AI Networking Cookbook: Practical recipes for AI-assisted network automation and development
Category
9,261 papers
It is shown that observed inconsistencies cannot be explained by a single ordering under any monotone link function, and a noise-augmented mixture Bradley-Terry model is introduced that infers latent preference components from repeated pairwise comparisons, suggesting that LLMs reflect plural preferences.
KV-cache eviction can do more than compress. In long-context LLMs, keeping only some cached tokens sometimes matches or exceeds full-cache accuracy, because many redundant prefill tokens otherwise dilute attention away from the tokens that carry the answer. This benefit is not uniform, and evicting the wrong tokens can...
It is found that removing the diagonal component usually preserves most of the gains from post-training, suggesting that post-training gains are carried primarily by reconfiguring and extending pretrained pathways rather than by substantially changing singular values of pre-trained models.
ITS is proposed, a query-efficient framework that uses an attention-derived pairwise dependency proxy to approximate the CMI-aware selection criterion and incorporates a diversity-promoting strategy to improve token coverage across sampling rounds, yielding aggregated token-wise signals that are less affected by depend...
Reach audiences
Advertise in front of researchers, engineers, and readers.
Test-time self-evolving agents improve by reusing past experience, yet sparse-reward trajectories contain failures, loops, and detours, while summaries often omit the state conditions and action dependencies needed for execution. We study executable Walkthrough induction from sparse-reward trajectories: extracting comp...
The Fusion Anything Model (FAM) is proposed, a foundation model for generalized multimodal data fusion that encodes transferable multimodal correlations during training and activates appropriate associations through in-context examples during inference.
The digital transformation of the Dutch labour market is reshaping occupational language, career pathways, and job-related skills. Addressing these changes requires granular labour market intelligence. This paper develops an AI-based methodology to analyse digitalisation using data covering millions of Dutch job profil...
This paper evaluates Wiktionary as an ethically crowdsourced lexicon for English dialects. We took a two-phase approach, providing an in-depth descriptive analysis of the crowdsourced lexicon for 12 national varieties of English before applying the lexicon to geo-referenced, country-level social media language data to...
MEMPROBE is the first benchmark to study memory recovery directly, reconstructing the user state a system retains and scoring it against ground truth, and is seen as a step toward an environment where agents are trained to remember their users, growing more faithful the longer they know them.
Draft-OPD, which uses target-assisted rollout for stable continuations and replays drafting from the verification-exposed error positions, allowing the drafter to learn from target feedback on both accepted and rejected proposals, focusing on the draft-induced errors that limit speculative acceptance.
Sometin Beta Pass Notin is introduced, a multilingual foundational ASR model that covers Yor\`ub\'a, Hausa, Igbo, Nigerian Pidgin, and Nigerian English, and outperform state-of-the-art multilingual models across major benchmarks, including Common Voice and FLEURS.
Whether a judge returns the same verdict when the same request is worded differently remains largely unexamined, so decoding noise is not charged to wording, and the release lets a reader ask the same of any judge not in the roster.
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.
