10 papers
Gaussian Process Bandits for AI System Optimization with Selectively Verified Feedback
Shuang Wu
Gaussian process bandits exploit similarities among configurations to optimize prompts, retrieval systems, and agent workflows. In these applications, however, inexpensive model-ba…
Improving Sample Diversity in Autoregressive Text-to-Image Generation via Cluster Truncation
Trang Nguyen, Shuang Wu, Runyan Tan +1
While diffusion models achieve state-of-the-art image quality for text-to-image (T2I) generation, recent work has demonstrated that they suffer from sample diversity collapse. In t…
Safe Multitask Molecular Graph Networks for Vapor Pressure and Odor Threshold Prediction
Shuang Wu, Meijie Wang, Lun Yu
We investigate two important tasks in odor-related property modeling: Vapor Pressure (VP) and Odor Threshold (OP). To evaluate the model's out-of-distribution (OOD) capability, we…
Dream-VL & Dream-VLA: Open Vision-Language and Vision-Language-Action Models with Diffusion Language Model Backbone
Jiacheng Ye, Shansan Gong, Jiahui Gao +6
While autoregressive Large Vision-Language Models (VLMs) have achieved remarkable success, their sequential generation often limits their efficacy in complex visual planning and dy…
Laplacian Kernelized Bandit
Shuang Wu, Arash A. Amini
We study multi-user contextual bandits where users are related by a graph and their reward functions exhibit both non-linear behavior and graph homophily. We introduce a principled…
p-less Sampling: A Robust Hyperparameter-Free Approach for LLM Decoding
Runyan Tan, Shuang Wu, Phillip Howard
Obtaining high-quality outputs from Large Language Models (LLMs) often depends upon the choice of a sampling-based decoding strategy to probabilistically choose the next token at e…
Policy Optimization Algorithms in a Unified Framework
Shuang Wu
Policy optimization algorithms are crucial in many fields but challenging to grasp and implement, often due to complex calculations related to Markov decision processes and varying…
Action-Attentive Deep Reinforcement Learning for Autonomous Alignment of Beamlines
Siyu Wang, Shengran Dai, Jianhui Jiang +3
Synchrotron radiation sources play a crucial role in fields such as materials science, biology, and chemistry. The beamline, a key subsystem of the synchrotron, modulates and direc…
MARS: Unleashing the Power of Variance Reduction for Training Large Models
Huizhuo Yuan, Yifeng Liu, Shuang Wu +2
Training deep neural networks--and more recently, large models demands efficient and scalable optimizers. Adaptive gradient algorithms like Adam, AdamW, and their variants have bee…
Graph Neural Thompson Sampling
Shuang Wu, Arash A. Amini
We consider an online decision-making problem with a reward function defined over graph-structured data. We formally formulate the problem as an instance of graph action bandit. We…