Author name cluster

Xu Cai

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

8 papers

2 author rows

AIIM Journal 2026 Journal Article

Development and validation of deep continual learning model to sequentially learn multiple clinical prediction tasks for ICU patients

Zhixuan Zeng
Yang Liu
Shuo Yao
Xu Cai
Wenbin Nan
Yiyang Xie
Xun Gong

Background ICU patients often suffer from critical and complex condition, and multiple potential risks should be monitored to provide them comprehensive care. However, no study proposes continual learning (CL) model that can effectively solve multiple clinical prediction tasks without catastrophic forgetting. This study proposes three deep CL models for ICU patients. Methods Three public ICU databases were employed. The included patients from MIMIC-III and MIMIC-IV were divided into eight task sets, and the patients from eICU-CRD composed the test set. We propose three CL models (CL_1, CL_2, CL_3) to sequentially learn eight prediction tasks on the eight task sets, and then externally validate them on the test set. We compare our models to three representative baseline CL models and the single-task (ST) and multi-task (MT) model. We train all the CL models under different orders, and evaluate their prediction performance by multiple metrics and their memory ability by backward transfer (BWT). We also analyzed the effect of previously learned tasks on learning new tasks. Results Our three CL models had comparable or slightly weaker performance compared to ST and MT model on the eight tasks. They effectively mitigated catastrophic forgetting, and their performance is robust to different training orders. CL_2 and CL_3 even have improved performance on the current task after learning some previous tasks. Our three CL models outperformed the baseline CL models in most experiments. Conclusions Our CL models are promising to sequentially learn multiple clinical prediction tasks for ICU patients. The CL_2 and CL_3 show the ability of utilizing information of previous tasks to improve learning new tasks. More new datasets and tasks are still needed to further verify the validity of the CL models.

Details DOI

ICML Conference 2025 Conference Paper

FlexControl: Computation-Aware Conditional Control with Differentiable Router for Text-to-Image Generation

Zheng Fang
Lichuan Xiang
Xu Cai
Kaicheng Zhou
Hongkai Wen 0001

Spatial conditioning control offers a powerful way to guide diffusion-based generative models. Yet, most implementations (e. g. , ControlNet) rely on ad-hoc heuristics to choose which network blocks to control — an approach that varies unpredictably with different tasks. To address this gap, we propose FlexControl, a novel framework that equips all diffusion blocks with control signals during training and employs a trainable gating mechanism to dynamically select which control signal to activate at each denoising step. By introducing a computation-aware loss, we can encourage the control signal to activate only when it benefits the generation quality. By eliminating manual control unit selection, FlexControl enhances adaptability across diverse tasks and streamlines the design pipeline with computation-aware training loss in an end-to-end training manner. Through comprehensive experiments on both UNet and DiT architectures on different control methods, we show that our method can upgrade existing controllable generative models in certain key aspects of interest. As evidenced by both quantitative and qualitative evaluations, FlexControl preserves or enhances image fidelity while also reducing computational overhead by selectively activating the most relevant blocks to control. These results underscore the potential of a flexible, data-driven approach for controlled diffusion and open new avenues for efficient generative model design. The code will soon be available at https: //github. com/Daryu-Fan/FlexControl.

Details

NeurIPS Conference 2025 Conference Paper

Shortcutting Pre-trained Flow Matching Diffusion Models is Almost Free Lunch

Xu Cai
Yang Wu
Qianli Chen
Haoran Wu
Lichuan Xiang
Hongkai Wen

We present an ultra-efficient post-training method for shortcutting large-scale pre-trained flow matching diffusion models into efficient few-step samplers, enabled by novel velocity field self-distillation. While shortcutting in flow matching, originally introduced by shortcut models, offers flexible trajectory-skipping capabilities, it requires a specialized step-size embedding incompatible with existing models unless retraining from scratch—a process nearly as costly as pretraining itself. Our key contribution is thus imparting a more aggressive shortcut mechanism to standard flow matching models (e. g. , Flux), leveraging a unique distillation principle that obviates the need for step-size embedding. Working on the velocity field rather than sample space and learning rapidly from self-guided distillation in an online manner, our approach trains efficiently, e. g. , producing a 3-step Flux <1 A100 day. Beyond distillation, our method can be incorporated into the pretraining stage itself, yielding models that inherently learn efficient, few-step flows without compromising quality. This capability also enables, to our knowledge, the first few-shot distillation method (e. g. , 10 text-image pairs) for dozen-billion-parameter diffusion models, delivering state-of-the-art performance at almost free cost.

PDF Details

AAAI Conference 2024 Conference Paper

Kernelized Normalizing Constant Estimation: Bridging Bayesian Quadrature and Bayesian Optimization

Xu Cai
Jonathan Scarlett

In this paper, we study the problem of estimating the normalizing constant through queries to the black-box function f, which is the integration of the exponential function of f scaled by a problem parameter lambda. We assume f belongs to a reproducing kernel Hilbert space (RKHS), and show that to estimate the normalizing constant within a small relative error, the level of difficulty depends on the value of lambda: When lambda approaches zero, the problem is similar to Bayesian quadrature (BQ), while when lambda approaches infinity, the problem is similar to Bayesian optimization (BO). More generally, the problem varies between BQ and BO. We find that this pattern holds true even when the function evaluations are noisy, bringing new aspects to this topic. Our findings are supported by both algorithm-independent lower bounds and algorithmic upper bounds, as well as simulation studies conducted on a variety of benchmark functions.

PDF Details DOI

TMLR Journal 2023 Journal Article

On Average-Case Error Bounds for Kernel-Based Bayesian Quadrature

Xu Cai
Thanh Lam
Jonathan Scarlett

In this paper, we study error bounds for Bayesian quadrature (BQ), with an emphasis on noisy settings, randomized algorithms, and average-case performance measures. We seek to approximate the integral of functions in a Reproducing Kernel Hilbert Space (RKHS), particularly focusing on the Mat\'ern-$\nu$ and squared exponential (SE) kernels, with samples from the function potentially being corrupted by Gaussian noise. We provide a two-step meta-algorithm that serves as a general tool for relating the average-case quadrature error with the $L^2$-function approximation error. When specialized to the Mat\'ern kernel, we recover an existing near-optimal error rate while avoiding the existing method of repeatedly sampling points. When specialized to other settings, we obtain new average-case results for settings including the SE kernel with noise and the Mat\'ern kernel with misspecification. Finally, we present algorithm-independent lower bounds that have greater generality and/or give distinct proofs compared to existing ones.

PDF Details

ICML Conference 2021 Conference Paper

Lenient Regret and Good-Action Identification in Gaussian Process Bandits

Xu Cai
Selwyn Gomes
Jonathan Scarlett

In this paper, we study the problem of Gaussian process (GP) bandits under relaxed optimization criteria stating that any function value above a certain threshold is “good enough”. On the theoretical side, we study various {\em lenient regret} notions in which all near-optimal actions incur zero penalty, and provide upper bounds on the lenient regret for GP-UCB and an elimination algorithm, circumventing the usual $O(\sqrt{T})$ term (with time horizon $T$) resulting from zooming extremely close towards the function maximum. In addition, we complement these upper bounds with algorithm-independent lower bounds. On the practical side, we consider the problem of finding a single “good action” according to a known pre-specified threshold, and introduce several good-action identification algorithms that exploit knowledge of the threshold. We experimentally find that such algorithms can typically find a good action faster than standard optimization-based approaches.

Details

ICML Conference 2021 Conference Paper

On Lower Bounds for Standard and Robust Gaussian Process Bandit Optimization

Xu Cai
Jonathan Scarlett

In this paper, we consider algorithm independent lower bounds for the problem of black-box optimization of functions having a bounded norm is some Reproducing Kernel Hilbert Space (RKHS), which can be viewed as a non-Bayesian Gaussian process bandit problem. In the standard noisy setting, we provide a novel proof technique for deriving lower bounds on the regret, with benefits including simplicity, versatility, and an improved dependence on the error probability. In a robust setting in which the final point is perturbed by an adversary, we strengthen an existing lower bound that only holds for target success probabilities very close to one, by allowing for arbitrary target success probabilities in (0, 1). Furthermore, in a distinct robust setting in which every sampled point may be perturbed by a constrained adversary, we provide a novel lower bound for deterministic strategies, demonstrating an inevitable joint dependence of the cumulative regret on the corruption level and the time horizon, in contrast with existing lower bounds that only characterize the individual dependencies.

Details

AAAI Conference 2019 Conference Paper

FRAME Revisited: An Interpretation View Based on Particle Evolution

Xu Cai
Yang Wu
Guanbin Li
Ziliang Chen
Liang Lin

FRAME (Filters, Random fields, And Maximum Entropy) is an energy-based descriptive model that synthesizes visual realism by capturing mutual patterns from structural input signals. The maximum likelihood estimation (MLE) is applied by default, yet conventionally causes the unstable training energy that wrecks the generated structures, which remains unexplained. In this paper, we provide a new theoretical insight to analyze FRAME, from a perspective of particle physics ascribing the weird phenomenon to KL-vanishing issue. In order to stabilize the energy dissipation, we propose an alternative Wasserstein distance in discrete time based on the conclusion that the Jordan-Kinderlehrer-Otto (JKO) discrete flow approximates KL discrete flow when the time step size tends to 0. Besides, this metric can still maintain the model’s statistical consistency. Quantitative and qualitative experiments have been respectively conducted on several widely used datasets. The empirical studies have evidenced the effectiveness and superiority of our method.

PDF Details