Geon Choi

Geon Choi, Namyoon Lee

In this paper, we introduce a novel class of pre-transformed polar codes, termed as deep polar codes. We first present a deep polar encoder that harnesses a series of multi-layered polar transformations with varying sizes. Our approach to encoding enables a low-complexity implementation while significantly enhancing the weight distribution of the code. Moreover, our encoding method offers flexibility in rate-profiling, embracing a wide range of code rates and blocklengths. Next, we put forth a low-complexity decoding algorithm called successive cancellation list with backpropagation parity checks (SCL-BPC). This decoding algorithm leverages the parity check equations in the reverse process of the multi-layered pre-transformed encoding for SCL decoding. Additionally, we present a low-latency decoding algorithm that employs parallel-SCL decoding by treating partially pre-transformed bit patterns as additional frozen bits. Through simulations, we demonstrate that deep polar codes outperform existing pre-transformed polar codes in terms of block error rates across various code rates under short block lengths, while maintaining low encoding and decoding complexity. Furthermore, we show that concatenating deep polar codes with cyclic-redundancy-check codes can achieve the meta-converse bound of the finite block length capacity within 0.4 dB in some instances.

Geon Choi, Jeonghun Park, Nir Shlezinger et al.

Simultaneous localization and mapping (SLAM) is a method that constructs a map of an unknown environment and localizes the position of a moving agent on the map simultaneously. Extended Kalman filter (EKF) has been widely adopted as a low complexity solution for online SLAM, which relies on a motion and measurement model of the moving agent. In practice, however, acquiring precise information about these models is very challenging, and the model mismatch effect causes severe performance loss in SLAM. In this paper, inspired by the recently proposed KalmanNet, we present a robust EKF algorithm using the power of deep learning for online SLAM, referred to as Split-KalmanNet. The key idea of Split-KalmanNet is to compute the Kalman gain using the Jacobian matrix of a measurement function and two recurrent neural networks (RNNs). The two RNNs independently learn the covariance matrices for a prior state estimate and the innovation from data. The proposed split structure in the computation of the Kalman gain allows to compensate for state and measurement model mismatch effects independently. Numerical simulation results verify that Split-KalmanNet outperforms the traditional EKF and the state-of-the-art KalmanNet algorithm in various model mismatch scenarios.

Jong Hak Moon, Geon Choi, Paloma Rabaey et al.

Radiology reports convey detailed clinical observations and capture diagnostic reasoning that evolves over time. However, existing evaluation methods are limited to single-report settings and rely on coarse metrics that fail to capture fine-grained clinical semantics and temporal dependencies. We introduce LUNGUAGE,a benchmark dataset for structured radiology report generation that supports both single-report evaluation and longitudinal patient-level assessment across multiple studies. It contains 1,473 annotated chest X-ray reports, each reviewed by experts, and 80 of them contain longitudinal annotations to capture disease progression and inter-study intervals, also reviewed by experts. Using this benchmark, we develop a two-stage framework that transforms generated reports into fine-grained, schema-aligned structured representations, enabling longitudinal interpretation. We also propose LUNGUAGESCORE, an interpretable metric that compares structured outputs at the entity, relation, and attribute level while modeling temporal consistency across patient timelines. These contributions establish the first benchmark dataset, structuring framework, and evaluation metric for sequential radiology reporting, with empirical results demonstrating that LUNGUAGESCORE effectively supports structured report evaluation. The code is available at: https://github.com/SuperSupermoon/Lunguage

Hyungyung Lee, Geon Choi, Jung-Oh Lee et al.

Recent progress in Large Vision-Language Models (LVLMs) has enabled promising applications in medical tasks, such as report generation and visual question answering. However, existing benchmarks focus mainly on the final diagnostic answer, offering limited insight into whether models engage in clinically meaningful reasoning. To address this, we present CheXStruct and CXReasonBench, a structured pipeline and benchmark built on the publicly available MIMIC-CXR-JPG dataset. CheXStruct automatically derives a sequence of intermediate reasoning steps directly from chest X-rays, such as segmenting anatomical regions, deriving anatomical landmarks and diagnostic measurements, computing diagnostic indices, and applying clinical thresholds. CXReasonBench leverages this pipeline to evaluate whether models can perform clinically valid reasoning steps and to what extent they can learn from structured guidance, enabling fine-grained and transparent assessment of diagnostic reasoning. The benchmark comprises 18,988 QA pairs across 12 diagnostic tasks and 1,200 cases, each paired with up to 4 visual inputs, and supports multi-path, multi-stage evaluation including visual grounding via anatomical region selection and diagnostic measurements. Even the strongest of 12 evaluated LVLMs struggle with structured reasoning and generalization, often failing to link abstract knowledge with anatomically grounded visual interpretation. The code is available at https://github.com/ttumyche/CXReasonBench

Geon Choi, Hangyul Yoon, Hyunju Shin et al.

The applicability of current lesion segmentation models for chest X-rays (CXRs) has been limited both by a small number of target labels and the reliance on long, detailed expert-level text inputs, creating a barrier to practical use. To address these limitations, we introduce a new paradigm: instruction-guided lesion segmentation (ILS), which is designed to segment diverse lesion types based on simple, user-friendly instructions. Under this paradigm, we construct MIMIC-ILS, the first large-scale instruction-answer dataset for CXR lesion segmentation, using our fully automated multimodal pipeline that generates annotations from chest X-ray images and their corresponding reports. MIMIC-ILS contains 1.1M instruction-answer pairs derived from 192K images and 91K unique segmentation masks, covering seven major lesion types. To empirically demonstrate its utility, we introduce ROSALIA, a vision-language model fine-tuned on MIMIC-ILS. ROSALIA can segment diverse lesions and provide textual explanations in response to user instructions. The model achieves high segmentation and textual accuracy in our newly proposed task, highlighting the effectiveness of our pipeline and the value of MIMIC-ILS as a foundational resource for pixel-level CXR lesion grounding.