Search for: All records

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 pretrained 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 controls 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. 

Secure memory systems employing AES-CTR encryption face signi! cant performance challenges due to high counter (CTR) cache miss rates, especially in applications with irregular memory access patterns. These high miss rates increase memory tra"c and latency, as each CTR cache miss triggers additional DRAM accesses. To address these bottlenecks and adapt to diverse access patterns, we propose COSMOS (Counter Optimized Secure Memory Operation Scheme), a novel solution leveraging reinforcement learning to reduce long memory access latency. COSMOS integrates two RL-based specialized predictors: one for data location prediction and another for CTR locality prediction, each with a well-de!ned state space, action space, and reward function. The RL-based data location predictor determines whether data reside on-chip or o#- chip after an L1 cache miss, enabling early CTR access for o#-chip predictions with minimal changes to the existing cache hierarchy. The RL-based CTR locality predictor identi!es CTRs with high locality, supporting a locality-centric CTR cache (LCR-CTR) to improve cache e"ciency and reduce miss rates. COSMOS improves performance over MorphCtr by 25% in for irregular memory access applications, with minimal hardware overhead.