collaborators

9 papers

cs.LG2026

UNIFUSION: Adapting Autoregressive Language Models into Discrete Diffusion under a Unified Reverse-Rate Objective

Xiaoyi Jiang, Jingyuan Li, Yixuan Jiang +4

Existing methods mainly adapt pretrained autoregressive (AR) language models to masked diffusion, whereas we directly adapt them to uniform-noise diffusion, where every token remai…

cs.LG2026

Mean-to-Score Discrete Diffusion: Posterior-Mean Denoisers for Score Entropy

Jingyuan Li, Xiaoyi Jiang, Yixuan Jiang +4

Score Entropy Discrete Diffusion (SEDD) parameterizes discrete reverse processes with unconstrained positive score ratios. While positivity guarantees nonnegative reverse jump rate…

cs.LG2026

OLEDLM: A Unified Language Model for OLED Molecular Design

Fukang Wen, Yuchong Tang, Jingyuan Li +9

The development of organic light-emitting diode (OLED) materials faces the compounded challenges of an astronomically large chemical space, stringent quantum-chemical constraints,…

cs.AI2026

Constant-Target Energy Matching: A Unified Framework for Continuous and Discrete Density Estimation

Zhijun Zeng, Yixuan Jiang, Pipi Hu +1

Density estimation is a central primitive in probabilistic modeling, yet continuous, discrete, and mixed-variable domains are often treated by separate objectives, limiting the abi…

cs.LG2026

Neural Continuous-Time Markov Chain: Discrete Diffusion via Decoupled Jump Timing and Direction

Jingyuan Li, Xiaoyi Jiang, Fukang Wen +5

Discrete diffusion models based on continuous-time Markov chains (CTMCs) have shown strong performance on language and discrete data generation, yet existing approaches typically p…

physics.chem-ph2026

Drifting to Boltzmann: Million-Fold Acceleration in Boltzmann Sampling with Force-Guided Drifting

Pipi Hu

Sampling molecular conformations from the Boltzmann distribution is essential for computational chemistry, but iterative diffusion methods are prohibitively slow. Drifting Models o…