Abstract:Applying language models (LMs) to tables is challenging due to the inherent structural differences between two-dimensional tables and one-dimensional text for which the LMs were originally designed. Furthermore, when applying linearized tables to LMs, the maximum token lengths often imposed in self-attention calculations make it difficult to comprehensively understand the context spread across large tables. To address these challenges, we present PieTa (Piece of Table), a new framework for sub-table-based question answering (QA). PieTa operates through an iterative process of dividing tables into smaller windows, using LMs to select relevant cells within each window, and merging these cells into a sub-table. This multi-resolution approach captures dependencies across multiple rows and columns while avoiding the limitations caused by long context inputs. Instantiated as a simple iterative sub-table union algorithm, PieTa demonstrates improved performance over previous sub-table-based QA approaches.
Abstract:We introduce a wireless RF network concept for capturing sparse event-driven data from large populations of spatially distributed autonomous microsensors, possibly numbered in the thousands. Each sensor is assumed to be a microchip capable of event detection in transforming time-varying inputs to spike trains. Inspired by brain information processing, we have developed a spectrally efficient, low-error rate asynchronous networking concept based on a code-division multiple access method. We characterize the network performance of several dozen submillimeter-size silicon microchips experimentally, complemented by larger scale in silico simulations. A comparison is made between different implementations of on-chip clocks. Testing the notion that spike-based wireless communication is naturally matched with downstream sensor population analysis by neuromorphic computing techniques, we then deploy a spiking neural network (SNN) machine learning model to decode data from eight thousand spiking neurons in the primate cortex for accurate prediction of hand movement in a cursor control task.
Abstract:ODIN is an innovative approach that addresses the problem of dataset constraints by integrating generative AI models. Traditional zero-shot learning methods are constrained by the training dataset. To fundamentally overcome this limitation, ODIN attempts to mitigate the dataset constraints by generating on-demand datasets based on user requirements. ODIN consists of three main modules: a prompt generator, a text-to-image generator, and an image post-processor. To generate high-quality prompts and images, we adopted a large language model (e.g., ChatGPT), and a text-to-image diffusion model (e.g., Stable Diffusion), respectively. We evaluated ODIN on various datasets in terms of model accuracy and data diversity to demonstrate its potential, and conducted post-experiments for further investigation. Overall, ODIN is a feasible approach that enables Al to learn unseen knowledge beyond the training dataset.