Achieving precise alignment between textual instructions and generated images in text-to-image generation is a significant challenge, particularly in rendering written text within images. Sate-of-the-art models like Stable Diffusion 3 (SD3), Flux, and AuraFlow still struggle with accurate text depiction, resulting in misspelled or inconsistent text. We introduce a training-free method with minimal computational overhead that significantly enhances text rendering quality. Specifically, we introduce an overshooting sampler for pre-trained rectified flow (RF) models, by alternating between over-simulating the learned ordinary differential equation (ODE) and reintroducing noise. Compared to the Euler sampler, the overshooting sampler effectively introduces an extra Langevin dynamics term that can help correct the compounding error from successive Euler steps and therefore improve the text rendering. However, when the overshooting strength is high, we observe over-smoothing artifacts on the generated images. To address this issue, we propose an Attention Modulated Overshooting sampler (AMO), which adaptively control the strength of overshooting for each image patch according to their attention score with the text content. AMO demonstrates a 32.3% and 35.9% improvement in text rendering accuracy on SD3 and Flux without compromising overall image quality or increasing inference cost.

Rectified Flow offers a simple and effective approach to high-quality generative modeling by learning a velocity field. However, we identify a limitation in directly modeling the velocity with an unconstrained neural network: the learned velocity often fails to satisfy certain boundary conditions, leading to inaccurate velocity field estimations that deviate from the desired ODE. This issue is particularly critical during stochastic sampling at inference, as the score function's errors are amplified near the boundary. To mitigate this, we propose a Boundary-enforced Rectified Flow Model (Boundary RF Model), in which we enforce boundary conditions with a minimal code modification. Boundary RF Model improves performance over vanilla RF model, demonstrating 8.01% improvement in FID score on ImageNet using ODE sampling and 8.98% improvement using SDE sampling.

Ruohong Zhang, Liangke Gui, Zhiqing Sun, Yihao Feng, Keyang Xu, Yuanhan Zhang, Di Fu, Chunyuan Li, Alexander G Hauptmann, Yonatan Bisk, Yiming Yang. Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers). 2025.

Keyang Xu, Tongzheng Ren, Shikun Zhang, Yihao Feng, Caiming Xiong. Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers). 2021.

Selective search architectures use resource selection algorithms such as Rank-S or Taily to rank index shards and determine how many to search for a given query. Most prior research evaluated solutions by their ability to improve efficiency without significantly reducing early-precision metrics such as [email protected] and [email protected] This paper recasts selective search as an early stage of a multi-stage retrieval architecture, which makes recall-oriented metrics more appropriate. A new algorithm is presented that predicts the number of shards that must be searched for a given query in order to meet recall-oriented goals. Decoupling shard ranking from deciding how many shards to search clarifies efficiency vs. effectiveness trade-offs, and enables them to be optimized independently. Experiments on two corpora demonstrate the value of this approach.

Many URLs on the Internet point to identical contents, which increase the burden of web crawlers. Techniques that detect such URLs (known as URL de-duping) can greatly save resources such as bandwidth and storage for crawlers. Traditional de-duping methods are usually limited to heavily engineered rule matching strategies.In this work, we propose a novel URL de-duping framework based on sequence-to-sequence (Seq2Seq) neural networks. A single concise translation model can take the place of thousands of explicit rules. Experiments indicate that a vanilla Seq2Seq architecture yields robust and accurate results in detecting duplicate URLs. Furthermore, we demonstrate the efficiency of this framework in the real large-scale web environment.