Fei Huang

TRIPS enhances efficiency in vision-language tasks by selecting relevant image patches.

A new approach using multi-agent systems to enhance smaller language models.

A new benchmark evaluates how role-playing agents interact socially.

A new framework improves how language agents learn and perform tasks.

A new method to enhance query rewriting without labeled data.

This article discusses the manipulations and flaws of PD plots in AI fairness.

Examining how LLMs ensure safety and the impact of jailbreaks.

A new method helps AI models learn from errors for better responses.

MIBench tests multimodal models' performance on multiple images.

mPLUG-Owl3 improves understanding of images and videos for better responses.

Otter improves LLMs with efficient parameter insertion, enhancing performance while saving resources.

MaVEn enhances AI's ability to process multiple images for better reasoning.

New experimental techniques enhance insights into scalar meson properties via photoproduction.

New framework improves training data for language models using images and text.

Research on the doubly charged Higgs particle and its implications for neutrinos.

New methods enhance how language models respond, balancing knowledge and current events.

Explore how Fair PCA promotes fairness in data-driven decisions for insurance.

Discover STORM, a novel model combining space and time in stock analysis.