34 citations · 69 across the 16 of their papers we have counts for
18 papers
Pointer-Augmented Autoregressive Generation of Patent Claims with Joint Topology and Content Decoding
Yongmin Yoo, Zhangkai Wu, Longbing Cao
Autoregressive decoders emit flat token sequences and cannot enforce hierarchical constraints across output segments, a limitation that becomes acute in patent claim generation, wh…
DUET: Unified Dual-Space Emotion Control for Diffusion and Flow-Matching Driven Text-to-Speech
Xu Zhang, Longbing Cao, Zhangkai Wu
Diffusion and flow-matching based text-to-speech (TTS) models excel in naturalness but often lack explicit emotion control, as emotional signals remain entangled with speaker ident…
Heterogeneous Dependency Graph-Guided Attentionfor Patent Representation Learning
Yongmin Yoo, Qiongkai Xu, Zhangkai Wu +1
Pre-trained language models advance patent classification and retrieval by encoding claims as flat token sequences, but they overlook the dependency hierarchy among claims. Incorpo…
Learning Physiology-Informed Vocal Spectrotemporal Representations for Speech Emotion Recognition
Xu Zhang, Longbing Cao, Runze Yang +1
Speech emotion recognition (SER) is essential for humanoid robot tasks such as social robotic interactions and robotic psychological diagnosis, where interpretable and efficient mo…
An Efficient Algorithm for Thresholding Monte Carlo Tree Search
Shoma Nameki, Atsuyoshi Nakamura, Junpei Komiyama +1
We introduce the Thresholding Monte Carlo Tree Search problem, in which, given a tree and a threshold , a player must answer whether the root node value of $\mathc…
Nested AutoRegressive Models
Hongyu Wu, Xuhui Fan, Zhangkai Wu +1
AutoRegressive (AR) models have demonstrated competitive performance in image generation, achieving results comparable to those of diffusion models. However, their token-by-token i…
VALA: Learning Latent Anchors for Training-Free and Temporally Consistent
Zhangkai Wu, Xuhui Fan, Zhongyuan Xie +2
Recent advances in training-free video editing have enabled lightweight and precise cross-frame generation by leveraging pre-trained text-to-image diffusion models. However, existi…
FAME: Fairness-aware Attention-modulated Video Editing
Zhangkai Wu, Xuhui Fan, Zhongyuan Xie +3
Training-free video editing (VE) models tend to fall back on gender stereotypes when rendering profession-related prompts. We propose \textbf{FAME} for \textit{Fairness-aware Atten…
FigBO: A Generalized Acquisition Function Framework with Look-Ahead Capability for Bayesian Optimization
Hui Chen, Xuhui Fan, Zhangkai Wu +1
Bayesian optimization is a powerful technique for optimizing expensive-to-evaluate black-box functions, consisting of two main components: a surrogate model and an acquisition func…
SCoT: Unifying Consistency Models and Rectified Flows via Straight-Consistent Trajectories
Zhangkai Wu, Xuhui Fan, Hongyu Wu +1
Pre-trained diffusion models are commonly used to generate clean data (e.g., images) from random noises, effectively forming pairs of noises and corresponding clean images. Distill…
A Survey on Pre-Trained Diffusion Model Distillations
Xuhui Fan, Zhangkai Wu, Hongyu Wu
Diffusion Models~(DMs) have emerged as the dominant approach in Generative Artificial Intelligence (GenAI), owing to their remarkable performance in tasks such as text-to-image syn…
ParamReL: Learning Parameter Space Representation via Progressively Encoding Bayesian Flow Networks
Zhangkai Wu, Xuhui Fan, Jin Li +3
The recently proposed Bayesian Flow Networks~(BFNs) show great potential in modeling parameter spaces, offering a unified strategy for handling continuous, discretized, and discret…
FedSI: Federated Subnetwork Inference for Efficient Uncertainty Quantification
Hui Chen, Hengyu Liu, Zhangkai Wu +2
While deep neural networks (DNNs) based personalized federated learning (PFL) is demanding for addressing data heterogeneity and shows promising performance, existing methods for f…
A Temporally Disentangled Contrastive Diffusion Model for Spatiotemporal Imputation
Yakun Chen, Kaize Shi, Zhangkai Wu +5
Spatiotemporal data analysis is pivotal across various domains, such as transportation, meteorology, and healthcare. The data collected in real-world scenarios are often incomplete…
Weakly Augmented Variational Autoencoder in Time Series Anomaly Detection
Zhangkai Wu, Longbing Cao, Qi Zhang +2
Due to their unsupervised training and uncertainty estimation, deep Variational Autoencoders (VAEs) have become powerful tools for reconstruction-based Time Series Anomaly Detectio…
CVAE: Gaussian Copula-based VAE Differing Disentangled from Coupled Representations with Contrastive Posterior
Zhangkai Wu, Longbing Cao
We present a self-supervised variational autoencoder (VAE) to jointly learn disentangled and dependent hidden factors and then enhance disentangled representation learning by a sel…
eVAE: Evolutionary Variational Autoencoder
Zhangkai Wu, Longbing Cao, Lei Qi
The surrogate loss of variational autoencoders (VAEs) poses various challenges to their training, inducing the imbalance between task fitting and representation inference. To avert…
Differentiable Meta-learning Model for Few-shot Semantic Segmentation
Pinzhuo Tian, Zhangkai Wu, Lei Qi +3
To address the annotation scarcity issue in some cases of semantic segmentation, there have been a few attempts to develop the segmentation model in the few-shot learning paradigm.…