activity
20242026
most citedGenerative Modeling Enables Molecular Structure Retrieval from Coulomb Explosion Imaging

3 citations · 3 across the 32 of their papers we have counts for

collaborators
Showing cs.LGShow all

46 papers · 1 filter

cs.LG2026

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…

cs.LG2026

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…

cs.LG2026

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…

cs.LG2026

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…

cs.LG2026

One-Step Generative Modeling via Wasserstein Gradient Flows

Jiaqi Han, Puheng Li, Qiushan Guo +3

Diffusion models and flow-based methods have shown impressive generative capability, especially for images, but their sampling is expensive because it requires many iterative updat…

cs.LG2026

A Unified View of Score-Based and Drifting Models

Chieh-Hsin Lai, Bac Nguyen, Naoki Murata +5

Drifting models train one-step generators by optimizing a kernel-induced mean-shift discrepancy between the data and model distributions, with Laplace kernels used by default in pr…