Tho Tran Huu

7 papers · 2023–2025 · 3 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

🌍 Conference Polyglot · Bronze 🗺️ Taxonomy Completionist (13)

Venues

ICML (4) ICLR (2) UAI (1)

Top co-authors

Tan Minh Nguyen (7) Hoang V. Tran (3) Hien Dang (3) Minh-Khoi Nguyen-Nhat (3) nhật Hồ (3) An Nguyen The (2) Duy-Tung Pham (2) Thieu Vo (2) Thanh Tran (2) Hung The Tran (1)

Research topics

Deep Learning (4) Machine Learning (4) Artificial Intelligence (2) Architectures (2) Optimization & Theory (2) Mathematics & Optimization (1) Application Areas (1) Bayesian & Probabilistic (1) Core AI (1) Core Methods (1) Learning Paradigms (1) Mathematics (1) Models (1) Techniques (1)

Keywords

neural collapse (2) feature learning (1) parameter estimation (1) optimal transport (1) sliced wasserstein distance (1) gaussian process (1) sparse approximation (1) parameter sharing (1) expressivity (1) latent variable (1) group action (1) variational autoencoder (1) weight space (1) equivariant learning (1) imbalanced data (1) neural functional network (1) deep linear network (1) uncertainty calibration (1) cross entropy (1) posterior collapse (1)

Papers

Equivariant Neural Functional Networks for Transformers ICLR 2025 Equivariant Polynomial Functional Networks ICML 2025 Tree-Sliced Wasserstein Distance: A Geometric Perspective ICML 2025 Beyond Vanilla Variational Autoencoders: Detecting Posterior Collapse in Conditional and Hierarchical Variational Autoencoders ICLR 2024 Neural Collapse for Cross-entropy Class-Imbalanced Learning with Unconstrained ReLU Features Model ICML 2024 Revisiting Kernel Attention with Correlated Gaussian Process Representation UAI 2024 Neural Collapse in Deep Linear Networks: From Balanced to Imbalanced Data ICML 2023