collaborators

7 papers

cs.CV2026

Rethinking Visual Autoregressive Sampling with Information-Grounding Guidance

Ky Dan Nguyen, Hoang Lam Tran, Anh-Dung Dinh +4

Autoregressive (AR) models based on next-scale prediction have emerged as a powerful tool for image generation, but they face a critical weakness: information inconsistencies betwe…

cs.CV2026

Learning Topology-Aware Implicit Field for Unified Pulmonary Tree Modeling with Incomplete Topological Supervision

Ziqiao Weng, Jiancheng Yang, Kangxian Xie +2

Pulmonary trees extracted from CT images frequently exhibit topological incompleteness, such as missing or disconnected branches, which substantially degrades downstream anatomical…

cs.LG2026

FedSKD: Aggregation-free Model-heterogeneous Federated Learning via Multi-dimensional Similarity Knowledge Distillation for Medical Image Classification

Ziqiao Weng, Weidong Cai, Bo Zhou

Federated learning (FL) enables privacy-preserving collaborative model training without direct data sharing. Model-heterogeneous FL (MHFL) extends this paradigm by allowing clients…

cs.RO2026

Constraining Streaming Flow Models for Adapting Learned Robot Trajectory Distributions

Jieting Long, Dechuan Liu, Weidong Cai +2

Robot motion distributions often exhibit multi-modality and require flexible generative models for accurate representation. Streaming Flow Policies (SFPs) have recently emerged as…

cs.CV2025

HiFusion: Hierarchical Intra-Spot Alignment and Regional Context Fusion for Spatial Gene Expression Prediction from Histopathology

Ziqiao Weng, Yaoyu Fang, Jiahe Qian +4

Spatial transcriptomics (ST) bridges gene expression and tissue morphology but faces clinical adoption barriers due to technical complexity and prohibitive costs. While computation…

cs.CV2025

VRM: Knowledge Distillation via Virtual Relation Matching

Weijia Zhang, Fei Xie, Weidong Cai +1

Knowledge distillation (KD) aims to transfer the knowledge of a more capable yet cumbersome teacher model to a lightweight student model. In recent years, relation-based KD methods…