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

Authors: Jiaming Li, Chenyu Zhu, Zhiyuan Ma et al.

arXiv · PDF

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.

Relevance

Loosely related to my installation-path equivalence work — both are about aligning models (their diffusion models via RL, my LLMs via fine-tuning/prompting/steering), and their mode-seeking vs. mode-covering distinction might map onto whether behavioral installation concentrates on a narrow behavior vs. preserves flexibility, though the technical domains are very different.

Abstract

arXiv:2605.10983v1 Announce Type: new Abstract: Reinforcement learning (RL) has shown extraordinary potential in aligning diffusion models to downstream tasks, yet most of them still suffer from significant reward hacking, which degrades generative diversity and quality by inducing visual mode collapse and amplifying unreliable rewards. We identify the root cause as the mode-seeking nature of these methods, which maximize expected reward without effectively constraining probability distribution over acceptable trajectories, causing concentration on a few high-reward paths. In contrast, we propose Trajectory Matching Policy Optimization (TMPO), which replaces scalar reward maximization with trajectory-level reward distribution matching. Specifically, TMPO introduces a Softmax Trajectory Balance (Softmax-TB) objective to match the policy probabilities of K trajectories to a reward-induced Boltzmann distribution. We prove that this objective inherits the mode-covering property of forward KL divergence, preserving coverage over all acceptable trajectories while optimizing reward. To further reduce multi-trajectory training time on large-scale flow-matching models, TMPO incorporates Dynamic Stochastic Tree Sampling, where trajectories share denoising prefixes and branch at dynamically scheduled steps, reducing redundant computation while improving training effectiveness. Extensive results across diverse alignment tasks such as human preference, compositional generation and text rendering show that TMPO improves generative diversity over state-of-the-art methods by 9.1%, and achieves competitive performance in all downstream and efficiency metrics, attaining the optimal trade-off between reward and diversity.