MindEye2: Shared-Subject Models Enable fMRI-to-Image with 1 Hour of Data (arxiv.org) | HN Screenshots

YHacker Newsscreenshots

Screenshot of arxiv.org: MindEye2: Shared-Subject Models Enable fMRI-to-Image with 1 Hour of Data

First screen, captured 2 years ago.

Looks similar

Screenshot of arxiv.org: Image Diffusion Models Exhibit Emergent Temporal Propagation in Videos

Image Diffusion Models Exhibit Emergent Temporal Propagation in Videos (arxiv.org)

111 points by 50kIters 11 months ago | 15 comments

Screenshot of arxiv.org: V*: Guided Visual Search as a Core Mechanism in Multimodal LLMs

V*: Guided Visual Search as a Core Mechanism in Multimodal LLMs (arxiv.org)

48 points by jonbaer 2 years ago | 3 comments

Screenshot of arxiv.org: NeRF-Supervised Feature Point Detection and Description

NeRF-Supervised Feature Point Detection and Description (arxiv.org)

43 points by QuantumWeb 2 years ago | 1 comments

Screenshot of arxiv.org: Ultralytics YOLO26: Unified Real-Time End-to-End Vision Models

Ultralytics YOLO26: Unified Real-Time End-to-End Vision Models (arxiv.org)

49 points by teleforce 4 months ago | 8 comments

Screenshot of arxiv.org: MM1: Methods, Analysis and Insights from Multimodal LLM Pre-training

MM1: Methods, Analysis and Insights from Multimodal LLM Pre-training (arxiv.org)

142 points by lord_sudo 2 years ago | 58 comments

Screenshot of arxiv.org: Apple MM1: Methods, Analysis and Insights from Multimodal LLM Pre-Training

Apple MM1: Methods, Analysis and Insights from Multimodal LLM Pre-Training (arxiv.org)

41 points by Anon84 2 years ago | 1 comments