Annus Shabbir
All work
AI / ML research · 2026

Inference-Time Reward Alignment for Diffusion & Flow Matching

Research on sparse vs. dense inference-time reward alignment; proposed ODE-DITA — improved PickScore by +0.46 with best-of-K selection.

  • PyTorch
  • Diffusion Models
  • Flow Matching
  • VLMs
  • SMC
+0.46PickScore (sparse best-of-K)

The problem

Align diffusion / flow-matching generations to a reward at inference time without reward hacking or credit-assignment failure.

My role

Researcher (MS project).

What I built

Studied sparse vs. dense inference-time alignment and proposed ODE-Dense Inference-Time Alignment (ODE-DITA): deterministic n-step probability-flow ODE rollouts, Sequential Monte Carlo resampling, dense gain weighting, and a VLM semantic corrector in a hybrid variant.

Architecture & stack

  • Deterministic n-step probability-flow ODE rollouts
  • Sequential Monte Carlo resampling + dense gain weighting
  • VLM semantic corrector (hybrid variant)
  • Evaluated across 50 prompts × 3 seeds

Have a similar project in mind?

Start a conversation