6 papers
What Makes a Good Unmasking Policy? A Controlled Study of Learned Unmasking in Diffusion Language Models
Jinya Sakurai, Xun Xu, Jaehong Yoon
Masked diffusion language models generate tokens in parallel, but their efficiency depends on which predictions are committed. Learned unmasking policies improve the speed--accurac…
Foreground Voice Activity Detection: Learning Speaker Selectivity from Supervision
Guangzhao Yang, Muhammad Huzaifah, Yu Pan +2
Voice activity detection (VAD) fronts most voice-agent pipelines, yet production detectors treat all human speech, background talkers included, as valid activity; in crowded settin…
Simplex Relaxation for Discrete Diffusion
Jinya Sakurai, Patrick Pynadath, Satoshi Hayakawa +4
Discrete diffusion models for categorical generation are defined by a corruption kernel, which determines the intermediate state space and the associated reverse prediction problem…
Test-Time Scaling for Safe Text-Guided Image Generation via Intermediate Clean Estimates
Jinya Sakurai, Shueicheng Yan, Xun Xu
Ensuring safety and policy compliance in text-to-image diffusion models remains a critical challenge, as benign or adversarial prompts can often elicit prohibited content, e.g. nud…
FairT2I: Mitigating Social Bias in Text-to-Image Generation via Large Language Model-Assisted Detection and Attribute Rebalancing
Jinya Sakurai, Yuki Koyama, Issei Sato
Text-to-image (T2I) models have advanced creative content generation, yet their reliance on large uncurated datasets often reproduces societal biases. We present FairT2I, a trainin…
Optimizing Implicit Neural Representations from Point Clouds via Energy-Based Models
Ryutaro Yamauchi, Jinya Sakurai, Ryo Furukawa +1
Reconstructing a continuous surface from an unoritented 3D point cloud is a fundamental task in 3D shape processing. In recent years, several methods have been proposed to address…