3 papers
cs.AI2026
Planned Diffusion
Daniel Israel, Tian Jin, Ellie Cheng +4
Most large language models are autoregressive: they generate tokens one at a time. Discrete diffusion language models can generate multiple tokens in parallel, but sampling from th…
cs.PL2026
Sharing State Between Prompts and Programs
Ellie Y. Cheng, Logan Weber, Tian Jin +1
The rise of large language models (LLMs) has introduced a new type of programming: natural language programming. Users write prompts, which are instructions in natural language, to…
cs.CL2025
Learning to Keep a Promise: Scaling Language Model Decoding Parallelism with Learned Asynchronous Decoding
Tian Jin, Ellie Y. Cheng, Zack Ankner +6
Decoding with autoregressive large language models (LLMs) traditionally occurs sequentially, generating one token after another. An emerging line of work explored parallel decoding…