Author

Hongsong Wang

Observed name: Wang, Hongsong

Institutions: South China Normal University, Southeast University

Observed institutions: South China Normal University, Southeast University

ORCID: 0000-0002-9464-1778

Observed ORCIDs: 0000-0002-9464-1778, 0009-0002-0605-6833

OpenAlex ID: A5128849717

When Policy Entropy Constraint Fails: Preserving Diversity in Flow-based RLHF via Perceptual Entropy

2026 · Tan, Xiaofeng, Liu, Jun, et al. · arXiv (Cornell University) · 3

PDF

OZ-TAL: Online Zero-Shot Temporal Action Localization

2026 · Han, Chaolei, Wang, Hongsong, et al. · arXiv (Cornell University) · 2

PDF

Multimodal Skeleton-based Action Representation Learning via Decomposition and Composition

2026 · Hongsong Wang, Heng Fei, et al. · Machine Intelligence Research · 2

PDF

TransMem: Transforming Hidden States into Memory for Large Language Models

2026 · Lei, Haodong, Liu, Junming, et al. · arXiv (Cornell University) · 1

PDF

Revealing Artifacts via Noise Amplification: A Novel Perspective for AI-Generated Video Detection

2026 · Cheng, Renxi, Gui, Jie, et al. · arXiv (Cornell University) · 1

PDF

MusicDET: Zero-Shot AI-Generated Music Detection

2026 · Han, Chaolei, Wang, Hongsong, et al. · arXiv (Cornell University) · 1

PDF

Marrying Text-to-Motion Generation with Skeleton-Based Action Recognition

2026 · Kuang, Jidong, Wang, Hongsong, et al. · arXiv (Cornell University) · 1

PDF

Point-Supervised Skeleton-Based Human Action Segmentation

2026 · Hongsong Wang, Yiqin Shen, et al. · Lecture notes in computer science

PDF

MATE: Meta-Prior-Guided Expert Teaming for Multimodal Emotion Recognition

2026 · Hongsong Wang, Kaixin Luo, et al. · ACM International Conference on Multimedia (ACM MM)

GenPrior: Unleashing Text-to-Motion Generative Priors for Zero-Shot Skeleton-based Action Recognition

2026 · Jidong Kuang, Hongsong Wang, et al. · ACM International Conference on Multimedia (ACM MM)

Retrieval-Driven Training-Free AI-Generated Video Attribution

2026 · Cheng, Renxi, Han, Chaolei, et al. · arXiv (Cornell University)

PDF

RAID: Towards Robust AI-Generated Image Detection with Bit-Reversed Images

2026 · Cheng, Renxi, Gui, Jie, et al. · arXiv (Cornell University)

PDF

BitC-3DGS: High-Capacity 3D Gaussian Splatting Watermarking via Bit Compression

2026 · Bi, Yuquan, Yu, Baosheng, et al. · arXiv (Cornell University)

PDF

Toward Universal Skeleton-Based Action Recognition across Heterogeneous Skeletons and Open Vocabularies

2026 · Kuang, Jidong, Wang, Hongsong, et al. · arXiv (Cornell University)

PDF

Structure-Aware Fine-Grained Gaussian Splatting for Expressive Avatar Reconstruction

2026 · Su, Yuze, Wang, Hongsong, et al. · arXiv (Cornell University)

PDF

Attribution as Retrieval: Model-Agnostic AI-Generated Image Attribution

2026 · Wang, Hongsong, Cheng, Renxi, et al. · arXiv (Cornell University)

PDF

Works count: 16

Citation count: 11

H-index: 2

I10-index: