AI Networking Cookbook: Practical recipes for AI-assisted network automation and development
Category
3,130 papers
Simulated students let researchers test tutoring systems and teaching strategies before real learners are available, but only if the simulation reproduces where a particular learner succeeds and fails. The common approach asks a large language model to role-play a student, but a role does not model what this learner kn...
Latent reasoning replaces natural-language chains of thought with compact continuous"soft-token"representations, reducing the number of intermediate tokens that must be decoded autoregressively. We use a small external encoder to induce latent reasoning in a frozen backbone model. The encoder iteratively maps the backb...
Layer-ablation studies often perturb early or late layers of a language model, compare the damage to prediction on two corpora, and read a larger early-layer effect on one corpus as early-layer specialization for its task. Such a comparison averages over the tokens that each corpus asks the model to predict, and these...
Large language model agents increasingly improve by distilling experience into reusable skills, but errors in that experience can persist in learned rules and affect later tasks. Existing evaluations largely examine clean learning or perturbations encountered after skills are frozen, leaving robustness during self-evol...
Reach audiences
Advertise in front of researchers, engineers, and readers.
While LLM-based agent systems have demonstrated remarkable proficiency in reasoning and solving complex real-world tasks, they also come with substantial token consumption and inference latency, limiting their practical deployment. To enhance the efficiency of agent systems, recent efforts have focused on transferring...
This work derives an explicitly computable sufficient disturbance budget under which the clearance guarantee degrades gracefully, and proves that the clearance margin is never violated and that the prescribed clearance is restored exponentially, yielding an explicit clearance floor.
We continue the study of beautiful pairs of henselian valued fields, initiated in joint work of the second author with Cubides Kovacsics and Ye. As our main result, we show that separably closed non-trivially valued fields of arbitrary imperfection degree admit beautiful pairs which are elementary pairs satisfying cert...
This work proposes FrameLite, a compact cropping model built on Qwen3, which outperforms the compared large-VLM croppers across public benchmarks with a substantially smaller backbone and develops three-stage training to turn this potential into stronger direct predictions.
The Multi-Hypothesis Verification Framework (MHVF) is proposed for training-free GUI grounding that combines multi-hypothesis exploration with local visual verification using a single pretrained vision-language model.
RepProbe, a benchmark of 42K real and synthetic video clips containing exactly k in [1, 20] complete repetitions, finds a consistent representation-to-output dissociation: substantial count information remains linearly decodable even when models fail to report the correct count.
Chronic pain management requires complex multidisciplinary reasoning integrating pharmacological, interventional, rehabilitative, and psychosocial approaches across multiple guideline frameworks (International Association for the Study of Pain [IASP], American College of Rheumatology [ACR], European Alliance of Associa...
Mark Feng Teng incorporates authentic materials into his academic writing classes in Macao to expose students to real-life language use and designs tasks to develop communicative skills. He structures lessons into three phases: teacher’s time, when he models academic skills that students will use later; learners’ time,...
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.
Learn how Google DeepMind and GovTech Singapore uses lightweight on-device Gemma models to intercept conversational scams in private chats with zero cloud data egress.
StudentSim is a research system for evaluating and improving AI tutoring tools before they are tested with learners. It models how individuals may engage with tutors, giving feedback to improve tutor performance across subjects like chess, writing, and mathematics. The post Simulating student learning for better AI tutoring 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.