AI Networking Cookbook: Practical recipes for AI-assisted network automation and development
Category
3,445 papers
This work introduces BOTTLED, a benchmark in which agents receive an entire unlabelled workload and must complete it under fixed time, compute and LLM API budgets, and finds that strong zero-shot task performance does not reliably translate into strong bottling capabilities.
This study evaluates the performance of lightweight open-source language models to resolve an input data entity against its corresponding best fitting SDM representation under resource-constrained conditions and provides significant and valuable insights into model selection, task formulation, and deployment strategies...
System-level results provide system-level evidence that deployment-time safety depends not only on the capability of individual guardrails, but also on how their decisions are organized and coordinated.
DynaCore is presented, a unified architecture for efficient LLM serving via system-architecture co-design that substantially reduces service-level latency over quantization and reconfigurable accelerators, and proposes disaggregated quantization, applying dual-side quantization to prefill and weight-only quantization t...
Reach audiences
Advertise in front of researchers, engineers, and readers.
This work presents HarnessSecurity, the first systematic empirical study and benchmark of open- and closed-source coding agent harnesses, and derives a ten-mechanism taxonomy and assesses 400 harness-mechanism cells using independent ratings by researchers and large language model judges.
This paper finds that the emergence of massive activations is controlled by a single channel in the input embedding to a spike feed-forward network (FFN), and names this channel the massive activation gating channel (MAGC).
This case study documents a CRA preparedness pilot for one such product, SEUXDR, an AI-augmented security monitoring product with a large-language-model active-response component on the open-source CYBERFORT platform, and offers practitioners a replicable starting point for translating CRA legal text into operational p...
SCSM constructs pairs of pretraining views from the same group of unlabeled traces through Segmentation, Combination, Scaling, and Masking, which produces diverse observable patterns while preserving the underlying packet events and local traffic dynamics of real trace fragments.
IndexAct is proposed, an interface for Index-Native Corpus Interaction that separates candidate-set refinement from text inspection, and achieves higher evidence coverage with a smaller average live context than terminal-based corpus interfaces, and maintains answer accuracy as the corpus expands.
BARE-AI, a runtime framework that detects, localizes, and mitigates BFAs during inference, and introduces AI Performance Counters, lightweight hardware monitors in the accelerator datapath that capture per-layer activation statistics such as sparsity, entropy, kurtosis, and spectral shift.
Large Language Models (LLMs) have disrupted the balance between content production and quality assurance that sustains knowledge commons, leading many to prohibit or restrict their use. But what happens when a community instead appropriates an LLM-powered tool for its own needs? We investigate this question through Wik...
Fine-grained emotion recognition supports therapy tools and social robots, but it needs facial data, which raises privacy and data-protection concerns. EmoNet-Face-HQ answers that with generated portraits, expert-rated over a $40$-category taxonomy far finer than the usual six to eight basic emotions. Under the protoco...
A Blog post by IBM Granite on Hugging Face
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
Gemini 4 Carbon is our strongest model with state-of-the-art cybersecurity and long horizon capabilities.
A Blog post by Liquid AI on Hugging Face
Genie 4: our new world model unlocking unprecedented realism in real-time simulation.
Generative AI
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
