Showing Post From Research
Robust Multimodal Learning via Cross-Modal Proxy Tokens
Imagine an AI designed to understand the world through multiple senses—like sight and hearing. It can identify a cat by both its picture (vision) and its “meow” (audio).
Read more
MMP: Towards Robust Multi-Modal Learning with Masked Modality Projection
In real-world applications, input modalities might be missing due to factors like sensor malfunctions or data constraints. Our recent paper addresses this challenge with a method called …
Read more
Basin-wide groundwater level forecasting with Transfer Learning and LSTM
Groundwater is the lifeline of millions, but predicting its levels—especially over large areas—is very difficult. Traditional physically based models demand immense data and computational …
Read more
U2A: Unified Unimodal Adaptation for Robust and Efficient Multimodal Learning
Imagine you are using an AI system that analyzes both images and text to classify food items. It works great—until suddenly, the text data is missing.
Read more
Model, Analyze, and Comprehend User Interactions within a Social Media Platform
Social media has transformed how we communicate, but have you ever wondered what really happens beneath the surface? Who drives the discussions?
Read more
Robust Multimodal Learning with Missing Modalities via Parameter-Efficient Adaptation
Missing modalities at test time can cause significant degradation in the performance of multimodal systems. In this paper, we presented a simple and parameter-efficient adaptation method for …
Read more