Search Results for author:
Found 4 papers, 0 papers with code
Astrea: A MOE-based Visual Understanding Model with Progressive Alignment
Vision-Language Models (VLMs) based on Mixture-of-Experts (MoE) architectures have emerged as a pivotal paradigm in multimodal understanding, offering a powerful framework for integrating visual and linguistic information.
Fine-tuning can Help Detect Pretraining Data from Large Language Models
In light of this, we introduce a novel and effective method termed Fine-tuned Score Deviation (FSD), which improves the performance of current scoring functions for pretraining data detection.
Exploring Learning Complexity for Efficient Downstream Dataset Pruning
In this paper, we propose a straightforward, novel, and training-free hardness score named Distorting-based Learning Complexity (DLC), to identify informative images and instructions from the downstream dataset efficiently.
Lyrics: Boosting Fine-grained Language-Vision Alignment and Comprehension via Semantic-aware Visual Objects
During the instruction fine-tuning stage, we introduce semantic-aware visual feature extraction, a crucial method that enables the model to extract informative features from concrete visual objects.
Ranked #1 on
Image Captioning
on nocaps entire
