9 papers
Bastion: Budget-Aware Speculative Decoding with Tree-structured Block Diffusion Drafting
Soowon Oh, Nam Cao, Yujin Kim +4
Block-diffusion drafters have recently emerged as a powerful alternative for speculative decoding by predicting multiple future-token distributions in a single parallel step. Howev…
Multi-Drafter Speculative Decoding with Alignment Feedback
Taehyeon Kim, Hojung Jung, Se-Young Yun
Speculative decoding (SD) accelerates large language model (LLM) inference by using a smaller model to draft future tokens, which are then verified by the target LLM. This preserve…
UniSAFE: A Comprehensive Benchmark for Safety Evaluation of Unified Multimodal Models
Segyu Lee, Boryeong Cho, Hojung Jung +8
Unified Multimodal Models (UMMs) offer powerful cross-modality capabilities but introduce new safety risks not observed in single-task models. Despite their emergence, existing saf…
KLASS: KL-Guided Fast Inference in Masked Diffusion Models
Seo Hyun Kim, Sunwoo Hong, Hojung Jung +2
Masked diffusion models have demonstrated competitive results on various tasks including language generation. However, due to its iterative refinement process, the inference is oft…
MolHIT: Advancing Molecular-Graph Generation with Hierarchical Discrete Diffusion Models
Hojung Jung, Rodrigo Hormazabal, Jaehyeong Jo +5
Molecular generation with diffusion models has emerged as a promising direction for AI-driven drug discovery and materials science. While graph diffusion models have been widely ad…
Temporal Alignment Guidance: On-Manifold Sampling in Diffusion Models
Youngrok Park, Hojung Jung, Sangmin Bae +1
Diffusion models have achieved remarkable success as generative models. However, even a well-trained model can accumulate errors throughout the generation process. These errors bec…