Chia-Hsiang Kao

Hi, I am a second-year CS PhD student at Cornell, advised by Prof. Bharath Hariharan. My research focuses on cross-modal learning and reasoning with the goal of building robust, trustworthy, and interpretable AI systems. During this period, I have had the prelilege to work with Prof. Kavita Bala, Prof. Carl Vondrick, and Prof. Volodymyr Kuleshov.

Before joining Cornell, I obtained my Medical Doctor degree 🩺 from National Yang Ming Chiao Tung University (NYCU) in Taiwan. During that time, I was fortunate to work with Dr. Pin-Yu Chen at MIT-IBM Research, Prof. Wei-Chen Chiu and Prof. Li-Fen Chen at NYCU, and Prof. Yu-Chiang Frank Wang at NTU.

Publication

Towards LLM Agents for Earth Observation

Chia-Hsiang Kao, Wenting Zhao, Shreelekha Revankar, Samuel Speas, Snehal Bhagat, Rajeev Datta, Cheng Perng Phoo, Utkarsh Mall, Carl Vondrick, Kavita Bala, Bharath Hariharan

We ask and answer: Are AI systems ready for reliable Earth Observation?

Counter-Current Learning: A Biologically Plausible Dual Network Approach for Deep Learning

Chia-Hsiang Kao, Bharath Hariharan

We design a non-backpropagation learning algorithm that mimicks the counter-current exchange mechanisms observed in biological systems.

AllClear: A Comprehensive Dataset and Benchmark for Cloud Removal in Satellite Imagery

Hangyu Zhou*, Chia-Hsiang Kao*, Cheng Perng Phoo, Utkarsh Mall, Bharath Hariharan, Kavita Bala

We build up the largest collection of satellite images with cloud occlusions.

Caduceus: Bi-directional equivariant long-range dna sequence modeling

Yair Schiff, Chia-Hsiang Kao, Aaron Gokaslan, Tri Dao, Albert Gu, Volodymyr Kuleshov

We design a DNA foundation model, specialized in long-context sequence modeling, combining the bi-directional equivariant intuition.

FedBug: A Bottom-Up Gradual Unfreezing Framework for Federated Learning

Chia-Hsiang Kao, Yu-Chiang Frank Wang

We design a federated learning framework to mitigate the dataset shift by gradually unfreezing the model.

MAML Is a Noisy Contrastive Learner in Classification

Chia-Hsiang Kao, Wei-Chen Chiu, Pin-Yu Chen

We show that Model-agnostic meta-learning (MAML) acts as contrastive leaerning.

Awards and Scholarships

2021

Student Travel Award, MICCAI

2020

Undergraduate Research Fellowship, National Science and Technology Council, Taiwan

2018

Undergraduate Research Fellowship, National Science and Technology Council, Taiwan

2018

Summer Research Fellowship, National Science and Technology Council, Taiwan

Services

Conference

AAAI[25], AISTATS[25], AutoML[22], ICML[25], ICLR[25], NeurIPS[21,24]

Interests

🏊🏼 and 🏄

Got a lifeguard license at 18!

🏃 and 🏞️

One half-marathon, two 10Ks, and five 8.9Ks so far!

🎤 and 🎸

Used to play the viola, but play the guitar more now!

Template: this
Last update: Nov. 2024