Deep Learning
Mass-Producing Failures of Multimodal Systems with Language Models Shengbang Tong Erik Jones
Deployed multimodal systems can fail in ways that evaluators did not anticipate.
Practical Equivariances via Relational Conditional Neural Processes Daolang Huang 1 Manuel Haussmann
However, prior attempts to include equivariances in CNPs do not scale effectively beyond two input dimensions.
Hierarchical Integration Diffusion Model for Realistic Image Deblurring Zheng Chen
Diffusion models (DMs) have recently been introduced in image deblurring and exhibited promising performance, particularly in terms of details reconstruction.
This Startup Wants to Spark a US DeepSeek Moment
With the US falling behind on open source models, one startup has a bold idea for democratizing AI: let anyone run reinforcement learning. Ever since DeepSeek burst onto the scene in January, momentum has grown around open source Chinese artificial intelligence models. Some researchers are pushing for an even more open approach to building AI that allows model-making to be distributed across the globe. Prime Intellect, a startup specializing in decentralized AI, is currently training a frontier large language model, called INTELLECT-3, using a new kind of distributed reinforcement learning for fine-tuning. The model will demonstrate a new way to build competitive open AI models using a range of hardware in different locations in a way that does not rely on big tech companies, says Vincent Weisser, the company's CEO.
TempME: Towards the Explainability of Temporal Graph Neural Networks via Motif Discovery
Temporal graphs are widely used to model dynamic systems with time-varying interactions.
Table of Contents 307 A PDE Symmetry Groups and Deriving Generators 2 308
Grids, groups, graphs, geodesics, and gauges.
Performance-optimized deep neural networks are evolving into worse models of inferotemporal visual cortex
One of the most impactful findings in computational neuroscience over the past decade is that the object recognition accuracy of deep neural networks (DNNs) correlates with their ability to predict neural responses to natural images in the inferotemporal (IT) cortex [1, 2].