Category
2,329 papers
Operation Waffles proposes a harmless proof-of-concept for studying whether large language models can introduce measurable lexical drift into human language. The paper suggests using an innocuous tracer term—“waffles”—to test whether small model-level preferences for particular words, metaphors, or phrasings survive in...
To compare response accuracy between contemporary large language models (LLMs) and pediatricians across difficulty-stratified pediatric clinical vignettes, characterize LLM response times, and quantify the effect of AI-generated outputs on pediatrician decisions. In a prospective, randomized, assessor-blinded, vignette...
Large language models (LLMs) increasingly support persona adoption and character role-play as a first-class, legitimate usecase; creative writing assistants, companion chatbots, and educational simulations all depend on it. Yet the same mechanism isthe substrate of one of the most persistent jailbreak families in the l...
Knowledge of large language models (LLMs) is frozen in parameters after pretraining and hard to update at low cost. This paper proposes a full-layer memory injection method based on compile-time key-value (KV) caches. Experiments on Qwen3-0.6B show full-layer token-level KV injection raises private-specification QA sco...
Reach audiences
Advertise in front of researchers, engineers, and readers.
This is a source-linked database of all-solid-state battery (ASSB) electrolyte formulations and their reported electrochemical performance, extracted from 1,000 peer-reviewed publications. Every record in the database is traceable to a source DOI and the reporting publication. Content • 2,764 electrolyte-formulation re...
Non-NF2 schwannomatosis (SWN) is a rare syndrome that causes nerve sheath tumors with complex genetic variations and poorly understood modifiers. With no approved pharmacologic interventions, there is an urgent need for treatments that prevent or reduce tumor growth, or that ameliorate schwannoma-associated pain. Many...
This review examines how current systems translate materials questions into computational tasks, identifies the settings in which reliability and recovery have been demonstrated, and explains why runnable calculations should be distinguished from scientifically justified conclusions.
Distressing low sexual desire is the most prevalent sexual dysfunction among women. One treatment option is eSense, an effective digital tool delivering mindfulness-based therapy (MBT). It integrates human “navigators” to support users and, though they improve eSense adherence, may be costly during scale-up. Large lang...
Pegasus AI is developing an AI-driven scientific workflow management system that combines machine learning, large language models, online monitoring, and human guidance to support the workflow lifecycle. It helps scientists create workflows, predict resource requirements, monitor execution, diagnose failures, and adapt...
human vs LLM in adaptive decision making, including four reinforcement learning tasks(one-armed, two-armed bandit tasks, reversal learning task and two-step task)
Large language model (LLM)-based agents are evolving into agents for computer use (ACUs) that read files, invoke applications, communicate over networks, and operate graphical interfaces, moving the effective security boundary from model inputs and outputs to autonomous actions that alter endpoint state. Conventional i...
This paper investigates hallucinations in large language models from the perspective of structured extraction, using prompt-based Semantic Role Labeling (SRL) as a controlled case study. SRL requires exact span boundaries and role assignments, while prompting constrained by rationales exposes the reasoning trace associ...
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.
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.
StudentSim is a research system for evaluating and improving AI tutoring tools before they are tested with learners. It models how individuals may engage with tutors, giving feedback to improve tutor performance across subjects like chess, writing, and mathematics. The post Simulating student learning for better AI tutoring appeared first on Microsoft Research.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
