Related papers: On-Device Fine-Tuning via Backprop-Free Zeroth-Ord…

The predominant paradigm for using machine learning models on a device is to train a model in the cloud and perform inference using the trained model on the device. However, with increasing number of smart devices and improved hardware,…

When the available hardware cannot meet the memory and compute requirements to efficiently train high performing machine learning models, a compromise in either the training quality or the model complexity is needed. In Federated Learning…

Machine learning at the edge offers great benefits such as increased privacy and security, low latency, and more autonomy. However, a major challenge is that many devices, in particular edge devices, have very limited memory, weak…

Fine-tuning large pretrained language models (LLMs) is a cornerstone of modern NLP, yet its growing memory demands (driven by backpropagation and large optimizer States) limit deployment in resource-constrained settings. Zero-order (ZO)…

Optical computing holds promise for high-speed, energy-efficient information processing, with diffractive optical networks emerging as a flexible platform for implementing task-specific transformations. A challenge, however, is the…

Offline preference optimization offers a simpler and more stable alternative to RLHF for aligning language models. However, their effectiveness is critically dependent on ranking accuracy, a metric where further gains are highly impactful.…

We study reinforcement learning in hybrid discrete-continuous action spaces, such as settings where the discrete component selects a regime (or index) and the continuous component optimizes within it -- a structure common in robotics,…

Performance optimization of deep learning models is conducted either manually or through automatic architecture search, or a combination of both. On the other hand, their performance strongly depends on the target hardware and how…

Large Language Model (LLM) at mobile devices and its potential applications never fail to fascinate. However, on-device LLM fine-tuning poses great challenges due to extremely high memory requirements and slow training speeds. Even with…

Nowadays, Large Language Models (LLMs) have been trained using extended context lengths to foster more creative applications. However, long context training poses great challenges considering the constraint of GPU memory. It not only leads…

Large Language Models (LLMs) fine-tuning techniques not only improve the adaptability to diverse downstream tasks, but also mitigate adverse effects of model quantization. Despite this, conventional quantization suffers from its structural…

Onboard learning is a transformative approach in edge AI, enabling real-time data processing, decision-making, and adaptive model training directly on resource-constrained devices without relying on centralized servers. This paradigm is…

Training large language models (LLMs) encounters challenges in GPU memory consumption due to the high memory requirements of model states. The widely used Zero Redundancy Optimizer (ZeRO) addresses this issue through strategic sharding but…

Embedded systems demand on-device processing of data using Neural Networks (NNs) while conforming to the memory, power and computation constraints, leading to an efficiency and accuracy tradeoff. To bring NNs to edge devices, several…

On-device learning remains a formidable challenge, especially when dealing with resource-constrained devices that have limited computational capabilities. This challenge is primarily rooted in two key issues: first, the memory available on…

The mixture of experts (MoE) model is a sparse variant of large language models (LLMs), designed to hold a better balance between intelligent capability and computational overhead. Despite its benefits, MoE is still too expensive to deploy…

Existing pretrained models for 3D mesh generation often suffer from data biases and produce low-quality results, while global reinforcement learning (RL) methods rely on object-level rewards that struggle to capture local structure details.…

Bayesian Optimization (BO) is an efficient tool for optimizing black-box functions, but its theoretical guarantees typically hold in the asymptotic regime. In many critical real-world applications such as drug discovery or materials design,…

In the last three years, the largest dense deep learning models have grown over 1000x to reach hundreds of billions of parameters, while the GPU memory has only grown by 5x (16 GB to 80 GB). Therefore, the growth in model scale has been…

Edge computing allows for reduced latency and operational costs compared to centralized cloud systems. In this context, serverless functions are emerging as a lightweight and effective paradigm for managing computational tasks on edge…