Huaxiu Yao

Affiliations

University of North Carolina at Chapel Hill

papers

622

total citations

papers (19)

MMedPO: Aligning Medical Vision-Language Models with Clinical-Aware Multimodal Preference Optimization

ICML 2025arXiv

citations

Improving Domain Generalization with Domain Relations

ICLR 2024arXiv

citations

Weak-for-Strong: Training Weak Meta-Agent to Harness Strong Executors

COLM 2025arXiv

citations

Generating Chain-of-Thoughts with a Pairwise-Comparison Approach to Searching for the Most Promising Intermediate Thought

ICML 2024arXiv

citations

FactTest: Factuality Testing in Large Language Models with Finite-Sample and Distribution-Free Guarantees

ICML 2025arXiv

citations

An Iterative Self-Learning Framework for Medical Domain Generalization

NEURIPS 2023

citations

GRASP: Navigating Retrosynthetic Planning with Goal-driven Policy

NEURIPS 2022

citations

Meta-Learning with Neural Bandit Scheduler

NEURIPS 2023

citations

Position: TrustLLM: Trustworthiness in Large Language Models

ICML 2024

citations

Functionally Regionalized Knowledge Transfer for Low-resource Drug Discovery

NEURIPS 2021

citations

One Meta-tuned Transformer is What You Need for Few-shot Learning

ICML 2024

citations

Huaxiu Yao

Affiliations

papers (19)

HALC: Object Hallucination Reduction via Adaptive Focal-Contrast Decoding

Wild-Time: A Benchmark of in-the-Wild Distribution Shift over Time

C-Mixup: Improving Generalization in Regression

Multimodal Representation Learning by Alternating Unimodal Adaptation

Meta-learning with an Adaptive Task Scheduler

Conformal Prediction for Deep Classifier via Label Ranking

ReAgent-V: A Reward-Driven Multi-Agent Framework for Video Understanding

Online Structured Meta-learning

MMedPO: Aligning Medical Vision-Language Models with Clinical-Aware Multimodal Preference Optimization

Improving Domain Generalization with Domain Relations

Weak-for-Strong: Training Weak Meta-Agent to Harness Strong Executors

Generating Chain-of-Thoughts with a Pairwise-Comparison Approach to Searching for the Most Promising Intermediate Thought

FactTest: Factuality Testing in Large Language Models with Finite-Sample and Distribution-Free Guarantees

An Iterative Self-Learning Framework for Medical Domain Generalization

GRASP: Navigating Retrosynthetic Planning with Goal-driven Policy

Meta-Learning with Neural Bandit Scheduler

Position: TrustLLM: Trustworthiness in Large Language Models

Functionally Regionalized Knowledge Transfer for Low-resource Drug Discovery

One Meta-tuned Transformer is What You Need for Few-shot Learning

papers (19)

HALC: Object Hallucination Reduction via Adaptive Focal-Contrast Decoding

Wild-Time: A Benchmark of in-the-Wild Distribution Shift over Time

C-Mixup: Improving Generalization in Regression

Multimodal Representation Learning by Alternating Unimodal Adaptation

Meta-learning with an Adaptive Task Scheduler

Conformal Prediction for Deep Classifier via Label Ranking

ReAgent-V: A Reward-Driven Multi-Agent Framework for Video Understanding

Online Structured Meta-learning

MMedPO: Aligning Medical Vision-Language Models with Clinical-Aware Multimodal Preference Optimization

Improving Domain Generalization with Domain Relations

Weak-for-Strong: Training Weak Meta-Agent to Harness Strong Executors

Generating Chain-of-Thoughts with a Pairwise-Comparison Approach to Searching for the Most Promising Intermediate Thought

FactTest: Factuality Testing in Large Language Models with Finite-Sample and Distribution-Free Guarantees

An Iterative Self-Learning Framework for Medical Domain Generalization

GRASP: Navigating Retrosynthetic Planning with Goal-driven Policy

Meta-Learning with Neural Bandit Scheduler

Position: TrustLLM: Trustworthiness in Large Language Models

Functionally Regionalized Knowledge Transfer for Low-resource Drug Discovery

One Meta-tuned Transformer is What You Need for Few-shot Learning