Category
8,685 papers
This property, coherence, is tested with a battery of logically linked questions that needs no labels, and finds that the checks need no labels expose biases that appear only when question forms are compared, and inconsistencies within items.
Constrained-option scoring reads a model's probabilities for a fixed set of permitted answers, so it returns a score even when the model is about to write something else. We study a prompt that quotes a multiple-choice item, ending in the item's own answer instruction, and asks for a forecast of whether a reader model...
This paper introduces MedRouter, an agentic system that uses an embedding-based multi-label router to select and query specialist LLMs, then passes their responses to a generator to produce the final answer, and proposes SCALE (Specialist Competence-Aware Learning), a two-stage training framework.
A recast long-duration ECG interpretation as a long-horizon, online (streaming, causal) sequential decision process and introduces ECG-Scroll, which evaluates a signal-threshold rule agent alongside off-the-shelf LLM agents online, characterizing how they use memory, tools, and planning and where the benchmark's head-r...
Reach audiences
Advertise in front of researchers, engineers, and readers.
SLU encompasses a diverse set of tasks, including ISLR, CSLR, and SLT. Although these tasks share basic semantic and linguistic foundations, they are typically addressed with task-specific architectures and training pipelines, which hinders knowledge sharing and requires costly pretraining and finetuning for each task....
In this work, we consider algorithmic harms that may arise as generative models are incorporated into machine learning platforms. We argue that existing harm taxonomies and threat models require extension to (1) address novel causal drivers of well-studied representational and quality-of-service harms; and (2) anticipa...
DAST (Diversifying Arithmetic Sampling with TokenTour), a method that increases the diversity of LLM outputs without any change to the marginal distribution and with negligible generation-time overhead, and significantly improves performance on the downstream task of ProtoQA.
TCMQA, an open benchmark of 38,279 questions from Chinese TCM licensing examinations, paired with 15,151 responses from 101 licensed practitioners, is presented, and 29 instruction-tuned models from 9 families are evaluated, finding difficulty does not transfer between models and practitioners.
DynamicDx evaluates each step in 71 neurological consultations across 11 sign categories, linking authentic patient videos to confirmed diagnoses and fixed charts built from the same case reports, so that every model queries the same evidence.
It is shown that general-purpose multimodal LLMs, without being trained as pathology foundation models, consistently outperform these specialized models in cross-domain histological similarity judgments, exposing a fundamental robustness gap in current pathology foundation models.
Large vision-language models (LVLMs) inherit massive activations from their text-only bases: spikes where a few fixed hidden channels receive values thousands of times above the typical magnitude. The text spike systematically appears in early layers at a fixed initial position, independently of input content. Visual s...
A separate survey comparison finds that selecting the more responsive checkpoint can worsen human fit; responsiveness is confounded with training status, and temperature calibration largely removes this cost but not errors in group ordering.
Flint-interactive gives AI agents a language for creating interactive visualizations. Click a chart, filter data, highlight related content, and explore beyond the view the author originally chose. The post Flint-interactive: A language for creating interactive data visualizations appeared first on Microsoft Research.
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
A new computational approach reveals how cells communicate to assemble into tissues. This could accelerate stem cell engineering, improve disease models, and inform therapies.
Zero-knowledge proofs can verify computing results without rerunning workloads or exposing sensitive data. Magnetar helps bring them into the mainstream with support for standard programming languages, major speed gains, and quantum-resistant security. The post Proof-based general-purpose computing with Magnetar appeared first on Microsoft Research.
A new language-processing tool could help identify the highest-risk individuals from natural language, enabling swifter interventions.
A Blog post by Liquid AI on Hugging Face
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
