Kaizhu Huang

Sequential Information Bottleneck Fusion: Towards Robust and Generalizable Multi-Modal Brain Tumor Segmentation

GeoSDF: Plane Geometry Diagram Synthesis via Signed Distance Field

F1-Reasoner: Synthesizing Verifiable Reasoning Data From Formal Math Statements

Towards Faithful Reasoning in Comics for Small MLLMs

Is Layer Normalization Fine-tuning Sufficient for Visual Distribution Shifts?

Depth-Aware Adversarial Training for Robust Image Classification

Tele-Catch: Adaptive Teleoperation for Dexterous Dynamic 3D Object Catching

ZeroDiff: Solidified Visual-semantic Correlation in Zero-Shot Learning

Can MLLMs Absorb Math Reasoning Abilities from LLMs as Free Lunch?

Is Your Model Really A Good Math Reasoner? Evaluating Mathematical Reasoning with Checklist

Decentralizing Test-time Adaptation under Heterogeneous Data Streams

Consistency Diffusion Models for Singel-Image 3D Reconstruction with priors

PO3AD: Predicting Point Offsets toward Better 3D Point Cloud Anomaly Detection

A Novel Soft Alignment Approach for Language Models with Explicit Listwise Rewards

Personalize to generalize: Towards a universal medical multi-modality generalization through personalization