Search Results for author:
Found 5 papers, 3 papers with code
EasyGen: Easing Multimodal Generation with a Bidirectional Conditional Diffusion Model and LLMs
We present EasyGen, an efficient model designed to enhance multimodal understanding and generation by harnessing the capabilities of diffusion models and large language models (LLMs).
Recon: Reducing Conflicting Gradients from the Root for Multi-Task Learning
Our experiments show that such a simple approach can greatly reduce the occurrence of conflicting gradients in the remaining shared layers and achieve better performance, with only a slight increase in model parameters in many cases.
A Closer Look at Blind Super-Resolution: Degradation Models, Baselines, and Performance Upper Bounds
The recently proposed practical degradation model includes a full spectrum of degradation types, but only considers complex cases that use all degradation types in the degradation process, while ignoring many important corner cases that are common in the real world.
Overcoming Catastrophic Forgetting in Incremental Few-Shot Learning by Finding Flat Minima
Our study shows that existing methods severely suffer from catastrophic forgetting, a well-known problem in incremental learning, which is aggravated due to data scarcity and imbalance in the few-shot setting.
Ranked #7 on
Few-Shot Class-Incremental Learning
on mini-Imagenet
Effectiveness of Pre-training for Few-shot Intent Classification
This paper investigates the effectiveness of pre-training for few-shot intent classification.
