ResearchAlpha Leak

Conferences Topics Top Authors Rankings Browse All

Home/Authors/Po-Yao Huang

Po-Yao Huang

Topic trends: 32,543 papers · similarity ≥ 0.4 · year ≥ 2024 · Data sourced from Semantic Scholar

34,598 papers | Abstracts: 31,650 (91.5%) | Citations: 34,598 (100.0%) | arXiv: 26,074 (75.4%)

Built: Feb 14, 2026, 8:46 PM AMS

10

papers

835

total citations

papers (10)

Masked Autoencoders that Listen

NEURIPS 2022arXiv

Perception Encoder: The best visual embeddings are not at the output of the network

NEURIPS 2025arXiv

MAViL: Masked Audio-Video Learners

NEURIPS 2023arXiv

Diffusion Models as Masked Autoencoders

PerceptionLM: Open-Access Data and Models for Detailed Visual Understanding

NEURIPS 2025arXiv

Space-Time Crop & Attend: Improving Cross-Modal Video Representation Learning

CiT: Curation in Training for Effective Vision-Language Data

MoDE: CLIP Data Experts via Clustering

STMT: A Spatial-Temporal Mesh Transformer for MoCap-Based Action Recognition

Self-Supervised Audio-Visual Soundscape Stylization