Qianying Liu
3 indexed papers
Publications per year
Top categories
Frequent co-authors
Research Timeline
The paper identifies a failure mode called spatial lexical bias in MLLMs, where adding a spatial word to options biases the model's choice, and demonstrates that this failure originates primarily from the language processing side rather than poor visual attention.
The paper identifies a failure mode called spatial lexical bias in MLLMs, where adding a spatial word to options biases the model's choice, and demonstrates that this failure originates primarily from the language processing side rather than poor visual attention.
The paper presents Foil, a method for looping sparse mixture-of-experts (MoE) models to improve expert usage and performance.
Papers
How to Loop MoE: Flatten the Experts, Untie the Attention
Shouren Wang, Chuang Ma, Mohsen Hariri, Debargha Ganguly +5 more
The paper presents Foil, a method for looping sparse mixture-of-experts (MoE) models to improve expert usage and performance.