De-Chuan Zhan

36

Papers

100

Total Citations

Papers (36)

What Makes Objects Similar: A Unified Multi-Metric Learning Approach

Leveraging Cross-Modal Neighbor Representation for Improved CLIP Classification

MOS: Model Surgery for Pre-Trained Model-Based Class-Incremental Learning

Improving LLMs for Recommendation with Out-Of-Vocabulary Tokens

Multimodal Tabular Reasoning with Privileged Structured Information

NeurIPS 2025arXiv

Addressing Imbalanced Domain-Incremental Learning through Dual-Balance Collaborative Experts

Revisit the Essence of Distilling Knowledge through Calibration

SIN: Selective and Interpretable Normalization for Long-Term Time Series Forecasting

Enhancing Class-Imbalanced Learning with Pre-Trained Guidance through Class-Conditional Knowledge Distillation

SeMOPO: Learning High-quality Model and Policy from Low-quality Offline Visual Datasets

Tabular Insights, Visual Impacts: Transferring Expertise from Tables to Images

MLI Formula: A Nearly Scale-Invariant Solution with Noise Perturbation

AD3: Implicit Action is the Key for World Models to Distinguish the Diverse Visual Distractors

Multi-layer Rehearsal Feature Augmentation for Class-Incremental Learning

Few-Shot Learning via Embedding Adaptation With Set-to-Set Functions

Distilling Cross-Task Knowledge via Relationship Matching

Learning Placeholders for Open-Set Recognition

Forward Compatible Few-Shot Class-Incremental Learning

Federated Learning With Position-Aware Neurons

Identifying Ambiguous Similarity Conditions via Semantic Matching

Learning Debiased Representations via Conditional Attribute Interpolation

Procrustean Training for Imbalanced Deep Learning

FOSTER: Feature Boosting and Compression for Class-Incremental Learning

Dual Consolidation for Pre-Trained Model-Based Domain-Incremental Learning

Task-Agnostic Guided Feature Expansion for Class-Incremental Learning

External Knowledge Injection for CLIP-Based Class-Incremental Learning

MIETT: Multi-Instance Encrypted Traffic Transformer for Encrypted Traffic Classification

Capability Instruction Tuning

Expandable Subspace Ensemble for Pre-Trained Model-Based Class-Incremental Learning

Towards Enabling Meta-Learning from Target Models

Asymmetric Temperature Scaling Makes Larger Networks Teach Well Again

Generalized Delayed Feedback Model with Post-Click Information in Recommender Systems

Model Spider: Learning to Rank Pre-Trained Models Efficiently

Few-Shot Class-Incremental Learning via Training-Free Prototype Calibration

Beyond probability partitions: Calibrating neural networks with semantic aware grouping

Rectify Heterogeneous Models with Semantic Mapping