Publications (9)
Magnifier Prompt: Tackling Multimodal Hallucination via Extremely Simple Instructions
Yuhan Fu, Ruobing Xie, Jiazhen Liu +4
Hallucinations in multimodal large language models (MLLMs) hinder their practical applications. To address this, we propose a Magnifier Prompt (MagPrompt), a simple yet effective m…
Mitigating Hallucination in Multimodal Large Language Model via Hallucination-targeted Direct Preference Optimization
Yuhan Fu, Ruobing Xie, Xingwu Sun +2
Multimodal Large Language Models (MLLMs) are known to hallucinate, which limits their practical applications. Recent works have attempted to apply Direct Preference Optimization (D…
PhD: A ChatGPT-Prompted Visual hallucination Evaluation Dataset
Jiazhen Liu, Yuhan Fu, Ruobing Xie +5
Multimodal Large Language Models (MLLMs) hallucinate, resulting in an emerging topic of visual hallucination evaluation (VHE). This paper contributes a ChatGPT-Prompted visual hall…
Notes on Diagrammatic Coaction for Cosmological Wavefunction Coefficients: A Two-Site Prelude
Yuhan Fu, Jiahao Liu
We study the coaction of cosmological wavefunction coefficients of conformally coupled scalars in FRW background of a two-site example, which turns out to have an elegant diagramma…
PILA: Plug-and-Play Insertion for LLM-native Advertising
Zhaowei Zhang, Yuhan Fu, Yihang Zhang +6
The paper introduces PILA, a plug‑and‑play sidecar that rewrites LLM responses to insert sponsored content, allowing ad placement without modifying the underlying language model.
Towards a Comprehensive Scaling Law of Mixture-of-Experts
Guoliang Zhao, Yuhan Fu, Shuaipeng Li +10
Mixture-of-Experts (MoE) models have become the consensus approach for enabling parameter-efficient scaling and cost-effective deployment in large language models. However, existin…
Evaluating and Pricing Advertisements in AI-Generated Responses
John L. Turner-Smith, Zimeng Huang, Yuhan Fu +2
The paper introduces a psychologically grounded agent simulation to create supervision for predicting click‑through intent of ads embedded in LLM‑generated responses, builds a ligh…
The disk wind in GRS 1915+105 as seen by Insight-HXMT
Honghui Liu, Yuhan Fu, Cosimo Bambi +7
We analyze three observations of GRS 1915+105 in 2017 by Insight-HXMT when the source was in a spectrally soft state. We find strong absorption lines from highly ionized iron, whic…
Multi-Object Sketch Animation by Scene Decomposition and Motion Planning
Jingyu Liu, Zijie Xin, Yuhan Fu +3
Sketch animation, which brings static sketches to life by generating dynamic video sequences, has found widespread applications in GIF design, cartoon production, and daily enterta…