相关论文: 1 Trillion Token (1TT) Platform: A Novel Framework…

We present Expert-Token-Routing, a unified generalist framework that facilitates seamless integration of multiple expert LLMs. Our framework represents expert LLMs as special expert tokens within the vocabulary of a meta LLM. The meta LLM…

Data sharing is very important for accelerating scientific research, business innovations, and for informing individuals. Yet, concerns over data privacy, cost, and lack of secure data-sharing solutions have prevented data owners from…

Decentralized storage networks offer services with intriguing possibilities to reduce inequalities in an extremely centralized market. The challenge is to conceive incentives that are fair in regard to the income distribution among peers.…

Federated Learning (FL) enables collaborative training of Large Language Models (LLMs) across distributed data sources while preserving privacy. However, when federated LLMs are deployed in critical applications, it remains unclear which…

Data only generates value for a few organizations with expertise and resources to make data shareable, discoverable, and easy to integrate. Sharing data that is easy to discover and integrate is hard because data owners lack information…

We introduce Aligner, a novel Parameter-Efficient Fine-Tuning (PEFT) method for aligning multi-billion-parameter-sized Large Language Models (LLMs). Aligner employs a unique design that constructs a globally shared set of tunable tokens…

Modern transportation network modeling increasingly involves the integration of diverse methodologies including sensor-based forecasting, reinforcement learning, classical flow optimization, and demand modeling that have traditionally been…

Large language models (LLMs) have achieved notable progress. Despite their success, next-token prediction (NTP), the dominant method for LLM training and inference, is constrained in both contextual coverage and inference efficiency due to…

Incentives that compensate for the involved costs in the decentralized training of a Federated Learning (FL) model act as a key stimulus for clients' long-term participation. However, it is challenging to convince clients for quality…

To efficiently select optimal dataset combinations for enhancing multi-task learning (MTL) performance in large language models, we proposed a novel framework that leverages a neural network to predict the best dataset combinations. The…

Machine learning is critical for innovation and efficiency in financial markets, offering predictive models and data-driven decision-making. However, challenges such as missing data, lack of transparency, untimely updates, insecurity, and…

Knowledge Tracing (KT) aims to estimate a learner's evolving mastery based on interaction histories. Recent studies have explored Large Language Models (LLMs) for KT via autoregressive nature, but such approaches typically require…

Federated Learning is an emerging distributed collaborative learning paradigm used by many of applications nowadays. The effectiveness of federated learning relies on clients' collective efforts and their willingness to contribute local…

In collaborative learning with streaming data, nodes (e.g., organizations) jointly and continuously learn a machine learning (ML) model by sharing the latest model updates computed from their latest streaming data. For the more resourceful…

Tabular data is the most abundant data type in the world, powering systems in finance, healthcare, e-commerce, and beyond. As tabular datasets grow and span multiple related targets, there is an increasing need to exploit shared task…

It is safe to assume that, for the foreseeable future, machine learning, especially deep learning will remain both data- and computation-hungry. In this paper, we ask: Can we build a global exchange where everyone can contribute computation…

Transformer models have achieved state-of-the-art results, with Large Language Models (LLMs), an evolution of first-generation transformers (1stTR), being considered the cutting edge in several NLP tasks. However, the literature has yet to…

Blockchain is a technology that is often used to share data and assets. However, in the decentralized ecosystem, blockchain-based systems can be utilized to share information and assets without the traditional barriers associated with solo…

We propose a new approach, termed Hybrid DLT, to address a broad range of industrial use cases where certain properties of both private and public DLTs are valuable, while other properties may be unnecessary or detrimental. The Hybrid DLT…

Training large language models (LLMs) requires vast amounts of high-quality data from institutions that face legal, privacy, and strategic constraints. Existing data procurement methods often rely on unverifiable trust or ignore…