrete diffusion (CADD), adaptive reward shaping for efficient reasoning (LASER), and Bayesian experimental design with LLMs (BED-LLM).
Dec 2025
CLaRa Released CLaRa bridges retrieval and generation with continuous latent reasoning. 1k+ GitHub stars! GitHub GitHub stars
Jul 2025
DiffuCoder Released Masked diffusion for code generation with Coupled-GRPO, achieving +4.4% on EvalPlus. GitHub GitHub stars
Seeking Undergraduate and Master Students
I am seeking undergraduate and master students to reach out as potential collaborators. Please send me an email with your latest CV if you are working on text diffusion, latent reasoning, coding LLMs/agent, AI scientist and are interested in collaborating.
Research Interests

My recent research focuses on pushing LLMs to gain more intuition and strong generalization, especially in the code domain:

Code LLM & Agents Building intelligent coding assistants and autonomous agents that understand and generate code
Long-Horizon Planning Enabling LLMs to perform complex, multi-step reasoning and planning over extended sequences
RAG & Reasoning with Continuous Tokens Retrieval-augmented generation and reasoning systems using continuous token representations
Text Diffusion Models Advancing non-autoregressive generation through diffusion-based approaches
Coding-Based AI Scientist Developing AI systems that can autonomously discover knowledge through code
Academic Service

Area Chair / Senior Program Committee:

ICLR 2023-2025 ICML 2022-2025 NeurIPS 2020-2025 ACL 2020-2021 EMNLP 2022 NAACL 2023 AAAI 2018-2021

Editorial Roles:

  • Action Editor for Transactions on Machine Learning Research (TMLR, since 2023)
  • Action Editor for ACL Rolling Review (ARR, since 2023)

Organization:

  • Organization Committee Member, ACL 2020
Visitor Map