arXiv subjects

Jihun Lee

Publications and source records attributed to Jihun Lee.

4 recordsLinked to original sources

arXiv2025

Piece of Table: A Divide-and-Conquer Approach for Selecting Subtables in Table Question Answering

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 subtable-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 subtable. 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 subtable union algorithm, PieTa demonstrates improved performance over previous subtable-based QA approaches.

cs.CL↗

arXiv2023

DeepCompass: AI-driven Location-Orientation Synchronization for Navigating Platforms

In current navigating platforms, the user's orientation is typically estimated based on the difference between two consecutive locations. In other words, the orientation cannot be identified until the second location is taken. This asynchronous location-orientation identification often leads to our real-life question: Why does my navigator tell the wrong direction of my car at the beginning? We propose DeepCompass to identify the user's orientation by bridging the gap between the street-view and the user-view images. First, we explore suitable model architectures and design corresponding input configuration. Second, we demonstrate artificial transformation techniques (e.g., style transfer and road segmentation) to minimize the disparity between the street-view and the user's real-time experience. We evaluate DeepCompass with extensive evaluation in various driving conditions. DeepCompass does not require additional hardware and is also not susceptible to external interference, in contrast to magnetometer-based navigator. This highlights the potential of DeepCompass as an add-on to existing sensor-based orientation detection methods.

cs.CV↗

arXiv2023

An Asynchronous Wireless Network for Capturing Event-Driven Data from Large Populations of Autonomous Sensors

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.

eess.SP↗

arXiv2023

ODIN: On-demand Data Formulation to Mitigate Dataset Lock-in

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.

cs.LG↗