Author

Huaibo Huang

Observed name: Huang, Huaibo

Institutions: Chinese Academy of Sciences, Institute of Automation, University of Chinese Academy of Sciences, University College of Applied Science

Observed institutions: Chinese Academy of Sciences, Institute of Automation, University of Chinese Academy of Sciences, University College of Applied Science

OpenAlex ID: A5134196552

FlashPrefill: Instantaneous Pattern Discovery and Thresholding for Ultra-Fast Long-Context Prefilling

2026 · Fan, Qihang, Huang, Huaibo, et al. · arXiv (Cornell University) · 13

InfiMM-HD: A Leap Forward in High-Resolution Multimodal Understanding

2024 · Liu, Haogeng, You, Quanzeng, et al. · arXiv (Cornell University) · 10

BitDance: Scaling Autoregressive Generative Models with Binary Tokens

2026 · Ai, Yuang, Han, Jiaming, et al. · arXiv (Cornell University) · 5

FlashPrefill V2: Block-Sparse Prefill Attention for Long-Context LLM Serving

2026 · Fan, Qihang, Huang, Huaibo, et al. · arXiv (Cornell University) · 3

BitLM: Unlocking Multi-Token Language Generation with Bitwise Continuous Diffusion

2026 · Zhuang, Shaobin, Ai, Yuang, et al. · arXiv (Cornell University) · 3

UniPrefill: Universal Long-Context Prefill Acceleration via Block-wise Dynamic Sparsification

2026 · Fan, Qihang, Huang, Huaibo, et al. · arXiv (Cornell University) · 3

HalluClear: Diagnosing, Evaluating and Mitigating Hallucinations in GUI Agents

2026 · Jin, Chao, Yang, Wenkui, et al. · arXiv (Cornell University) · 3

Coloring the Noise: Adversarial Sobolev Alignment for Faithful Image Super Resolution

2026 · Wang, Hongbo, Huang, Huaibo, et al. · arXiv (Cornell University) · 1

UniWeTok: An Unified Binary Tokenizer with Codebook Size $\mathit{2^{128}}$ for Unified Multimodal Large Language Model

2026 · Zhuang, Shaobin, Ai, Yuang, et al. · arXiv (Cornell University) · 1

The GUI Is Not the State: Diagnosing State Aliasing in GUI World Models

2026 · Liu, Dongsheng, Jin, Chao, et al. · arXiv (Cornell University)

Vera: Identity-Faithful Human Subject-to-Video Generation

2026 · Xu, Yulong, Liu, Xinyue, et al. · arXiv (Cornell University)

Hallo4D: Multi-Modal Hallucination Mitigation for Consistent Spatio-Temporal Generation

2026 · Wang, Hongbo, Huang, Huaibo, et al. · arXiv (Cornell University)

Random Wins All: Rethinking Grouping Strategies for Vision Tokens

2026 · Fan, Qihang, Ai, Yuang, et al. · arXiv (Cornell University)

Works count: 13

Citation count: 42

H-index: 3

I10-index: 2