AI Networking Cookbook: Practical recipes for AI-assisted network automation and development
We have 12 of 32 papers
We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.
Not the right person? Other researchers publish under this name.
External-memory systems extend language-model applications beyond a context window, but their quality depends critically on the model executing the write path: deciding what to retain, how precisely to represent it, and how new evidence should update persistent state. Existing frameworks typically place a general-purpo...
On-policy distillation (OPD) is increasingly applied to frontier foundation model post-training. Prior work in this area has largely focused on algorithmic advances, yet it remains unclear how much OPD depends on its training questions and, in particular, how far this dependence can be reduced. Across two representativ...
MAS-OPD is presented, where Role-Advantage Specialization defines the role advantage as the difference between the teacher signals under target and non-target role conditions, and Privileged Attribution for Coordination attributes an interaction conflict to its source and supplies it to the teacher alone as privileged...
USA is proposed, which converts per-parameter update magnitudes measured during a brief warm-up into per-coordinate perturbation radii, reducing curvature precisely on the coordinates that carry most of the merging displacement.
RAZOR, a training-free pruning method based on consensus residuals, the deviations of expert outputs from their original weighted mixture, gives the exact output change for a single deletion under survivor renormalization and router refill.
AdvRole is proposed, an adversarial context rewriting framework that turns role-playing RL into a closed-loop curriculum and shows that AdvRole consistently outperforms baselines.
Guided On-Policy Distillation (Guided-OPD), a simple yet effective algorithm that mixes teacher- and student-generated turns within each rollout and schedules the teacher's intervention probability along a curriculum that decays to zero is proposed.
TrustMOPD replaces example-level teacher selection with label-free, token-level supervision allocation and closes the overall-score gap between the initial student and oracle-routed teachers when trained on single- and multi-teacher on-policy distillation.
DF-OPD matches and even surpasses real data, and the questions it produces track the teacher's own post-training data on three key diagnostics of training dynamics, which other real datasets do not.
It is found that effective warm-up relies on teacher-compatible chain-of-thought supervision, and that even incorrect teacher rollouts can provide comparable benefits to correct ones, which suggests that warm-up primarily transfers a teacher-compatible thinking pattern rather than merely correct answers.
NGM-RAG is introduced, a novel framework that leverages graph structures to effectively capture and utilize relational knowledge for improved retrieval and answer generation and proposes a neural graph matching approach that combines text-based matching with Graph Neural Networks (GNNs).
Experiments on reasoning, code-generation, scientific-knowledge, scientific-knowledge, and tool-use benchmarks show that these implementations can be executed through the same verl-based backend while retaining their method-specific objectives and task-dependent performance profiles.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.