Skip to content
View chaewon-research's full-sized avatar

Block or report chaewon-research

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
chaewon-research/README.md

Chaewon Yoon

Data Science student at the University of Wisconsin-Madison.

I study efficient and reliable machine learning, especially what happens when models are pushed under constraints on precision, memory, or compute. My current work looks at where approximation causes important failures and how to preserve or recover the computations that matter without giving up all of the efficiency gains.

Current interests: Efficient ML · Model Compression · Low-Precision Inference · Adaptive Computation · Efficient Inference · ML Systems

CV · LinkedIn · Email


Current Research

Quantized Defect Correction (QDC)

Conditional Precision Bottlenecks and Quantized Defect Correction in Fractional Neural Operators

QDC studies how aggressive low-precision inference affects different parts of a neural operator and whether the resulting failures can be corrected selectively rather than by restoring the entire model to high precision.

The project compares activation and weight sensitivity under quantization, uses residual information to identify important defects, applies selective correction under fixed computational budgets, and includes numerical validation and an A100 W8A8 inference evaluation.

Topics: Quantization · Model Compression · Selective Correction · Neural Operators · GPU Inference

Repository · Preprint · Software DOI


Research Direction

The broader question I want to pursue is:

How far can we reduce the computational cost of machine-learning systems without losing the internal computations or representations that are important for their capabilities?

My current QDC work studies this question in neural operators. I am interested in extending the same general problem to model and representation compression, adaptive precision, memory-efficient inference, and larger neural architectures.


Selected Earlier Research

EvidenceLens

Evidence-state interfaces for bounded human-AI visual inspection.

ACM UIST Adjunct 2026 Poster Publication

Repository · Paper · ACM DOI

C-TEA

Risk-aware active evidence acquisition under workflow, resource, safety, and review-capacity constraints.

Repository · Preprint

Transition-Preserving State Tracking

Controlled generation and auditable state tracking for multi-turn structured interfaces.

Repository · Preprint

Additional research and engineering projects are available under the Repositories tab.


Selected Presentations

WiSys SPARK Symposium 2026
Placement-Aware Quantization for Fractional-PDE Neural Surrogates
DOI

Pi Mu Epsilon Regional Undergraduate Mathematics Conference 2025
Numerical Stability and Convergence of Physics-Constrained Neural Networks in Vibration Modeling
DOI


Contact

Email: chaewon.yoon.ds@gmail.com

Pinned Loading

  1. qdc-fractional-neural-operators qdc-fractional-neural-operators Public

    Quantized Defect Correction for low-precision neural operators: precision-sensitive failure diagnosis, selective recovery, and A100 inference evaluation.

    Python

  2. c-tea c-tea Public

    Risk-aware active evidence acquisition with workflow, resource, safety, and review-capacity constraints.

    Python

  3. evidencelens evidencelens Public

    Evidence-state interfaces for safer human-AI visual inspection. ACM UIST Adjunct 2026 poster publication.