20 citations · 30 across the 13 of their papers we have counts for
14 papers
MiniCorp: The Last Mile to an AI Agent Corporation
Jingying Zeng, Zhenwei Dai, Jinning Li +6
The last mile toward enterprise AGI is a company that runs itself. Training and adapting such agents require longitudinal enterprise data, which remain scarce, costly to acquire, a…
LLM-Integrated Bayesian State Space Models for Multimodal Time-Series Forecasting
Sungjun Cho, Changho Shin, Suenggwan Jo +3
Forecasting in the real world requires integrating structured time-series data with unstructured textual information, but existing methods are architecturally limited by fixed inpu…
TARDIS: Mitigating Temporal Misalignment via Representation Steering
Changho Shin, Xinya Yan, Suenggwan Jo +3
Language models often struggle with temporal misalignment, performance degradation caused by shifts in the temporal distribution of data. Continuously updating models to avoid degr…
Personalize Your LLM: Fake it then Align it
Yijing Zhang, Dyah Adila, Changho Shin +1
Personalizing large language models (LLMs) is essential for delivering tailored interactions that improve user experience. Many existing personalization methods require fine-tuning…
Weak-to-Strong Generalization Through the Data-Centric Lens
Changho Shin, John Cooper, Frederic Sala
The weak-to-strong generalization phenomenon is the driver for important machine learning applications including highly data-efficient learning and, most recently, performing super…
Evaluating Language Model Context Windows: A "Working Memory" Test and Inference-time Correction
Amanda Dsouza, Christopher Glaze, Changho Shin +1
Large language models are prominently used in real-world applications, often tasked with reasoning over large volumes of documents. An exciting development in this space is models…
Is Free Self-Alignment Possible?
Dyah Adila, Changho Shin, Yijing Zhang +1
Aligning pretrained language models (LMs) often requires large-scale preference data and substantial computational resources. These costs become even more prohibitive for multi-obj…
OTTER: Effortless Label Distribution Adaptation of Zero-shot Models
Changho Shin, Jitian Zhao, Sonia Cromp +2
Popular zero-shot models suffer due to artifacts inherited from pretraining. One particularly detrimental issue, caused by unbalanced web-scale pretraining data, is mismatched labe…
Multimodal Data Curation via Object Detection and Filter Ensembles
Tzu-Heng Huang, Changho Shin, Sui Jiet Tay +2
We propose an approach for curating multimodal data that we used for our entry in the 2023 DataComp competition filtering track. Our technique combines object detection and weak su…
Zero-Shot Robustification of Zero-Shot Models
Dyah Adila, Changho Shin, Linrong Cai +1
Zero-shot inference is a powerful paradigm that enables the use of large pretrained models for downstream classification tasks without further training. However, these models are v…
Mitigating Source Bias for Fairer Weak Supervision
Changho Shin, Sonia Cromp, Dyah Adila +1
Weak supervision enables efficient development of training sets by reducing the need for ground truth labels. However, the techniques that make weak supervision attractive -- such…
Universalizing Weak Supervision
Changho Shin, Winfred Li, Harit Vishwakarma +2
Weak supervision (WS) frameworks are a popular way to bypass hand-labeling large datasets for training data-hungry models. These approaches synthesize multiple noisy but cheaply-ac…
Subtask Gated Networks for Non-Intrusive Load Monitoring
Changho Shin, Sunghwan Joo, Jaeryun Yim +3
Non-intrusive load monitoring (NILM), also known as energy disaggregation, is a blind source separation problem where a household's aggregate electricity consumption is broken down…
Statistical Characteristics of Deep Representations: An Empirical Investigation
Daeyoung Choi, Kyungeun Lee, Duhun Hwang +1
In this study, the effects of eight representation regularization methods are investigated, including two newly developed rank regularizers (RR). The investigation shows that the s…