Category
3,243 papers
This work introduces ActionOPD, an action-level on-policy distillation method motivated by maximizing expected teacher-action likelihood at student-encountered states, and establishes ActionOPD as a promising approach to agent distillation.
This work introduces EXAM, an EXtremist Agent Modeling framework that capable of configuring extremist agents for specific tasks and precisely controlling their population proportion, spatial distribution, interaction protocols, and measurement interfaces.
Vision-language-action policies fine-tuned on LIBERO are trained and evaluated on the same ten instruction strings, and rewording the instruction changes base OpenVLA's success by -38.0 points, although the stronger policies lose a much smaller fraction of it than base OpenVLA.
Functional gastrointestinal disorders, now termed disorders of gut-brain interaction, are heterogeneous conditions shaped by psychological, physiological, microbial, and environmental factors.Diagnosis and treatment remain difficult because symptoms overlap, trajectories fluctuate, and no single objective biomarker exi...
Reach audiences
Advertise in front of researchers, engineers, and readers.
Background Burnout is a common, serious occupational mental-health problem in nursing, and psychological resilience is a modifiable factor that may be associated with lower burnout. Whether this association holds equally across the education-to-practice transition, from interns to registered nurses, is unclear, and the...
Grading programming coursework is challenging work, and sending student work to a commercial API raises privacy problems for a university. We built a grading system that runs entirely locally and tested it on 125 real submissions from six different laboratory exercises for which two instructors had already marked every...
Abstract This pilot study aimed to explore how a specific group of neurodivergent students in the 4th and 5th grades of elementary school represent scientists through drawing. To this end, the Draw-a-Scientist Test (DAST) was administered to 7 neurodivergent children with a diagnosed Autism Spectrum Disorder (ASD) who...
Body appreciation has received a good deal of research attention due to its role in the promotion of well-being and adaptive eating. Prior meta-analytic evidence has pointed to small gender differences in body appreciation (favoring men), but the rapidly expanding literature and growing recognition of gender diversity...
Abstract Annotated text data are central to many empirical applications in political science, yet many annotation tasks involve categories that are sparsely populated. These low- N categories pose problems for both encoder-only and decoder-only (generative) Transformer large language models (LLMs), leading to low perfo...
This teaching companion accompanies Chapter 8, Authorship Attribution in Arabic: From Stylometric Methods to Large Language Models, prepared for the edited volume Arabic Digital Humanities (John Benjamins). It provides an illustrated teaching guide, Python and R scripts, fixed evaluation folds, corpus and excerpt manif...
Machine-learning intrusion detectors reach high average accuracy yet fail consistently on a small set of flows near the decision boundary, where benign and attack traffic overlap in feature space. These errors matter operationally, and standard remedies stop short: adversarial training adds perturbations whose gradient...
Financial institutions want to read the narrative of markets with language models, but much of what matters most — internal research, positions, committee notes, client communications — cannot leave their perimeter. This report describes how Epistemic Symmetry Theory (EST), a framework that detects regime changes in ma...
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.
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
Learn how Google DeepMind and GovTech Singapore uses lightweight on-device Gemma models to intercept conversational scams in private chats with zero cloud data egress.
We’re giving developers, enterprises, scientists, and consumers access to Gemini 4 Argon, our latest frontier model.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
