Category
20,518 papers
A fundamental bottleneck for translating thoughts to speech is the high physical cost of motor input forcing a strict tradeoff between communication speed and expressivity. Generative AI offers a promising solution by expanding highly abbreviated text input into fluent sentences, significantly reducing the motor burden...
Reliability--Uncertainty Self-Distillation weights each attempt's distillation loss by additively combining judged reliability, estimated from a self-judge's score and confidence, with student predictive uncertainty.
Clinical note generation from doctor--patient dialogue is high-volume and hallucination-intolerant: a fabricated laboratory value can create patient-safety risk, not a quality regression. We ask whether an agentic \emph{verification} architecture, rather than generator scale, can make a small language model viable here...
LLM agents are becoming increasingly capable of handling daily workspace tasks by interacting with application environments through tool calls. However, as agents read and write sensitive user data across email, documents, and other applications, a central privacy question is whether they preserve contextual integrity...
Reach audiences
Advertise in front of researchers, engineers, and readers.
In procedural tool-use domains, how much of the gap between base models is procedure rather than capability? We build an explicit program from a teacher's traces and run it in front of unchanged small models, including an 8B model. The construction, PLVR , takes the reasoning traces of a teacher, Kimi-K3, clusters thei...
We present a graph-based framework for Composite AI systems that integrate multiple AI techniques to address complex problems. We describe an architecture using specialized control nodes to orchestrate diverse models including planning, machine learning, constraint programming, and large language models. The system emp...
Tool-augmented LLM agents discover relevant APIs from large registries before planning execution, yet finite context windows prohibit injecting all tool definitions into a single prompt. The dominant approach, which we term Retrieve-then-Plan (RtP), embeds the user query and retrieves similar tools via approximate near...
Prompting is a widely used method for adapting general-purpose LLMs to domain-specific tasks. Effective prompts can be tedious to create manually, so prompt writing is increasingly handed to LLMs, with recent work training LLMs to write prompts for other models. These techniques either write prompts without observing h...
LLM agent frameworks heavily rely on external skill assets to standardize tool usage, encode operational workflows, and supply executable runtime resources. Despite their widespread adoption, multi-component skill packages frequently suffer from cross-artifact inconsistencies, where documentation, scripts, and configur...
Due to their complex and multifaceted character, liver diseases represent a huge global health burden and contribute considerably to morbidity and mortality globally. Although the liver is essential for detoxification, protein synthesis, metabolic equilibrium, and biochemical regulation, it is extremely vulnerable to d...
Microbial infections continue to pose a significant global health challenge due to the increasing prevalence of antimicrobial resistance (AMR), multidrug-resistant (MDR) pathogens, and the limited effectiveness of conventional antimicrobial therapies. Traditional antimicrobial agents often suffer from poor aqueous solu...
Genotoxic impurities (GTIs) are trace-level contaminants capable of damaging DNA and increasing the potential for mutation and carcinogenesis. They may arise from starting materials, reagents, catalysts, intermediates, by-products, degradation pathways, manufacturing operations, or packaging interactions. Their control...
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
