Explore Your Brain

M 1.1 - 6 km NW of The Geysers, CA

M 1.05 near 6 km NW of The Geysers, CA. Updated from USGS real-time earthquake feed.

M 0.7 - 7 km W of Cobb, CA

M 0.71 near 7 km W of Cobb, CA. Updated from USGS real-time earthquake feed.

M 2.0 - 41 km WSW of Anchor Point, Alaska

M 2 near 41 km WSW of Anchor Point, Alaska. Updated from USGS real-time earthquake feed.

M 1.9 - 47 km ESE of Beatty, Nevada

M 1.89 near 47 km ESE of Beatty, Nevada. Updated from USGS real-time earthquake feed.

M 1.7 - 20 km N of Pāhala, Hawaii

M 1.71 near 20 km N of Pāhala, Hawaii. Updated from USGS real-time earthquake feed.

M 4.7 - 119 km W of Ternate, Indonesia

M 4.7 near 119 km W of Ternate, Indonesia. Updated from USGS real-time earthquake feed.

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

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 f...

Generalization in LLM Problem Solving: The Case of the Shortest Path

Whether language models can systematically generalize remains actively debated. Yet empirical performance is jointly shaped by multiple factors such as training data, training paradigms, and inference-time strategies, m...

Diagnosing LLM Judge Reliability: Conformal Prediction Sets and Transitivity Violations

LLM-as-judge frameworks are increasingly used for automatic NLG evaluation, yet their per-instance reliability remains poorly understood. We present a two-pronged diagnostic toolkit applied to SummEval: $\textbf{(1)}$ a...

How Do LLMs and VLMs Understand Viewpoint Rotation Without Vision? An Interpretability Study

Over the past year, spatial intelligence has drawn increasing attention. Many prior works study it from the perspective of visual-spatial intelligence, where models have access to visuospatial information from visual in...

AD4AD: Benchmarking Visual Anomaly Detection Models for Safer Autonomous Driving

The reliability of a machine vision system for autonomous driving depends heavily on its training data distribution. When a vehicle encounters significantly different conditions, such as atypical obstacles, its perceptu...

Why Do Vision Language Models Struggle To Recognize Human Emotions?

Understanding emotions is a fundamental ability for intelligent systems to be able to interact with humans. Vision-language models (VLMs) have made tremendous progress in the last few years for many visual tasks, potent...

Prism: Symbolic Superoptimization of Tensor Programs

This paper presents Prism, the first symbolic superoptimizer for tensor programs. The key idea is sGraph, a symbolic, hierarchical representation that compactly encodes large classes of tensor programs by symbolically r...

SegWithU: Uncertainty as Perturbation Energy for Single-Forward-Pass Risk-Aware Medical Image Segmentation

Reliable uncertainty estimation is critical for medical image segmentation, where automated contours feed downstream quantification and clinical decision support. Many strong uncertainty methods require repeated inferen...