9 papers
LiFT: Lifted Inter-slice Feature Trajectories for 3D Image Generation from 2D Generators
Xinhe Zhang, Yuyang Zhang, Pengfei Jin +3
High-resolution 3D medical image generation remains challenging because fully volumetric models are computationally expensive, while efficient 2D slice generators often fail to pre…
Provably Efficient Sensor Allocation for Unknown High-dimensional Systems with Limited Sensing
Yuyang Zhang, Derya Cansever, Na Li
This paper focuses on learning efficient sensor allocations that ensure observability of unknown high-dimensional linear systems using only a small number of sensors. Existing meth…
Decentralized Diffusion Policy Learning for Enhanced Exploration in Cooperative Multi-agent Reinforcement Learning
Yuyang Zhang, Haldun Balim, Na Li
Cooperative multi-agent reinforcement learning (MARL) involves complex agent interactions and requires effective exploration strategies. A prominent class of MARL algorithms, decen…
Max-Entropy Reinforcement Learning with Flow Matching and A Case Study on LQR
Yuyang Zhang, Yang Hu, Bo Dai +1
Soft actor-critic (SAC) is a popular algorithm for max-entropy reinforcement learning. In practice, the energy-based policies in SAC are often approximated using simple policy clas…
Human-AI Co-Embodied Intelligence for Scientific Experimentation and Manufacturing
Xinyi Lin, Yuyang Zhang, Yuanhang Gan +10
Scientific experimentation and manufacturing rely on prolonged protocol development and complex, multi-step implementation, which require continuous human expertise for precise exe…
A Model-Based Approach to Imitation Learning through Multi-Step Predictions
Haldun Balim, Yang Hu, Yuyang Zhang +1
Imitation learning is a widely used approach for training agents to replicate expert behavior in complex decision-making tasks. However, existing methods often struggle with compou…
Error-In-Variables Methods for Efficient System Identification with Finite-Sample Guarantees
Yuyang Zhang, Xinhe Zhang, Jia Liu +1
This paper addresses the problem of learning linear dynamical systems from noisy observations. In this setting, existing algorithms either yield biased parameter estimates or have…
Enhancing Preference-based Linear Bandits via Human Response Time
Shen Li, Yuyang Zhang, Zhaolin Ren +3
Interactive preference learning systems infer human preferences by presenting queries as pairs of options and collecting binary choices. Although binary choices are simple and wide…
Learning Low-dimensional Latent Dynamics from High-dimensional Observations: Non-asymptotics and Lower Bounds
Yuyang Zhang, Shahriar Talebi, Na Li
In this paper, we focus on learning a linear time-invariant (LTI) model with low-dimensional latent variables but high-dimensional observations. We provide an algorithm that recove…