AI Networking Cookbook: Practical recipes for AI-assisted network automation and development
Category
9,049 papers
Ruby-ASR is presented, which refines the conventional target into a span-bound orthographic--lexical-reading sequence and shows that refining the recognition target can improve lexical-reading recovery without sacrificing readable orthographic transcription.
This work studies whether task-specialist models should be handled by separate task-specialist models or by a single model trained through multi-task training, sequential updates, or model merging, and concludes with practical guidelines for selecting fine-tuning strategies in real-world settings.
ChinaUnicom DataAgent (UniDataAgent) is presented, an ontology grounded system for reusable question-to-report analysis that separates semantic acquisition from online execution and has the potential to be replicated in other enterprises.
A method for distilling sequential computation by replacing spans of input tokens with collapsed representations, computed on the fly by a lightweight merge module, allowing pretrained models to operate on compressed inputs without architectural changes or re-training.
Reach audiences
Advertise in front of researchers, engineers, and readers.
Probabilistic question-answering systems -- whether large language models (LLMs) themselves, retrieval-augmented generation (RAG), or trained multi-hop retrievers -- conflate"what is known"and"how to reason"into a single probabilistic computation: hallucination cannot be eradicated, evidence chains cannot be audited, a...
Hidden diffusion trajectories are established as actionable signals for selective test-time reasoning repair and LOCKR, a hidden-state trajectory-guided planner that decides when to allocate additional computation, expands a structured set of targeted repair branches, and selects the most promising continuation using t...
Text-to-speech systems increasingly process user-generated text (UGT) such as ppl and imo, whose pronunciation must be inferred from the canonical rather than surface form. We introduce UGTPhon, the first grapheme-to-phoneme (G2P) benchmark for UGT in English, Vietnamese, and Korean, together with an inference-grounded...
Evidence that evaluation material entered training does not reveal how much it affected evaluation. This distinction leaves a contaminated benchmark score difficult to interpret: provenance can establish contact, but only a counterfactual can quantify the performance attributable to that contact. We present LeakScale,...
The results show that context representations following the principled approach can reduce reliance on model scale, pointing toward a future of AI systems with frontier-level performance powered by smaller models.
Tempered Evidence Fusion (TEF) is proposed, a training-free rule that weights each sentence's log-odds by its normalized information gain, as derived from a generalized Bayesian posterior, making the fused score nearly vanish for uncertain sentences while preserving the Bayes-optimal weight of decisive evidence.
Results show that out-of-domain generalization remains a major bottleneck and highlight the effectiveness of recent Arabic-specialized speech models, multimodal dialect identification approaches, and ensemble methods.
Post-hoc analyses quantify changes in answers and submitted evidence, and show when aggregate accuracy and evidence-coverage rates miss the claim-level pattern, as well as revealing changes that endpoint and aggregate metrics leave unresolved.
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.
