Molei Tao

Jaemoo Choi, Yuchen Zhu, Wei Guo et al.

Reinforcement learning has been widely applied to diffusion and flow models for visual tasks such as text-to-image generation. However, these tasks remain challenging because diffusion models have intractable likelihoods, which creates a barrier for directly applying popular policy-gradient type methods. Existing approaches primarily focus on crafting new objectives built on already heavily engineered LLM objectives, using ad hoc estimators for likelihood, without a thorough investigation into how such estimation affects overall algorithmic performance. In this work, we provide a systematic analysis of the RL design space by disentangling three factors: i) policy-gradient objectives, ii) likelihood estimators, and iii) rollout sampling schemes. We show that adopting an evidence lower bound (ELBO) based model likelihood estimator, computed only from the final generated sample, is the dominant factor enabling effective, efficient, and stable RL optimization, outweighing the impact of the specific policy-gradient loss functional. We validate our findings across multiple reward benchmarks using SD 3.5 Medium, and observe consistent trends across all tasks. Our method improves the GenEval score from 0.24 to 0.95 in 90 GPU hours, which is $4.6\times$ more efficient than FlowGRPO and $2\times$ more efficient than the SOTA method DiffusionNFT without reward hacking.

Ye He, Yitong Qiu, Molei Tao

When a diffusion model is not memorizing the training data set, how does it generalize exactly? A quantitative understanding of the distribution it generates would be beneficial to, for example, an assessment of the model's performance for downstream applications. We thus explicitly characterize what diffusion model generates, by proposing a log-density ridge manifold and quantifying how the generated data relate to this manifold as inference dynamics progresses. More precisely, inference undergoes a reach-align-slide process centered around the ridge manifold: trajectories first reach a neighborhood of the manifold, then align as being pushed toward or away from the manifold in normal directions, and finally slide along the manifold in tangent directions. Within the scope of this general behavior, different training errors will lead to different normal and tangent motions, which can be quantified, and these detailed motions characterize when inter-mode generations emerge. More detailed understanding of training dynamics will lead to more accurate quantification of the generation inductive bias, and an example of random feature model will be considered, for which we can explicitly illustrate how diffusion model's inductive biases originate as a composition of architectural bias and training accuracy, and how they evolve with the inference dynamics. Experiments on synthetic multimodal distributions and MNIST latent diffusion support the predicted directional effects, in both low- and high-dimensions.