The recent breakthroughs in natural language processing for model pretraining on large
quantities of data have opened the way for similar foundation models in computer vision …

The scaling of Transformers has driven breakthrough capabilities for language models. At
present, the largest large language models (LLMs) contain upwards of 100B parameters …

PaliGemma is an open Vision-Language Model (VLM) that is based on the SigLIP-So400m
vision encoder and the Gemma-2B language model. It is trained to be a versatile and …

The ubiquitous and demonstrably suboptimal choice of resizing images to a fixed resolution
before processing them with computer vision models has not yet been successfully …

Casting semantic segmentation of outdoor LiDAR point clouds as a 2D problem, eg, via
range projection, is an effective and popular approach. These projection-based methods …

We present PlainMamba: a simple non-hierarchical state space model (SSM) designed for
general visual recognition. The recent Mamba model has shown how SSMs can be highly …

Scaling laws have been recently employed to derive compute-optimal model size (number
of parameters) for a given compute duration. We advance and refine such methods to infer …

Abstract Rotary Position Embedding (RoPE) performs remarkably on language models,
especially for length extrapolation of Transformers. However, the impacts of RoPE on …

Since the introduction of the Vision Transformer (ViT), researchers have sought to make ViTs
more efficient by removing redundant information in the processed tokens. While different …

Visual data comes in various forms, ranging from small icons of just a few pixels to long
videos spanning hours. Existing multi-modal LLMs usually standardize these diverse visual …