5 papers
DRTriton: Large-Scale Synthetic Data Driven Reinforcement Learning for Triton Kernel Generation
Siqi Guo, Ming Lin, Tianbao Yang
Developing efficient CUDA kernels is a fundamental yet challenging task in the generative AI industry. Recent research leverages Large Language Models (LLMs) to automatically conve…
NeuCLIP: Efficient Large-Scale CLIP Training with Neural Normalizer Optimization
Xiyuan Wei, Chih-Jen Lin, Tianbao Yang
Accurately estimating the normalization term (also known as the partition function) in the contrastive loss is a central challenge for training Contrastive Language-Image Pre-train…
Breaking the Limits of Open-Weight CLIP: An Optimization Framework for Self-supervised Fine-tuning of CLIP
Anant Mehta, Xiyuan Wei, Xingyu Chen +1
CLIP has become a cornerstone of multimodal representation learning, yet improving its performance typically requires a prohibitively costly process of training from scratch on bil…
Model Steering: Learning with a Reference Model Improves Generalization Bounds and Scaling Laws
Xiyuan Wei, Ming Lin, Fanjiang Ye +4
This paper formalizes an emerging learning paradigm that uses a trained model as a reference to guide and enhance the training of a target model through strategic data selection or…
Myna: Masking-Based Contrastive Learning of Musical Representations
Ori Yonay, Tracy Hammond, Tianbao Yang
We present Myna, a simple yet effective approach for self-supervised musical representation learning. Built on a contrastive learning framework, Myna introduces two key innovations…