Local deployment of large-scale music AI models on commodity hardware

We present the MIDInfinite, a web application capable of generating symbolic music using a large-scale generative AI model locally on commodity hardware. Creating this demo involved porting the Anticipatory Music Transformer, a large language model (LLM) pre-trained on the Lakh MIDI dataset, to the Machine Learning Compilation (MLC) framework. Once the model is ported, MLC facilitates inference on a variety of runtimes including C++, mobile, and the browser. We envision that MLC has the potential to bridge the gap between the landscape of increasingly capable music AI models and technology more familiar to music software developers. As a proof of concept, we build a web application that allows users to generate endless streams of multi-instrumental MIDI in the browser, either from scratch or conditioned on a prompt. On commodity hardware (an M3 Macbook Pro), our demo can generate 51 notes per second, which is faster than real-time playback for 72.9% of generations, and increases to 86.3% with 2 seconds of upfront buffering.

Approximating Martingale Process for Variance Reduction in Deep Reinforcement Learning with Large State Space

Approximating Martingale Process (AMP) is proven to be effective for variance reduction in reinforcement learning (RL) in specific cases such as Multiclass Queueing Networks. However, in the already proven cases, the state space is relatively small and all possible state transitions can be iterated through. In this paper, we consider systems in which state space is large and have uncertainties when considering state transitions, thus making AMP a generalized variance-reduction method in RL. Specifically, we will investigate the application of AMP in ride-hailing systems like Uber, where Proximal Policy Optimization (PPO) is incorporated to optimize the policy of matching drivers and customers.

Photo Rater: Photographs Auto-Selector with Deep Learning

Photo Rater is a computer vision project that uses neural networks to help photographers select the best photo among those that are taken based on the same scene. This process is usually referred to as "culling" in photography, and it can be tedious and time-consuming if done manually. Photo Rater utilizes three separate neural networks to complete such a task: one for general image quality assessment, one for classifying whether the photo is blurry (either due to unsteady hands or out-of-focusness), and one for assessing general aesthetics (including the composition of the photo, among others). After feeding the image through each neural network, Photo Rater outputs a final score for each image, ranking them based on this score and presenting it to the user.