activity
20242026
collaborators

9 papers

cs.LG2026

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…

cs.CV2026

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…

cs.LG2026

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…

cs.LG2026

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…

cs.LG2026

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…

cs.LG2026

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…