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,…
Clifford Kolmogorov-Arnold Networks
Matthias Wolff, Francesco Alesiani, Christof Duhme +1
We introduce Clifford Kolmogorov-Arnold Network (ClKAN), a flexible and efficient architecture for function approximation in arbitrary Clifford Algebra spaces. We propose the use o…
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…
Covariance-Aware Goodness for Scalable Forward-Forward Learning
Xiaoyi Jiang, Bashir M. Al-Hashimi, Kai Xu
The Forward-Forward algorithm eliminates global gradient flow and full network activations storage. However, in convolutional settings, existing BP-free FF methods significantly un…