How I Study AI - Learn AI Papers & Lectures the Easy Way

MMFineReason: Closing the Multimodal Reasoning Gap via Open Data-Centric Methods

Intermediate

Honglin Lin, Zheng Liu et al.Jan 29arXiv

MMFineReason is a huge, open dataset (1.8 million examples, 5.1 billion solution tokens) that teaches AIs to think step by step about pictures and text together.

#multimodal reasoning#vision-language models#chain-of-thought

See Less, See Right: Bi-directional Perceptual Shaping For Multimodal Reasoning

Intermediate

Shuoshuo Zhang, Yizhen Zhang et al.Dec 26arXiv

The paper teaches vision-language models (AIs that look and read) to pay attention to the right picture parts without needing extra tools during answering time.

#BiPS#perceptual shaping#vision-language models

CASA: Cross-Attention via Self-Attention for Efficient Vision-Language Fusion

Intermediate

Moritz Böhle, Amélie Royer et al.Dec 22arXiv

CASA is a new way to mix images and text inside a language model that keeps speed and memory low while keeping accuracy high.

#CASA#cross-attention#self-attention

Papers3

MMFineReason: Closing the Multimodal Reasoning Gap via Open Data-Centric Methods

See Less, See Right: Bi-directional Perceptual Shaping For Multimodal Reasoning

CASA: Cross-Attention via Self-Attention for Efficient Vision-Language Fusion