IanHuang's picture

4 2

IanHuang

Hukcc1

·

https://hukcc.github.io/

AI & ML interests

Multimodal LLMs | Efficiency | Reliability | Hallucination Detection & Mitigation | Video Understanding | Layout Understanding

Recent Activity

authored a paper 5 days ago

D-CoDe: Scaling Image-Pretrained VLMs to Video via Dynamic Compression and Question Decomposition

authored a paper 5 days ago

SHIELD: Suppressing Hallucinations In LVLM Encoders via Bias and Vulnerability Defense

authored a paper 5 days ago

Distorted or Fabricated? A Survey on Hallucination in Video LLMs

View all activity

Organizations

upvoted a paper 3 months ago

SHIELD: Suppressing Hallucinations In LVLM Encoders via Bias and Vulnerability Defense

Paper • 2510.16596 • Published Oct 18, 2025 • 1

upvoted a paper 4 months ago

Fine-T2I: An Open, Large-Scale, and Diverse Dataset for High-Quality T2I Fine-Tuning

Paper • 2602.09439 • Published Feb 10 • 14

upvoted 2 papers 8 months ago

Achieving Tokenizer Flexibility in Language Models through Heuristic Adaptation and Supertoken Learning

Paper • 2505.09738 • Published May 14, 2025 • 10

D-CoDe: Scaling Image-Pretrained VLMs to Video via Dynamic Compression and Question Decomposition

Paper • 2510.08818 • Published Oct 9, 2025 • 2