Perceiver IO
perceiver-io-2b49b3ae·2 events·first seen 28d agoAliases: Perceiver IO, Perceiver
Co-occurring entities
More like this (12)
Recent events (2)
Perceiver IO: a scalable, fully-attentional model that works on any modality
Hugging Face published a blog post introducing Perceiver IO, a general-purpose transformer-based architecture designed to handle arbitrary input and output modalities by using a small latent array to avoid quadratic attention scaling. The model decouples input size from the attention bottleneck, enabling it to process images, audio, video, text, and multimodal data within a single unified framework. The post covers the architecture's design principles and its integration into the Hugging Face ecosystem.
In-context learning applied to Multiple Instance Learning via Perceiver-style pretraining on synthetic data
A new arXiv preprint proposes pretraining an in-context learner with a Perceiver-style architecture on synthetic bag-structured data to solve Multiple Instance Learning (MIL) tasks from a handful of labeled bags at inference time, requiring no gradient updates. The authors evaluate several synthetic data generators and find that a mixture-pretrained model captures complementary inductive biases, outperforming supervised baselines across twelve MIL benchmarks. The work addresses the low-label regime common in domains like computational pathology and satellite imagery.