There have been many attempts to leverage multiple diffusion models for collaborative generation, extending beyond the original domain. A prominent approach involves synchronizing multiple diffusion trajectories by mixing the estimated scores to artificially correlate the generation processes. However, existing methods rely on naive heuristics, such as averaging, without considering task specificity. These approaches do not clarify why such methods work and often fail when a heuristic suitable for one task is blindly applied to others. In this paper, we present a probabilistic framework for analyzing why diffusion synchronization works and reveal where heuristics should be focused—modeling correlations between multiple trajectories and adapting them to each specific task. We further identify optimal correlation models per task, achieving better results than previous approaches that apply a single heuristic across all tasks without justification.

Storage class memory (SCM) has been proposed as a solution to bridge the performance gap between main memory and storage in data-intensive applications. To overcome the limitations of prior technologies like 3D cross-point memory (3DXP), Selector-Only Memory (SOM) has recently emerged as a promising candidate for next-generation SCM. However, SOM devices face various reliability challenges that limit their ability to function as ideal memory devices. Among various non-ideal characteristics, threshold voltage (Vth) drift, which increases Vthover time, has been identified as a critical issue that raises the error rate of SOM. Moreover, device variation caused by immature manufacturing processes results in Vthdiscrepancies across devices, reducing the read window margin (RWM) and thus contributing to an increased error rate. In response to these issues, we propose Securer, consisting of self-error detection and correction techniques that inherently detect and correct errors for SOM, without relying on external methods such as error correction codes (ECC). The first technique effectively identifies all errors through a dual-polarity read operation, leveraging the unique features of SOM. For the second technique, an analytical drift estimation model is introduced to estimate the magnitude of Vthdrift experienced by erroneous cells. Using this information, an adaptive error-aware read operation, which tracks the drifted Vth, is employed to correct the detected errors. Experimental results across real workloads from various applications demonstrate that Securer achieves error rates below 10−13without significant overhead, and confirm error-free data integrity in conjunction with single-error correction code.

Time-to-event analysis, also known as survival analysis, aims to predict the time of occurrence of an event, given a set of features. One of the major challenges in this area is dealing with censored data, which can make learning algorithms more complex. Traditional methods such as Cox’s proportional hazards model and the accelerated failure time (AFT) model have been popular in this field, but they often require assumptions such as proportional hazards and linearity. In particular, the AFT models often require pre-specified parametric distributional assumptions. To improve predictive performance and alleviate strict assumptions, there have been many deep learning approaches for hazard-based models in recent years. However, representation learning for AFT has not been widely explored in the neural network literature, despite its simplicity and interpretability in comparison to hazard-focused methods. In this work, we introduce the Deep AFT Rank-regression model for Time-to-event prediction (DART). This model uses an objective function based on Gehan’s rank statistic, which is efficient and reliable for representation learning. On top of eliminating the requirement to establish a baseline event time distribution, DART retains the advantages of directly predicting event time in standard AFT models. The proposed method is a semiparametric approach to AFT modeling that does not impose any distributional assumptions on the survival time distribution. This also eliminates the need for additional hyperparameters or complex model architectures, unlike existing neural network-based AFT models. Through quantitative analysis on various benchmark datasets, we have shown that DART has significant potential for modeling high-throughput censored time-to-event data.

Modern web applications are getting more sophisticated by using frameworks that make development easy, but pose challenges for security analysis tools. New analysis techniques are needed to handle such frameworks that grow in number and popularity. In this paper, we describe Gelato that addresses the most crucial challenges for a security-aware client-side analysis of highly dynamic web applications. In particular, we use a feedback-driven and state-aware crawler that is able to analyze complex framework-based applications automatically, and is guided to maximize coverage of security-sensitive parts of the program. Moreover, we propose a new lightweight client-side taint analysis that outperforms the state-of-the-art tools, requires no modification to browsers, and reports non-trivial taint flows on modern JavaScript applications. Gelato reports vulnerabilities with higher accuracy than existing tools and achieves significantly better coverage on 12 applications of which three are used in production.

Nowadays, industrial research labs operate like startups. In a relatively short amount of time, researchers are expected not only to explore innovative ideas but also show how the new ideas can add value to the organisation. One way to do this, especially when developing tools, is to construct usable prototypes. When the technology underlying the research tool is highly complex or niche, like program analysis, field trials with potential users also help explaining and demonstrating the benefits of the tool. Getting support from potential users helps demonstrate value to the organisation, which in turn justifies conducting more extensive research and investing more resources to enhance the initial prototype.

We present a novel method for decomposing an image into base and texture layers. Our method is simple and effective, and can handle textures of high contrast, which traditional image filtering techniques may not handle efficiently. The method first removes high-frequency texture information using low-pass filtering, and then restores structural information of the image using a deconvolution operation. Experimental results demonstrate the effectiveness of our method.

We propose a novel technique for extracting a series of displaced subdivision surfaces sharing the same topology and the same displacement map from a given animated mesh. Our motion-based mesh simplification method creates control meshes with a small number of vertices but keeps the motion information. Extracted control meshes are simpler than the original meshes, and so easier to edit and take less storage. Our method uses only one displacement map for all frames, which greatly reduces the amount of data.