Hao Wang

45

Papers

181

Total Citations

Papers (45)

Zero-1-to-3: Domain-Level Zero-Shot Cognitive Diagnosis via One Batch of Early-Bird Students towards Three Diagnostic Objectives

Agent4Edu: Generating Learner Response Data by Generative Agents for Intelligent Education Systems

Backdoor Federated Learning by Poisoning Backdoor-Critical Layers

Learning to Prompt Knowledge Transfer for Open-World Continual Learning

Revealing Key Details to See Differences: A Novel Prototypical Perspective for Skeleton-based Action Recognition

B-spine: Learning B-spline Curve Representation for Robust and Interpretable Spinal Curvature Estimation

OLinear: A Linear Model for Time Series Forecasting in Orthogonally Transformed Domain

NeurIPS 2025arXiv

MultiGO: Towards Multi-level Geometry Learning for Monocular 3D Textured Human Reconstruction

PhysSplat: Efficient Physics Simulation for 3D Scenes via MLLM-Guided Gaussian Splatting

Cautiously-Optimistic Knowledge Sharing for Cooperative Multi-Agent Reinforcement Learning

ADHMR: Aligning Diffusion-based Human Mesh Recovery via Direct Preference Optimization

Enhancing Plausibility Evaluation for Generated Designs with Denoising Autoencoder

LARGO: Latent Adversarial Reflection through Gradient Optimization for Jailbreaking LLMs

Sequence Complementor: Complementing Transformers for Time Series Forecasting with Learnable Sequences

SSC-VAE: Structured Sparse Coding Based Variational Autoencoder for Detail Preserved Image Reconstruction

FIC-TSC: Learning Time Series Classification with Fisher Information Constraint

From Feature Interaction to Feature Generation: A Generative Paradigm of CTR Prediction Models

CSPCL: Category Semantic Prior Contrastive Learning for Deformable DETR-Based Prohibited Item Detectors

NeurIPS 2025arXiv

PoGDiff: Product-of-Gaussians Diffusion Models for Imbalanced Text-to-Image Generation

Design Graph Guided Element Importance-Aware Layout Generation with Multi-Modality Cascade Transformer

Near-Optimal Quantum Algorithm for Minimizing the Maximal Loss

Delving into Differentially Private Transformer

Probabilistic Conceptual Explainers: Trustworthy Conceptual Explanations for Vision Foundation Models

Probability Distribution of Hypervolume Improvement in Bi-objective Bayesian Optimization

TimeMIL: Advancing Multivariate Time Series Classification via a Time-aware Multiple Instance Learning

Fractional Deep Reinforcement Learning for Age-Minimal Mobile Edge Computing

RegGS: Unposed Sparse Views Gaussian Splatting with 3DGS Registration

Cracking Instance Jigsaw Puzzles: A Superior Alternative to Multiple Instance Learning for Whole Slide Image Analysis

Stealthy Backdoor Attack in Federated Learning via Adaptive Layer-wise Gradient Alignment

AirCache: Activating Inter-modal Relevancy KV Cache Compression for Efficient Large Vision-Language Model Inference

Knowledge-Guided Part Segmentation

Unified Open-World Segmentation with Multi-Modal Prompts

Outdoor Monocular SLAM with Global Scale-Consistent 3D Gaussian Pointmaps

Medical MLLM Is Vulnerable: Cross-Modality Jailbreak and Mismatched Attacks on Medical Multimodal Large Language Models

Manhattan Self-Attention Diffusion Residual Networks with Dynamic Bias Rectiﬁcation for BCI-based Few-Shot Learning

WHALE-FL: Wireless and Heterogeneity Aware Latency Efficient Federated Learning over Mobile Devices via Adaptive Subnetwork Scheduling

Knockoffs Inference for Partially Linear Models with Automatic Structure Discovery

Integrated Decision Gradients: Compute Your Attributions Where the Model Makes Its Decision

StyleStudio: Text-Driven Style Transfer with Selective Control of Style Elements

Cheaper and Faster: Distributed Deep Reinforcement Learning with Serverless Computing

ViLT-CLIP: Video and Language Tuning CLIP with Multimodal Prompt Learning and Scenario-guided Optimization

DOCTR: Disentangled Object-Centric Transformer for Point Scene Understanding

Composite Active Learning: Towards Multi-Domain Active Learning with Theoretical Guarantees

FedST: Federated Style Transfer Learning for Non-IID Image Segmentation

CGI-DM: Digital Copyright Authentication for Diffusion Models via Contrasting Gradient Inversion