Functional near-infrared spectroscopy (fNIRS) and diffuse optical tomography (DOT) are rapidly evolving toward wearable, multimodal, and data-driven, AI-support...
On December 4, 2025, Anthropic released Anthropic Interviewer, an AI tool for running qualitative interviews at scale, along with a public dataset of 1,250 inte...
We release Pantagruel models, a new family of self-supervised encoder models for French text and speech. Instead of predicting modality-tailored targets such as...
As machine learning models become increasingly embedded in societal infrastructure, auditing them for bias is of growing importance. However, in real-world depl...
As Large Language Models (LLMs) are increasingly deployed in real-world settings, correctness alone is insufficient. Reliable deployment requires maintaining tr...
Large language model (LLM) routing aims to exploit the specialized strengths of different LLMs for diverse tasks. However, existing approaches typically focus o...
Preference tuning aligns pretrained language models to human judgments of quality, helpfulness, or safety by optimizing over explicit preference signals rather ...
Recent deepfake detection methods have increasingly explored frequency domain representations to reveal manipulation artifacts that are difficult to detect in t...
Semi-supervised medical image segmentation is an effective method for addressing scenarios with limited labeled data. Existing methods mainly rely on frameworks...
We propose a novel framework for decomposing arbitrarily posed humans into animatable multi-layered 3D human avatars, separating the body and garments. Conventi...
Turning Retail’s “That Was Easy” Moments into Reality Every “that was easy” shopping experience is powered by teams racing against shipping deadlines, fixing m...
We introduce AutoMonitor-Bench, the first benchmark designed to systematically evaluate the reliability of LLM-based misbehavior monitors across diverse tasks a...
