In recent years, there have been exceptional advancements in Artificial Intelligence, with many new advanced models being introduced, especially in NLP and Computer Vision. CLIP is a neural network developed…

For LLMs, auto-regressive decoding is now considered the gold standard. Because LLMs generate output tokens individually, the procedure is time-consuming and expensive. Methods based on speculative sampling provide an answer…

In artificial intelligence, the pursuit of improving text-to-image generation models has gained significant traction. DALL-E 3, a notable contender in this domain, has recently drawn attention for its remarkable ability…

Super-resolution (SR) techniques have recently been proposed to upscale the outputs of neural radiance fields (NeRF) and generate high-quality images with enhanced inference speeds. However, existing NeRF+SR methods increase training…

This paper was accepted at the workshop on Regulatable ML at NeurIPS 2023. Conformal Prediction (CP) is a method of estimating risk or uncertainty when using Machine Learning to help…

We study differentially private stochastic convex optimization (DP-SCO) under user-level privacy, where each user may hold multiple data items. Existing work for user-level DP-SCO either requires super-polynomial runtime or…

Tracking biosignals is crucial for monitoring wellness and preempting the development of severe medical conditions. Today, wearable devices can conveniently record various biosignals, creating the opportunity to monitor health status…

Representations from models such as Bidirectional Encoder Representations from Transformers (BERT) and Hidden units BERT (HuBERT) have helped to achieve state-of-the-art performance in dimensional speech emotion recognition. Both HuBERT, and…