Tag: faang

Scaling the input image resolution is essential for enhancing the performance of Vision Language Models (VLMs), particularly in text-rich image understanding tasks. However, popular visual encoders such as ViTs become inefficient at high resolutions due to the large number of tokens and high encoding latency. At different operational resolutions, the vision encoder of a VLM …

Read more “FastVLM: Efficient Vision encoding for Vision Language Models”

Gemini 2.5 Flash is our first fully hybrid reasoning model, giving developers the ability to turn thinking on or off.

Learning disentangled representations from unlabelled data is a fundamental challenge in machine learning. Solving it may unlock other problems, such as generalization, interpretability, or fairness. Although remarkably challenging to solve in theory, disentanglement is often achieved in practice through prior matching. Furthermore, recent works have shown that prior matching approaches can be enhanced by leveraging …

Read more “Disentangled Representational Learning with the Gromov-Monge Gap”

Transform text-based prompts into high-resolution eight-second videos in Gemini Advanced and use Whisk Animate to turn images into eight-second animated clips.

Building general-purpose models that can effectively perceive the world through multimodal signals has been a long-standing goal. Current approaches involve integrating separately pre-trained components, such as connecting vision encoders to LLMs and continuing multimodal training. While such approaches exhibit remarkable sample efficiency, it remains an open question whether such late-fusion architectures are inherently superior. In …

Read more “Scaling Laws for Native Multimodal Models”

This paper was accepted at the Workshop on Foundation Models in the Wild at ICLR 2025. Visual understanding is inherently contextual – what we focus on in an image depends on the task at hand. For instance, given an image of a person holding a bouquet of flowers, we may focus on either the person …

Read more “FocalLens: Instruction Tuning Enables Zero-Shot Conditional Image Representations”