PPaperPicks

Nhat Ho

35 papers at tracked venues · 32 at CORE A* · active 20242025

Venues

Frequent coauthors

Papers

  1. Attack on Prompt: Backdoor Attack in Prompt-Based Continual Learning
  2. Beyond Losses Reweighting: Empowering Multi-Task Learning via the Generalization Perspective
  3. ExGra-Med: Extended Context Graph Alignment for Medical Vision-Language Models
  4. Improving Generalization with Flat Hilbert Bayesian Inference
  5. Lightspeed Geometric Dataset Distance via Sliced Optimal Transport
  6. On Minimax Estimation of Parameters in Softmax-Contaminated Mixture of Experts
  7. On Zero-Initialized Attention: Optimal Prompt and Gating Factor Estimation
  8. RepLoRA: Reparameterizing Low-rank Adaptation via the Perspective of Mixture of Experts
  9. Revisiting Prefix-tuning: Statistical Benefits of Reparameterization among Prompts
  10. Statistical Advantages of Perturbing Cosine Router in Mixture of Experts
  11. Towards Marginal Fairness Sliced Wasserstein Barycenter
  12. Understanding Expert Structures on Minimax Parameter Estimation in Contaminated Mixture of Experts
  13. X-Drive: Cross-modality Consistent Multi-Sensor Data Synthesis for Driving Scenarios
  14. A Bayesian Approach for Personalized Federated Learning in Heterogeneous Settings
  15. A General Theory for Softmax Gating Multinomial Logistic Mixture of Experts
  16. Bayesian Nonparametrics Meets Data-Driven Distributionally Robust Optimization
  17. Beyond Vanilla Variational Autoencoders: Detecting Posterior Collapse in Conditional and Hierarchical Variational Autoencoders
  18. Diffeomorphic Mesh Deformation via Efficient Optimal Transport for Cortical Surface Reconstruction
  19. FuseMoE: Mixture-of-Experts Transformers for Fleximodal Fusion
  20. Hierarchical Hybrid Sliced Wasserstein: A Scalable Metric for Heterogeneous Joint Distributions
  21. Improving Computational Complexity in Statistical Models with Local Curvature Information
  22. Integrating Efficient Optimal Transport and Functional Maps for Unsupervised Shape Correspondence Learning
  23. Is Temperature Sample Efficient for Softmax Gaussian Mixture of Experts?
  24. Mixture of Experts Meets Prompt-Based Continual Learning
  25. Neural Collapse for Cross-entropy Class-Imbalanced Learning with Unconstrained ReLU Features Model
  26. On Least Square Estimation in Softmax Gating Mixture of Experts
  27. On Parameter Estimation in Deviated Gaussian Mixture of Experts
  28. Quasi-Monte Carlo for 3D Sliced Wasserstein
  29. Revisiting Deep Audio-Text Retrieval Through the Lens of Transportation
  30. Sigmoid Gating is More Sample Efficient than Softmax Gating in Mixture of Experts
  31. Sliced Wasserstein Estimation with Control Variates
  32. Sliced Wasserstein with Random-Path Projecting Directions
  33. Statistical Perspective of Top-K Sparse Softmax Gating Mixture of Experts
  34. Structure-Aware E(3)-Invariant Molecular Conformer Aggregation Networks
  35. Towards Convergence Rates for Parameter Estimation in Gaussian-gated Mixture of Experts