AI Networking Cookbook: Practical recipes for AI-assisted network automation and development
We have 5 of 16 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.
Spatio-temporal video grounding (STVG) aims to localize objects or events described by natural language queries in both space and time. Existing STVG models are typically trained and evaluated under the assumption that each query is relevant to the input video. In this work, we challenge this assumption by studying the...
Pocket-STVG is presented, a lightweight cascade architecture that addresses STVG by combining efficient pre-trained components instead of large end-to-end models and establishing a favorable performance-efficiency trade-off for STVG.
A controlled study on the example of bViT model applying one weight-tied block $L$ times, which achieves accuracy parity with ViT on 12-lead electrocardiogram (ECG) classification tasks from the PTB-XL dataset under identical training protocols.
It is found that standard ViTs remain preferable when FLOPs are the primary constraint, whereas recurrent ViTs offer a better accuracy--parameter trade-off under memory constraints, whereas naive recurrence collapses to near-random performance.
This work proposes a hierarchical Mixture-of-Experts (HMoE) Transformer that processes INR weights using conditional computation aligned with the structure of the underlying implicit network and develops weight-space attribution and pruning methods that identify parameters most relevant for classification.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.