collaborators

5 papers

cs.LG2026

IPEC: Test-Time Incremental Prototype Enhancement Classifier for Few-Shot Learning

Wenwen Liao, Hang Ruan, Jianbo Yu +3

Metric-based few-shot approaches have gained significant popularity due to their relatively straightforward implementation, high interpret ability, and computational efficiency. Ho…

cs.CV2026

Beyond Single Prompts: Synergistic Fusion and Arrangement for VICL

Wenwen Liao, Jianbo Yu, Yuansong Wang +2

Vision In-Context Learning (VICL) enables inpainting models to quickly adapt to new visual tasks from only a few prompts. However, existing methods suffer from two key issues: (1)…

cs.CV2026

Enhancing Visual In-Context Learning by Multi-Faceted Fusion

Wenwen Liao, Jianbo Yu, Yuansong Wang +2

Visual In-Context Learning (VICL) has emerged as a powerful paradigm, enabling models to perform novel visual tasks by learning from in-context examples. The dominant "retrieve-the…

cs.CV2026

InfoSculpt: Sculpting the Latent Space for Generalized Category Discovery

Wenwen Liao, Hang Ruan, Jianbo Yu +3

Generalized Category Discovery (GCD) aims to classify instances from both known and novel categories within a large-scale unlabeled dataset, a critical yet challenging task for rea…

cs.CV2026

EfficientFSL: Enhancing Few-Shot Classification via Query-Only Tuning in Vision Transformers

Wenwen Liao, Hang Ruan, Jianbo Yu +3

Large models such as Vision Transformers (ViTs) have demonstrated remarkable superiority over smaller architectures like ResNet in few-shot classification, owing to their powerful…