Wei Shen

19

Papers

30

Total Citations

Papers (19)

On the Training Convergence of Transformers for In-Context Classification of Gaussian Mixtures

Parameter-efficient Fine-tuning in Hyperspherical Space for Open-vocabulary Semantic Segmentation

Partial Label Learning with a Partner

Understanding Fine-tuning CLIP for Open-vocabulary Semantic Segmentation in Hyperbolic Space

Tendency-driven Mutual Exclusivity for Weakly Supervised Incremental Semantic Segmentation

HyperET: Efficient Training in Hyperbolic Space for Multi-modal Large Language Models

FATE: Feature-Adapted Parameter Tuning for Vision-Language Models

Label-Free Backdoor Attacks in Vertical Federated Learning

SAM-PARSER: Fine-Tuning SAM Efficiently by Parameter Space Reconstruction

ViTree: Single-Path Neural Tree for Step-Wise Interpretable Fine-Grained Visual Categorization

Parameter Efficient Fine-tuning via Cross Block Orchestration for Segment Anything Model

Linear Alignment: A Closed-form Solution for Aligning Human Preferences without Tuning and Feedback

Marten: Visual Question Answering with Mask Generation for Multi-modal Document Understanding

Training Large Language Models for Reasoning through Reverse Curriculum Reinforcement Learning

Star with Bilinear Mapping

Domain Generalization in CLIP via Learning with Diverse Text Prompts

Generalized Tensor-based Parameter-Efficient Fine-Tuning via Lie Group Transformations

A Token-level Text Image Foundation Model for Document Understanding

Segment Any 3D Gaussians