Search Results for author:
Found 5 papers, 5 papers with code
SAT: Dynamic Spatial Aptitude Training for Multimodal Language Models
While many studies highlight that large multimodal language models (MLMs) struggle to reason about space, they only focus on static spatial relationships, and not dynamic awareness of motion and space, i. e., reasoning about the effect of egocentric and object motions on spatial relationships.
Cambrian-1: A Fully Open, Vision-Centric Exploration of Multimodal LLMs
We introduce Cambrian-1, a family of multimodal LLMs (MLLMs) designed with a vision-centric approach.
V-IRL: Grounding Virtual Intelligence in Real Life
There is a sensory gulf between the Earth that humans inhabit and the digital realms in which modern AI agents are created.
Your Diffusion Model is Secretly a Zero-Shot Classifier
Our generative approach to classification, which we call Diffusion Classifier, attains strong results on a variety of benchmarks and outperforms alternative methods of extracting knowledge from diffusion models.
Ranked #1 on
Image Classification
on ObjectNet (ImageNet classes)
Internet Explorer: Targeted Representation Learning on the Open Web
Modern vision models typically rely on fine-tuning general-purpose models pre-trained on large, static datasets.
