Picture for Wei Huang

Wei Huang

Marketing and Commercialization Center, JD.com

NLPrompt: Noise-Label Prompt Learning for Vision-Language Models

Add code
Dec 02, 2024
Viaarxiv icon

On the Feature Learning in Diffusion Models

Add code
Dec 02, 2024
Viaarxiv icon

VideoEspresso: A Large-Scale Chain-of-Thought Dataset for Fine-Grained Video Reasoning via Core Frame Selection

Add code
Nov 22, 2024
Viaarxiv icon

MapSAM: Adapting Segment Anything Model for Automated Feature Detection in Historical Maps

Add code
Nov 11, 2024
Viaarxiv icon

On the Comparison between Multi-modal and Single-modal Contrastive Learning

Add code
Nov 05, 2024
Viaarxiv icon

Provably Transformers Harness Multi-Concept Word Semantics for Efficient In-Context Learning

Add code
Nov 04, 2024
Viaarxiv icon

Identifiability Analysis of Linear ODE Systems with Hidden Confounders

Add code
Oct 29, 2024
Viaarxiv icon

Efficient Function Placement in Virtual Networks: An Online Learning Approach

Add code
Oct 17, 2024
Viaarxiv icon

MC-MoE: Mixture Compressor for Mixture-of-Experts LLMs Gains More

Add code
Oct 08, 2024
Figure 1 for MC-MoE: Mixture Compressor for Mixture-of-Experts LLMs Gains More
Figure 2 for MC-MoE: Mixture Compressor for Mixture-of-Experts LLMs Gains More
Figure 3 for MC-MoE: Mixture Compressor for Mixture-of-Experts LLMs Gains More
Figure 4 for MC-MoE: Mixture Compressor for Mixture-of-Experts LLMs Gains More
Viaarxiv icon

On the Optimization and Generalization of Two-layer Transformers with Sign Gradient Descent

Add code
Oct 07, 2024
Figure 1 for On the Optimization and Generalization of Two-layer Transformers with Sign Gradient Descent
Figure 2 for On the Optimization and Generalization of Two-layer Transformers with Sign Gradient Descent
Figure 3 for On the Optimization and Generalization of Two-layer Transformers with Sign Gradient Descent
Figure 4 for On the Optimization and Generalization of Two-layer Transformers with Sign Gradient Descent
Viaarxiv icon