2 citations · 3 across the 14 of their papers we have counts for
14 papers
Not All Variables Agree: Reliability-Aware Variable-Wise Gradient Surgery for Multivariate Time-Series Forecasting
Jinwoo Park, Hyeongwon Kang, Pilsung Kang
In data-driven training, multivariate time-series forecasting is usually optimized with a scalar loss averaged over samples, variables, and horizons. This averaging is convenient,…
FinLifeBench: Exhaustive Life-Event History and Financial-State Reconstruction from Longitudinal Banking Dialogue
Hangyeul Lee, Juyoung Oh, Jaeyong Ko +5
Repeated banking interactions require assistants to maintain complete, current, and traceable customer records as life changes emerge incidentally in routine requests. Existing ben…
Detecting the Undetectable: Enhancing Unsupervised time series Anomaly Detection via Active Learning
Seung Hun Han, Hyeongwon Kang, Jinwoo Park +1
Despite the increasing sophistication of industrial AI systems, the ability to reliably detect subtle and noisy anomalies in complex time series data remains a critical yet unresol…
Cliff Tokens: Analyzing Failure Trigger Tokens in LLM Mathematical Reasoning
Jaeyong Ko, Pilsung Kang, Jinu Lee +1
Large language models reach high accuracy in mathematical reasoning, but individual traces on the same problem diverge; some arrive at the correct answer while others fail. Prior w…
DeCoFlow: Structural Decomposition of Normalizing Flows for Continual Anomaly Detection
Hun Im, Jungi Lee, Subeen Cha +1
In industrial environments, new product categories arrive sequentially, requiring continual anomaly detection without access to past data. Normalizing Flows (NFs) provide exact den…
Detecting Time Series Anomalies Like an Expert: A Multi-Agent LLM Framework with Specialized Analyzers
Hyeongwon Kang, Jeongseob Kim, Jinwoo Park +1
Time-series anomaly detection often returns scores or intervals, while analysts need to understand the abnormal behavior and the evidence supporting it. We introduce SAGE (Speciali…
Forecasting Anomaly Precursors via Uncertainty-Aware Time-Series Ensembles
Hyeongwon Kang, Jinwoo Park, Seunghun Han +1
Detecting anomalies in time-series data is critical in domains such as industrial operations, finance, and cybersecurity, where early identification of abnormal patterns is essenti…
COMET: Codebook-based Online-adaptive Multi-scale Embedding for Time-series Anomaly Detection
Jinwoo Park, Hyeongwon Kang, Seung Hun Han +1
Time series anomaly detection is a critical task across various industrial domains. However, capturing temporal dependencies and multivariate correlations within patch-level repres…
AlienLM: Alienization of Language for API-Boundary Privacy in Black-Box LLMs
Jaehee Kim, Pilsung Kang
Modern LLMs are increasingly accessed via black-box APIs, requiring users to transmit sensitive prompts, outputs, and fine-tuning data to external providers, creating a critical pr…
A Gradient Accumulation Method for Dense Retriever under Memory Constraint
Jaehee Kim, Yukyung Lee, Pilsung Kang
InfoNCE loss is commonly used to train dense retriever in information retrieval tasks. It is well known that a large batch is essential to stable and effective training with InfoNC…
Navigating the Path of Writing: Outline-guided Text Generation with Large Language Models
Yukyung Lee, Soonwon Ka, Bokyung Son +2
Large Language Models (LLMs) have impacted the writing process, enhancing productivity by collaborating with humans in content creation platforms. However, generating high-quality,…
CheckEval: A reliable LLM-as-a-Judge framework for evaluating text generation using checklists
Yukyung Lee, Joonghoon Kim, Jaehee Kim +4
Existing LLM-as-a-Judge approaches for evaluating text generation suffer from rating inconsistencies, with low agreement and high rating variance across different evaluator models.…
Boosting Prompt-Based Self-Training With Mapping-Free Automatic Verbalizer for Multi-Class Classification
Yookyung Kho, Jaehee Kim, Pilsung Kang
Recently, prompt-based fine-tuning has garnered considerable interest as a core technique for few-shot text classification task. This approach reformulates the fine-tuning objectiv…
RAPID: Training-free Retrieval-based Log Anomaly Detection with PLM considering Token-level information
Gunho No, Yukyung Lee, Hyeongwon Kang +1
As the IT industry advances, system log data becomes increasingly crucial. Many computer systems rely on log texts for management due to restricted access to source code. The need…