↓Skip to main content

🏢 University of Texas at Austin

CoFie: Learning Compact Neural Surface Representations with Coordinate Fields
·2625 words·13 mins· loading · loading
AI Generated Computer Vision 3D Vision 🏢 University of Texas at Austin
CoFie: A novel local geometry-aware neural surface representation dramatically improves accuracy and efficiency in 3D shape modeling by using coordinate fields to compress local shape information.
Causal language modeling can elicit search and reasoning capabilities on logic puzzles
·2119 words·10 mins· loading · loading
Natural Language Processing Large Language Models 🏢 University of Texas at Austin
LLMs surprisingly master complex logic puzzles like Sudoku and Zebra puzzles after training on strategically ordered solution steps, revealing hidden reasoning abilities.
Bayesian Nonparametrics Meets Data-Driven Distributionally Robust Optimization
·2079 words·10 mins· loading · loading
AI Generated AI Theory Optimization 🏢 University of Texas at Austin
Boost machine learning model robustness by minimizing a novel data-driven risk criterion that blends Bayesian nonparametrics and smooth ambiguity aversion, ensuring superior out-of-sample performance.
An Accelerated Gradient Method for Convex Smooth Simple Bilevel Optimization
·448 words·3 mins· loading · loading
Machine Learning Optimization 🏢 University of Texas at Austin
Accelerated Gradient Method for Bilevel Optimization (AGM-BiO) achieves state-of-the-art convergence rates for simple bilevel optimization problems, requiring fewer iterations than existing methods to…
Adaptive and Optimal Second-order Optimistic Methods for Minimax Optimization
·1754 words·9 mins· loading · loading
AI Generated AI Theory Optimization 🏢 University of Texas at Austin
New adaptive second-order optimistic methods for minimax optimization achieve optimal convergence without line search, simplifying updates and improving efficiency.
AdaFlow: Imitation Learning with Variance-Adaptive Flow-Based Policies
·2201 words·11 mins· loading · loading
AI Applications Robotics 🏢 University of Texas at Austin
AdaFlow: a novel imitation learning framework boasts fast inference and diverse action generation via variance-adaptive flow-based policies, significantly outperforming existing methods.
Active Classification with Few Queries under Misspecification
·253 words·2 mins· loading · loading
Active Learning 🏢 University of Texas at Austin
Learning halfspaces efficiently under noise is cracked! A novel query language enables a polylog query algorithm for Massart noise, overcoming previous limitations.
A Bayesian Approach for Personalized Federated Learning in Heterogeneous Settings
·1730 words·9 mins· loading · loading
Machine Learning Federated Learning 🏢 University of Texas at Austin
FedBNN: a novel Bayesian framework for personalized federated learning, achieves superior performance in heterogeneous settings while ensuring strict privacy via differential privacy.
$ extit{Read-ME}$: Refactorizing LLMs as Router-Decoupled Mixture of Experts with System Co-Design
·2049 words·10 mins· loading · loading
Natural Language Processing Large Language Models 🏢 University of Texas at Austin
Read-ME refactors pre-trained dense LLMs into efficient, router-decoupled Mixture-of-Experts (MoEs) via activation sparsity, achieving up to 10.1% improvement on MMLU and 6.1% reduction in latency.