Theory & Scaling
Unifying diffusion formulations, scaling laws, training objectives, probabilistic inference, and model architectures.
DiffuLM @ NeurIPS 2026
Diffusion Language Models:
Foundations, Efficiency, and Reasoning
The first NeurIPS workshop dedicated to diffusion language models
WorkshopDecember 12, 2026
LocationSydney, Australia · Full day
Paper deadline
August 31, 2026 September 5, 2026 · AoEExtended
Closes in
Calculating…
Workshop focus
From foundations to intelligence
Efficiency
Parallel decoding, fast sampling, long-context generation, serving, evaluation, and hardware-aware systems.
Reasoning
Global self-correction, diverse solution paths, test-time scaling, planning, code generation, and RL post-training.
Six invited talks
Invited Speakers
Stefano Ermon
Stanford University
Subham Sahoo
MBZUAI
Arash Vahdat
NVIDIA Research
Volodymyr Kuleshov
Cornell · Inception Labs
Itai Gat
Meta Superintelligence Lab
Aditya Grover
UCLA · Inception
Academia × Industry
Organizers
Jinjie Ni
Senior Research Scientist
Google DeepMind
Shansan Gong
Ph.D. Candidate
HKU
Amin Karimi Monsefi
Ph.D. Candidate
Ohio State University
Yuchen Zhu
Ph.D. Candidate
Georgia Tech
Irina Belousova
ML Engineering Manager
Apple
Michael Qizhe Shieh
Assistant Professor
NUS
Yizhe Zhang
Research Scientist
Meta
Pavlo Molchanov
Research Director
NVIDIA Research