Dang Nguyen

hsgser's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

authored 10 papers 6 months ago

Understanding the Robustness of Multi-modal Contrastive Learning to Distribution Shift

Paper • 2310.04971 • Published Oct 8, 2023

On Cross-Layer Alignment for Model Fusion of Heterogeneous Neural Networks

Paper • 2110.15538 • Published Oct 29, 2021 • 1

Self-Attention Amortized Distributional Projection Optimization for Sliced Wasserstein Point-Cloud Reconstruction

Paper • 2301.04791 • Published Jan 12, 2023

Mini-batch Coresets for Memory-efficient Language Model Training on Data Mixtures

Paper • 2407.19580 • Published Jul 28, 2024

Synthetic Text Generation for Training Large Language Models via Gradient Matching

Paper • 2502.17607 • Published Feb 24

On Transportation of Mini-batches: A Hierarchical Approach

Paper • 2102.05912 • Published Feb 11, 2021

Improving Mini-batch Optimal Transport via Partial Transportation

Paper • 2108.09645 • Published Aug 22, 2021

Changing the Training Data Distribution to Reduce Simplicity Bias Improves In-distribution Generalization

Paper • 2404.17768 • Published Apr 27, 2024

Beyond Semantic Entropy: Boosting LLM Uncertainty Quantification with Pairwise Semantic Similarity

Paper • 2506.00245 • Published May 30

Do We Need All the Synthetic Data? Towards Targeted Synthetic Image Augmentation via Diffusion Models

Paper • 2505.21574 • Published May 27