11 citations · 11 across the 11 of their papers we have counts for
6 papers · 1 filter
D-DOIT: Training-free Adaptation of Discrete Diffusion via Doob's h-Transform
Jieke Wu, Qijie Zhu, Weimin Wu +3
We propose D-DOIT (Discrete Doob-Oriented Inference-time Transformation), a training-free and efficient adaptation method for discrete diffusion models with generic rewards. D-DOIT…
Discrete Flow Matching Policy Optimization
Maojiang Su, Po-Chung Hsieh, Weimin Wu +4
We introduce Discrete flow Matching policy Optimization (DoMinO), a unified framework for Reinforcement Learning (RL) fine-tuning Discrete Flow Matching (DFM) models under a broad…
On Structured State-Space Duality
Jerry Yao-Chieh Hu, Xiwen Zhang, Ali ElSheikh +2
Structured State-Space Duality (SSD) [Dao & Gu, ICML 2024] is an equivalence between a simple Structured State-Space Model (SSM) and a masked attention mechanism. In particular, a…
POLO: Preference-Guided Multi-Turn Reinforcement Learning for Lead Optimization
Ziqing Wang, Yibo Wen, William Pattie +6
Lead optimization in drug discovery requires efficiently navigating vast chemical space through iterative cycles to enhance molecular properties while preserving structural similar…
Universal Approximation with Softmax Attention
Jerry Yao-Chieh Hu, Hude Liu, Hong-Yu Chen +2
We prove that with linear transformations, both (i) two-layer self-attention and (ii) one-layer self-attention followed by a softmax function are universal approximators for contin…
In-Context Deep Learning via Transformer Models
Weimin Wu, Maojiang Su, Jerry Yao-Chieh Hu +2
We investigate the transformer's capability to simulate the training process of deep models via in-context learning (ICL), i.e., in-context deep learning. Our key contribution is p…