Skip to content
View ShengYun-Peng's full-sized avatar

Highlights

  • Pro
Block or Report

Block or report ShengYun-Peng

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.

Please don't include any personal information such as legal names or email addresses. Maximum 100 characters, markdown supported. This note will be visible to only you.
Report abuse

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

Report abuse
ShengYun-Peng/README.md

Hi there 👋 I am ShengYun (Anthony) Peng, a CS PhD student @Georgia Tech

Research interest:

My research strengthens the generalization and safety of the generative AI, spanning vision models, LLMs, and VLMs. As steps towards this goal, I work on:

  • Generalizable multimodal representation learning: foundation models for table recognition (UniTable, Table Transformer, Self-supervised Pretraining), RGB-infrared fusion object tracking (DsiamMFT, SiamFT), structural health monitoring (system identification).
  • Safe and robust machine learning models: LLM loss landscape (coming soon!), robust CNN design principles (#1 on RobustBench CIFAR-10), multi-task person tracking (SkeleVision), and defending LLM attacks (LLM Self Defense)

Papers

  • Navigating the Safety Landscape: Measuring Risks in Finetuning Large Language Models, preprint - [paper] [code coming soon]
  • UniTable: Towards a Unified Framework for Table Structure Recognition via Self-Supervised Pretraining, preprint - [paper] [code]
  • Self-Supervised Pre-Training for Table Structure Recognition Transformer, AAAI'24 Workshop Oral - [paper] [code]
  • High-Performance Transformers for Table Structure Recognition Need Early Convolutions, NeurIPS'23 Workshop Oral - [paper] [code]
  • Robust Principles: Architectural Design Principles for Adversarially Robust CNNs, BMVC'23 Best Poster Award - [paper] [code]
  • SkeleVision: Towards Adversarial Resiliency of Person Tracking with Multi-Task Learning, ECCV'22 Workshop - [paper] [code]

Pinned Loading

  1. poloclub/unitable poloclub/unitable Public

    UniTable: Towards a Unified Table Foundation Model

    Jupyter Notebook 294 16

  2. poloclub/robust-principles poloclub/robust-principles Public

    Robust Principles: Architectural Design Principles for Adversarially Robust CNNs

    Python 16 3

  3. poloclub/tsr-convstem poloclub/tsr-convstem Public

    High-Performance Transformers for Table Structure Recognition Need Early Convolutions

    Python 36 2