Know Your Step: Faster and Better Alignment for Flow Matching Models via Step-aware Advantages

Recent advances in flow matching models, particularly with reinforcement learning (RL), have significantly enhanced human preference alignment in few step text to image generators. However, existing RL based approaches for flow matching models typically rely on numerous denoising steps, while suffering from sparse and imprecise reward signals that often lead to suboptimal alignment. To address these limitations, we propose Temperature Annealed Few step Sampling with Group Relative Policy Optimization (TAFS GRPO), a novel framework for training flow matching text to image models into efficient few step generators well aligned with human preferences. Our method iteratively injects adaptive temporal noise onto the results of one step samples. By repeatedly annealing the model's sampled outputs, it introduces stochasticity into the sampling process while preserving the semantic integrity of each generated image. Moreover, its step aware advantage integration mechanism combines the GRPO to avoid the need for the differentiable of reward function and provide dense and step specific rewards for stable policy optimization. Extensive experiments demonstrate that TAFS GRPO achieves strong performance in few step text to image generation and significantly improves the alignment of generated images with human preferences. The code and models of this work will be available to facilitate further research.

Near-Optimal Experimental Design Under the Budget Constraint in Online Platforms

A/B testing, or controlled experiments, is the gold standard approach to causally compare the performance of algorithms on online platforms. However, conventional Bernoulli randomization in A/B testing faces many challenges such as spillover and carryover effects. Our study focuses on another challenge, especially for A/B testing on two-sided platforms -- budget constraints. Buyers on two-sided platforms often have limited budgets, where the conventional A/B testing may be infeasible to be applied, partly because two variants of allocation algorithms may conflict and lead some buyers to exceed their budgets if they are implemented simultaneously. We develop a model to describe two-sided platforms where buyers have limited budgets. We then provide an optimal experimental design that guarantees small bias and minimum variance. Bias is lower when there is more budget and a higher supply-demand rate. We test our experimental design on both synthetic data and real-world data, which verifies the theoretical results and shows our advantage compared to Bernoulli randomization.

No-regret Learning in Repeated First-Price Auctions with Budget Constraints

Recently the online advertising market has exhibited a gradual shift from second-price auctions to first-price auctions. Although there has been a line of works concerning online bidding strategies in first-price auctions, it still remains open how to handle budget constraints in the problem. In the present paper, we initiate the study for a buyer with budgets to learn online bidding strategies in repeated first-price auctions. We propose an RL-based bidding algorithm against the optimal non-anticipating strategy under stationary competition. Our algorithm obtains $\widetilde O(\sqrt T)$-regret if the bids are all revealed at the end of each round. With the restriction that the buyer only sees the winning bid after each round, our modified algorithm obtains $\widetilde O(T^{\frac{7}{12}})$-regret by techniques developed from survival analysis. Our analysis extends to the more general scenario where the buyer has any bounded instantaneous utility function with regrets of the same order.

An analysis of a random algorithm for estimating all the matchings

Counting the number of all the matchings on a bipartite graph has been transformed into calculating the permanent of a matrix obtained from the extended bipartite graph by Yan Huo, and Rasmussen presents a simple approach (RM) to approximate the permanent, which just yields a critical ratio O($n\omega(n)$) for almost all the 0-1 matrices, provided it's a simple promising practical way to compute this #P-complete problem. In this paper, the performance of this method will be shown when it's applied to compute all the matchings based on that transformation. The critical ratio will be proved to be very large with a certain probability, owning an increasing factor larger than any polynomial of $n$ even in the sense for almost all the 0-1 matrices. Hence, RM fails to work well when counting all the matchings via computing the permanent of the matrix. In other words, we must carefully utilize the known methods of estimating the permanent to count all the matchings through that transformation.