9 papers
Flow Matching with Missing Data
Fairoz Nower Khan, Nabuat Zaman Nahim, Peizhong Ju
Flow matching assumes fully observed training data, which many real-world applications rarely provide. We propose Missing-Data Flow Matching, which treats the missing coordinates o…
FoA-SR: Faithful or Aesthetic? Profile-Aware Preference Optimization for Real-World Image Super-Resolution
Amjad Mahdi Alqarni, Peizhong Ju
Real-world image super-resolution (SR) is often designed with a single restoration objective, despite the current capacity of generative models to produce multiple high-quality rec…
Flow Matching for Offline Reinforcement Learning with Discrete Actions
Fairoz Nower Khan, Nabuat Zaman Nahim, Ruiquan Huang +2
Generative policies based on diffusion models and flow matching have shown strong promise for offline reinforcement learning (RL), but their applicability remains largely confined…
Discrete MeanFlow: One-Step Generation via Conditional Transition Kernels
Fairoz Nower Khan, Nabuat Zaman Nahim, Md Sajid Ahmed +2
MeanFlow enables one-step generation in continuous spaces by learning an average velocity over a time interval rather than the instantaneous velocity field of flow matching. Howeve…
Discrete Flow Matching for Offline-to-Online Reinforcement Learning
Fairoz Nower Khan, Nabuat Zaman Nahim, Peizhong Ju
Many reinforcement learning (RL) tasks have discrete action spaces, but most generative policy methods based on diffusion and flow matching are designed for continuous control. Mea…
An LP-based Sampling Policy for Multi-Armed Bandits with Side-Observations and Stochastic Availability
Ashutosh Soni, Peizhong Ju, Atilla Eryilmaz +1
We study the stochastic multi-armed bandit (MAB) problem where an underlying network structure enables side-observations across related actions. We use a bipartite graph to link ac…