Skip to content
Sagan

Paper

TMPO: Trajectory Matching Policy Optimization for Diverse and Efficient Diffusion Alignment

Unreadunread

AI summary

The authors propose TMPO (Trajectory Matching Policy Optimization) to align diffusion models using reinforcement learning without suffering from reward hacking — the problem where models collapse onto a few high-reward outputs and lose diversity. Instead of maximizing expected reward (which is "mode-seeking"), TMPO matches the model's probability distribution over entire generation trajectories to a reward-induced Boltzmann distribution. This "mode-covering" approach preserves diversity over all acceptable outputs while still optimizing reward. They also introduce a tree-sampling trick to share computation across multiple trajectories during training, speeding up large flow-matching models.

Main takeaways:

  • Standard RL fine-tuning of diffusion models is mode-seeking: it concentrates probability on a few high-reward paths, causing visual mode collapse and reward hacking.
  • TMPO uses trajectory-level distribution matching (Softmax Trajectory Balance objective) to cover all acceptable trajectories, not just maximize reward.
  • Improves generative diversity by 9.1% over state-of-the-art methods while maintaining competitive reward and efficiency.
  • Dynamic Stochastic Tree Sampling shares denoising prefixes across K trajectories, reducing redundant computation during multi-trajectory training.
  • Effective across human preference alignment, compositional generation, and text rendering tasks.