Poster · Sydney

DACA-GRPO: Denoising-Aware Credit Assignment for Reinforcement Learning in Diffusion Language Models

Name: DACA-GRPO: Denoising-Aware Credit Assignment for Reinforcement Learning in Diffusion Language Models
Start: 2026-12-08T17:00:00+11:00
End: 2026-12-08T20:00:00+11:00
Location: Hall 1-4, ICC Sydney

When: Tue 8 Dec 2026, 17:00–20:00 AEDT
Where: Hall 1-4, ICC Sydney
Exhibition Centre, Level 1
Session: Sydney Poster Session 2
Authors: Amin Karimi Monsefi, Dominic Culver, Nikhil Bhendawade, Lokesh Boominathan, Manuel R Ciosici, Yizhe Zhang, Irina Belousova
Organisations: Apple
QRS classification: Reinforcement learning, Language models, Generative models

Open in schedule Official page