Wei-Lun Chao

Assistant Professor@Boston University, Boston University·美国·OpenReview

研究方向

Generative models · Tabular deep learning · Foundation model · Interpretable model · Parameter efficient transfer learning · federated learning · long-tailed visual recognition · perception in autonomous driving · visual question answering · multi-modal signal processing · transfer learning · domain adaptation · meta learning · few-shot learning · zero-shot learning

Wei-Lun Chao

BioCAP: Exploiting Synthetic Captions Beyond Labels in Biological Foundation Models

Continual Unlearning for Text-to-Image Diffusion Models: A Regularization Perspective

High-Fidelity Scientific Simulation Surrogates via Adaptive Implicit Neural Representations

AVA-Bench: Atomic Visual Ability Benchmark for Vision Foundation Models

EgoFact: A Benchmark for Multi-Hop Multimodal Retrieval-Augmented Generation

A Closer Look at TabPFN v2: Understanding Its Strengths and Extending Its Capabilities

BioCLIP 2: Emergent Properties from Scaling Hierarchical Contrastive Learning

Revisiting Semi-Supervised Learning in the Era of Foundation Models

Frequency-Guided Masking for Enhanced Vision Self-Supervised Learning

Revisiting Nearest Neighbor for Tabular Data: A Deep Tabular Baseline Two Decades Later

Rethinking Pre-Training in Tabular Data: A Neighborhood Embedding Perspective

What Do You See in Common? Learning Hierarchical Prototypes over Tree-of-Life to Discover Evolutionary Traits

Learning 3D Perception from Others' Predictions

Zero-shot Object-level Out-of-distribution Detection with Context-aware Inpainting

Lessons Learned from a Unifying Empirical Study of Parameter-Efficient Transfer Learning (PETL) in Visual Recognition

KnobGen: Controlling the Sophistication of Artwork in Sketch-Based Diffusion Models