AI Networking Cookbook: Practical recipes for AI-assisted network automation and development
Category
9,261 papers
Linear probing and activation steering use linear directions to predict and control behavior-level concepts such as correctness, safety, and social bias in question answering. We call these \emph{behavior-level concept directions}. Drawing on the Linear Representation Hypothesis (LRH) and circuit studies, these directi...
Voice provides a natural and immediate interface for AI agents. Many settings in which voice agents could be useful, including meetings, households, and collaborative work, are inherently multi-speaker. Supporting these settings introduces challenges that are largely absent from one-on-one interaction. We introduce the...
The objective is to preserve the full-precision model's answer-supporting behavior rather than improve gold-label accuracy, and the method better preserves the full-precision model's answer behavior and rationale-to-answer support.
This work integrates tree-structured speculative decoding into the DeepSeek-V4-Flash pipeline via branch-aware causal verification, temporary state isolation, and accepted-path state refresh, keeping verification and compressed-state updates consistent across branches.
Reach audiences
Advertise in front of researchers, engineers, and readers.
A systematic benchmark of diverse open-source LLMs for multilingual readability assessment is conducted, focusing on the prediction of discrete readability levels required by educational frameworks, to establish the viability of out-of-the-box LLMs as robust, cross-lingual readability assessors.
It is found that across Llama-3.1-8B and Mistral-7B, operation-span transplants causally redirect which visible state is read even when the two worlds hold identical values, revealing a routing record.
The results suggest that decision models are useful as a first step in the annotation pipeline: routing low-confidence items to an LLM matches or exceeds the LLM alone at a quarter to half of its cost.
An operation-based view that evaluates mathematical frameworks by the conceptual operations they support is proposed, identifying thirteen operations (including similarity, composition, generalization, and grounding) that recur across cognition, psychology, and AI.
QLoRA-fine-tuned compact LLMs can generate curator-style annotations with genuine biological value for a substantial subset of proteins, and is concluded that QLoRA-fine-tuned compact LLMs can generate curator-style annotations with genuine biological value for a substantial subset of proteins.
LLJ Cards is introduced, a framework that synthesizes best practices from measurement theory, natural language generation, and machine learning literature into practical guidelines for LLJ-based evaluations and provides a structured framework for applying these principles in the design and reporting of automated evalua...
Speech-to-text engines are extremely needed nowadays for different applications, representing an essential enabler in human-robot interaction. Still, some languages suffer from the lack of labeled speech data, especially in the Arabic dialects or any low-resource languages. The need for a self-supervised training proce...
A novel unified retrieval-augmented framework, URA-NER, including three key components: Progressive Granularity Retrieval, Model-aware Representation Enhancement, and Reason-aware Knowledge Verification is proposed, including three key components: Progressive Granularity Retrieval, Model-aware Representation Enhancemen...
A Blog post by Ai2 on Hugging Face
A Blog post by IBM Research on Hugging Face
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.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
