Yucheng Liu

Vinodh Kumar Sunkara, Satheeshkumar Karuppusamy, Hangjun Xu et al.

Traditional ads recommendation systems have primarily focused on optimizing for prediction accuracy of click or conversion events using canonical metrics such as recall or normalized discounted cumulative gain (NDCG). With the hyper-growth of ads inventory and liquidity with generative AI technologies, the prediction stability and predictability is becoming increasingly critical. Intuitively, prediction stability and predictability can be defined to quantify system robustness with respect to minor/noisy input (ads, creatives) perturbations, the lack of which could lead to advertiser perceivable problems such as repeatability, cold start and under-exploration. In this paper, we introduce a new evaluation framework for quantifying stability and predictability of an ads recommender system, and present an online validated semantic candidate generation framework powered by fine-tuned Large Language Models (LLMs) that showed significant improvement along these metrics by fundamentally improving the semantic-awareness of the system. The approach extracts hierarchical semantic attributes from ad creatives to obtain LLM representations, which serve as the foundation for graph-based expansion, ensuring the retrieved candidates encapsulate semantic variants of an ad, guaranteeing that small creative variants from the advertiser yield consistent and explainable delivery results to the user. We tested this LLM ads retrieval framework in a large-scale industrial ads recommendation system, demonstrating significant improvements across offline and online A/B experiments, showcasing gains in both predictability and traditional performance metrics. Although evaluated in the ads stack, this is a general framework that can be applied broadly to any large-scale recommendation and retrieval systems facing similar scaling and predictability challenges.

Muyang Li, Yucheng Liu, Jianbo Ma et al.

Vision-Language Models (VLMs) have enhanced traditional LLMs with visual capabilities through the integration of vision encoders. While recent works have explored various combinations of vision encoders and LLMs, there still lacks a principled understanding of what makes a vision encoder suitable for VLM alignment. In this paper, we systematically investigate this question via comprehensive experiments on a curated collection of 19 pre-trained vision encoders from diverse sources. We first demonstrate that common practices, such as choosing encoders with the largest size or highest zero-shot accuracy, consistently fail to identify optimal models. In fact, these metrics show only weak to moderate correlation with VLM performance. This intriguing finding begs a fundamental question: What factors of vision-encoders matter in VLM? Through comprehensive analysis, we identify that the structural similarity across modalities plays a crucial but previously overlooked role in vision-encoder selection, which we measure using the Gromov-Wasserstein distance as a proxy. From a theoretical perspective, we show that the learnability of cross-modality mapping can be provably associated with the Gromov-Wasserstein distance. Empirical verification on 60+ full VLM training runs shows that our proposed inference-only metric performs significantly better than alternative model selection strategies and exhibits a much stronger correlation with final VLM performance, thereby enabling efficient and effective prediction of VLM performance before full training.

Yucheng Liu, Tak Shing Au Yeung, Eric T. Chung et al.

Efficient simulation of Darcy flow in highly heterogeneous porous media requires iterative solvers that remain robust under large permeability contrasts and mixed boundary conditions. Spectral coarse spaces in two-level overlapping Schwarz methods provide such robustness, but their practical use is often limited by an expensive setup phase dominated by many local generalized eigenvalue solves. We propose a purely algebraic, coarse-space approximation that avoids these repeated local eigensolves by using a graph neural network operating on the system-matrix graph. On the analysis side, we introduce a coefficient-weighted subspace-distance measure to quantify the discrepancy between the approximated and target local multiscale coarse spaces, and we derive a condition-number bound for the resulting preconditioned operator in terms of this distance. This bound yields a principled supervised-training objective and links learning error to solver performance. Numerical experiments on 2D and 3D high-contrast Darcy systems with varying mixed boundary conditions demonstrate that the proposed approach substantially reduces setup cost and improves end-to-end time-to-solution, while preserving robust convergence across the tested contrasts and boundary configurations.

Yucheng Liu, Longyu Jiang

Signal separation in the passive underwater acoustic domain has heavily relied on deep learning techniques to isolate ship radiated noise. However, the separation networks commonly used in this domain stem from speech separation applications and may not fully consider the unique aspects of underwater acoustics beforehand, such as the influence of different propagation media, signal frequencies and modulation characteristics. This oversight highlights the need for tailored approaches that account for the specific characteristics of underwater sound propagation. This study introduces a novel temporal network designed to separate ship radiated noise by employing a dual-path model and a feature decoupling approach. The mixed signals' features are transformed into a space where they exhibit greater independence, with each dimension's significance decoupled. Subsequently, a fusion of local and global attention mechanisms is employed in the separation layer. Extensive comparisons showcase the effectiveness of this method when compared to other prevalent network models, as evidenced by its performance in the ShipsEar and DeepShip datasets.

Heqiang Wang, Xiang Liu, Yucheng Liu et al.

With the increasing number and enhanced capabilities of IoT devices in smart buildings, these devices are evolving beyond basic data collection and control to actively participate in deep learning tasks. Federated Learning (FL), as a decentralized learning paradigm, is well-suited for such scenarios. However, the limited computational and communication resources of IoT devices present significant challenges. While existing research has extensively explored efficiency improvements in Horizontal FL, these techniques cannot be directly applied to Vertical FL due to fundamental differences in data partitioning and model structure. To address this gap, we propose a Lightweight Vertical Federated Learning (LVFL) framework that jointly optimizes computational and communication efficiency. Our approach introduces two distinct lightweighting strategies: one for reducing the complexity of the feature model to improve local computation, and another for compressing feature embeddings to reduce communication overhead. Furthermore, we derive a convergence bound for the proposed LVFL algorithm that explicitly incorporates both computation and communication lightweighting ratios. Experimental results on an image classification task demonstrate that LVFL effectively mitigates resource demands while maintaining competitive learning performance.

Yucheng Liu, Tian Zhu

Relationship extraction and named entity recognition have always been considered as two distinct tasks that require different input data, labels, and models. However, both are essential for structured sentiment analysis. We believe that both tasks can be combined into a single stacked model with the same input data. We performed different experiments to find the best model to extract multiple opinion tuples from a single sentence. The opinion tuples will consist of holders, targets, and expressions. With the opinion tuples, we will be able to extract the relationship we need.

Yucheng Liu, Lawrence Ong, Sarah Johnson et al.

We study the information leakage to a guessing adversary in zero-error source coding. The source coding problem is defined by a confusion graph capturing the distinguishability between source symbols. The information leakage is measured by the ratio of the adversary's successful guessing probability after and before eavesdropping the codeword, maximized over all possible source distributions. Such measurement under the basic adversarial model where the adversary makes a single guess and allows no distortion between its estimator and the true sequence is known as the maximum min-entropy leakage or the maximal leakage in the literature. We develop a single-letter characterization of the optimal normalized leakage under the basic adversarial model, together with an optimum-achieving scalar stochastic mapping scheme. An interesting observation is that the optimal normalized leakage is equal to the optimal compression rate with fixed-length source codes, both of which can be simultaneously achieved by some deterministic coding schemes. We then extend the leakage measurement to generalized adversarial models where the adversary makes multiple guesses and allows certain level of distortion, for which we derive single-letter lower and upper bounds.

Yucheng Liu, Naji Khosravan, Yulin Liu et al.

Creating large scale high-quality annotations is a known challenge in medical imaging. In this work, based on the CycleGAN algorithm, we propose leveraging annotations from one modality to be useful in other modalities. More specifically, the proposed algorithm creates highly realistic synthetic CT images (SynCT) from prostate MR images using unpaired data sets. By using SynCT images (without segmentation labels) and MR images (with segmentation labels available), we have trained a deep segmentation network for precise delineation of prostate from real CT scans. For the generator in our CycleGAN, the cycle consistency term is used to guarantee that SynCT shares the identical manually-drawn, high-quality masks originally delineated on MR images. Further, we introduce a cost function based on structural similarity index (SSIM) to improve the anatomical similarity between real and synthetic images. For segmentation followed by the SynCT generation from CycleGAN, automatic delineation is achieved through a 2.5D Residual U-Net. Quantitative evaluation demonstrates comparable segmentation results between our SynCT and radiologist drawn masks for real CT images, solving an important problem in medical image segmentation field when ground truth annotations are not available for the modality of interest.