Artificial Intelligence Medical Compendium

Explore the latest research on artificial intelligence and machine learning in medicine.

Showing 30,271 to 30,280 of 220,100 articles

AnimationBench: Are Video Models Good at Character-Centric Animation?

arXiv
Video generation has advanced rapidly, with recent methods producing increasingly convincing animated results. However, existing benchmarks-largely designed for realistic videos-struggle to evaluate animation-style generation with its stylized appear... read more 

MM-WebAgent: A Hierarchical Multimodal Web Agent for Webpage Generation

arXiv
The rapid progress of Artificial Intelligence Generated Content (AIGC) tools enables images, videos, and visualizations to be created on demand for webpage design, offering a flexible and increasingly adopted paradigm for modern UI/UX. However, direc... read more 

TokenLight: Precise Lighting Control in Images using Attribute Tokens

arXiv
This paper presents a method for image relighting that enables precise and continuous control over multiple illumination attributes in a photograph. We formulate relighting as a conditional image generation task and introduce attribute tokens to enco... read more 

TokenLight: Precise Lighting Control in Images using Attribute Tokens

arXiv
This paper presents a method for image relighting that enables precise and continuous control over multiple illumination attributes in a photograph. We formulate relighting as a conditional image generation task and introduce attribute tokens to enco... read more 

LeapAlign: Post-Training Flow Matching Models at Any Generation Step by Building Two-Step Trajectories

arXiv
This paper focuses on the alignment of flow matching models with human preferences. A promising way is fine-tuning by directly backpropagating reward gradients through the differentiable generation process of flow matching. However, backpropagating t... read more 

(1D) Ordered Tokens Enable Efficient Test-Time Search

arXiv
Tokenization is a key component of autoregressive (AR) generative models, converting raw data into more manageable units for modeling. Commonly, tokens describe local information, such as regions of pixels in images or word pieces in text, and AR gen... read more 

RelativeFlow: Taming Medical Image Denoising Learning with Noisy Reference

arXiv
Medical image denoising (MID) lacks absolutely clean images for supervision, leading to a noisy reference problem that fundamentally limits denoising performance. Existing simulated-supervised discriminative learning (SimSDL) and simulated-supervised... read more 

$π_{0.7}$: a Steerable Generalist Robotic Foundation Model with Emergent Capabilities

arXiv
We present a new robotic foundation model, called $π_{0.7}$, that can enable strong out-of-the-box performance in a wide range of scenarios. $π_{0.7}$ can follow diverse language instructions in unseen environments, including multi-stage tasks with v... read more 

ProtoTTA: Prototype-Guided Test-Time Adaptation

arXiv
Deep networks that rely on prototypes-interpretable representations that can be related to the model input-have gained significant attention for balancing high accuracy with inherent interpretability, which makes them suitable for critical domains su... read more 

Brain Score Tracks Shared Properties of Languages: Evidence from Many Natural Languages and Structured Sequences

arXiv
Recent breakthroughs in language models (LMs) using neural networks have raised the question: how similar are these models' processing to human language processing? Results using a framework called Brain Score (BS) -- predicting fMRI activations duri... read more