AI Networking Cookbook: Practical recipes for AI-assisted network automation and development
We have 9 of 19 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.
Context-management techniques such as summarization and selective retrieval may help reduce energy consumption in agent deployments, and suggest that context-management techniques such as summarization and selective retrieval may help reduce energy consumption in agent deployments.
Results show that proxy-based empirical gain achieves strong ranking agreement with proxy-defined realized utility and substantially outperforms row-count and token-count baselines in the tested setting, while the prototype provides a controlled sanity check of the valuation pipeline and its sensitivity to duplication-...
World Action Models (WAMs) enable future-aware control by jointly modeling actions and environment dynamics. However, iterative diffusion or flow inference incurs substantial denoising latency. Prior inference state offers a natural opportunity for acceleration, yet changing planning contexts, observations, and interme...
AtomWorld-Mem is introduced, a memory-restored atomistic world model that recovers the latent world state missing from instantaneous crystal snapshots and improves long-horizon atomistic progress under fixed microscopic event budgets while maintaining high-fidelity evolution across energetic, structural, and vacancy-tr...
Zeva-Ego is introduced, a unified framework that learns physical priors from human experience and evolves through robot interaction and demonstrates a scalable path toward embodied intelligence that learns from human experience and continuously improves through its own interaction.
Zeva is presented, the first framework that enables in-context learning from a robot's own physical interaction experience while keeping the policy model frozen, and achieves the best performance among the compared frontier VLAs and WAMs and enables self-evolution during deployment without gradient updates.
Zetta is presented, a closed-loop embodied harness that evolves code-based runtime critics and recovery skills online while keeping the base policy frozen, and shows that closed-loop harness self-evolution opens a scaling path for reliable physical intelligence.
Token skipping is a widely used training-free way to accelerate vision--language--action (VLA) models by bypassing computation for most visual tokens at each control step according to a gate. When the next gate is harvested from the previous accelerated forward, however, the tokens skipped at one step are also the ones...
The results show that token attribution is not a reliable proxy for marginal energy under batched execution, and that measured Shapley ground truth can calibrate low-cost request features toward fairer attribution.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.