10 papers
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…
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…
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,…
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…
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…
BlinDNO: A Distributional Neural Operator for Dynamical System Reconstruction from Time-Label-Free data
Zhijun Zeng, Junqing Chen, Zuoqiang Shi
We study an inverse problem for stochastic and quantum dynamical systems in a time-label-free setting, where only unordered density snapshots sampled at unknown times drawn from an…