68 papers
Constrained Decoding for Diffusion Language Models via Efficient Inference over Finite Automata
Meihua Dang, Stefano Ermon
Constrained decoding is essential for serving LLMs, ensuring that generated outputs follow specific structures such as JSON schema-formatted function calls. Existing systems are de…
Diffusion Language Model Parallel Decoding via Product-of-Experts Bridge
Juntong Shi, Brian L. Trippe, Jure Leskovec +2
Diffusion language models (DLMs) offer substantial speed advantages through parallel decoding, but the lack of token dependencies limits generation quality compared to autoregressi…
Mitigating Bias in Locally Constrained Decoding via Tractable Proposals
Meihua Dang, Linxin Song, Honghua Zhang +3
Generations from large language models often fail to conform to desired constraints such as JSON schema. Existing locally constrained decoding (LCD) approaches enforce constraints…
GUDA: Counterfactual Group-wise Training Data Attribution for Diffusion Models via Unlearning
Naoki Murata, Yuhta Takida, Chieh-Hsin Lai +4
Training-data attribution for vision generative models aims to identify which training data influenced a given output. While most methods score individual examples, practitioners o…
The Principles of Diffusion Models
Chieh-Hsin Lai, Yang Song, Dongjun Kim +2
This book presents the core principles that have guided the development of diffusion models, tracing their origins and showing how diverse formulations arise from shared mathematic…
Beyond Pairwise Preferences: Listwise Reward-Aware Alignment for Diffusion Models
Austin Wang, Jiaqi Han, Stefano Ermon +1
Preference optimization has emerged as an efficient alternative to online reinforcement learning from human feedback (RLHF) for aligning text-to-image diffusion models. However, ex…