Haoyu Wang

Affiliations

Purdue UniversitySUNY BuffaloUniversity at AlbanyUniversity of Electronic Science and Technology of China

papers

356

total citations

papers (19)

CODA: A Real-World Road Corner Case Dataset for Object Detection in Autonomous Driving

ECCV 2022arXiv

135

citations

Detecting Backdoors During the Inference Stage Based on Corruption Robustness Consistency

CVPR 2023arXiv

citations

Learning Better with Less: Effective Augmentation for Sample-Efficient Visual Reinforcement Learning

NEURIPS 2023arXiv

citations

Reading Your Heart: Learning ECG Words and Sentences via Pre-training ECG Language Model

ICLR 2025arXiv

citations

Collab-RAG: Boosting Retrieval-Augmented Generation for Complex Question Answering via White-Box and Black-Box LLM Collaboration

COLM 2025arXiv

citations

Towards Federated RLHF with Aggregated Client Preference for LLMs

ICLR 2025arXiv

citations

Mastering Massive Multi-Task Reinforcement Learning via Mixture-of-Expert Decision Transformer

ICML 2025arXiv

citations

AceSearcher: Bootstrapping Reasoning and Search for LLMs via Reinforced Self-Play

NEURIPS 2025arXiv

citations

Dual-view X-ray Detection: Can AI Detect Prohibited Items from Dual-view X-ray Images like Humans?

CVPR 2025arXiv

citations

Towards Poisoning Fair Representations

ICLR 2024arXiv

citations

LIDAO: Towards Limited Interventions for Debiasing (Large) Language Models

ICML 2024arXiv

citations

Word-Level Emotional Expression Control in Zero-Shot Text-to-Speech Synthesis

NEURIPS 2025arXiv

citations

Towards Precise Embodied Dialogue Localization via Causality Guided Diffusion

CVPR 2025

citations

Low-Biased General Annotated Dataset Generation

CVPR 2025arXiv

citations

Spatial Alignment and Temporal Matching Adapter for Video-Radar Remote Physiological Measurement

ICCV 2025

citations

Estimating Spatially-Varying Lighting in Urban Scenes with Disentangled Representation

ECCV 2022

citations

Haoyu Wang

Affiliations

papers (19)

CODA: A Real-World Road Corner Case Dataset for Object Detection in Autonomous Driving

Detecting Backdoors During the Inference Stage Based on Corruption Robustness Consistency

Interactive Medical Image Segmentation: A Benchmark Dataset and Baseline

Glocal Energy-Based Learning for Few-Shot Open-Set Recognition

MV-VTON: Multi-View Virtual Try-On with Diffusion Models

Learning Better with Less: Effective Augmentation for Sample-Efficient Visual Reinforcement Learning

Reading Your Heart: Learning ECG Words and Sentences via Pre-training ECG Language Model

Collab-RAG: Boosting Retrieval-Augmented Generation for Complex Question Answering via White-Box and Black-Box LLM Collaboration

Towards Federated RLHF with Aggregated Client Preference for LLMs

Mastering Massive Multi-Task Reinforcement Learning via Mixture-of-Expert Decision Transformer

AceSearcher: Bootstrapping Reasoning and Search for LLMs via Reinforced Self-Play

Dual-view X-ray Detection: Can AI Detect Prohibited Items from Dual-view X-ray Images like Humans?

Towards Poisoning Fair Representations

LIDAO: Towards Limited Interventions for Debiasing (Large) Language Models

Word-Level Emotional Expression Control in Zero-Shot Text-to-Speech Synthesis

Towards Precise Embodied Dialogue Localization via Causality Guided Diffusion

Low-Biased General Annotated Dataset Generation

Spatial Alignment and Temporal Matching Adapter for Video-Radar Remote Physiological Measurement

Estimating Spatially-Varying Lighting in Urban Scenes with Disentangled Representation

papers (19)

CODA: A Real-World Road Corner Case Dataset for Object Detection in Autonomous Driving

Detecting Backdoors During the Inference Stage Based on Corruption Robustness Consistency

Interactive Medical Image Segmentation: A Benchmark Dataset and Baseline

Glocal Energy-Based Learning for Few-Shot Open-Set Recognition

MV-VTON: Multi-View Virtual Try-On with Diffusion Models

Learning Better with Less: Effective Augmentation for Sample-Efficient Visual Reinforcement Learning

Reading Your Heart: Learning ECG Words and Sentences via Pre-training ECG Language Model

Collab-RAG: Boosting Retrieval-Augmented Generation for Complex Question Answering via White-Box and Black-Box LLM Collaboration

Towards Federated RLHF with Aggregated Client Preference for LLMs

Mastering Massive Multi-Task Reinforcement Learning via Mixture-of-Expert Decision Transformer

AceSearcher: Bootstrapping Reasoning and Search for LLMs via Reinforced Self-Play

Dual-view X-ray Detection: Can AI Detect Prohibited Items from Dual-view X-ray Images like Humans?

Towards Poisoning Fair Representations

LIDAO: Towards Limited Interventions for Debiasing (Large) Language Models

Word-Level Emotional Expression Control in Zero-Shot Text-to-Speech Synthesis

Towards Precise Embodied Dialogue Localization via Causality Guided Diffusion

Low-Biased General Annotated Dataset Generation

Spatial Alignment and Temporal Matching Adapter for Video-Radar Remote Physiological Measurement

Estimating Spatially-Varying Lighting in Urban Scenes with Disentangled Representation