A BERTology View of LLM Orchestrations: Token- and Layer-Selective Probes for Efficient Single-Pass Classification
Paper
• 2601.13288 • Published
• 14
AI & ML interests
Ingenieria en Inteligencia Artificial
Recent Activity
View all activity
Papers
A BERTology View of LLM Orchestrations: Token- and Layer-Selective Probes for Efficient Single-Pass Classification
Entropy Sentinel: Continuous LLM Accuracy Monitoring from Decoding Entropy Traces in STEM
lucianodelcorro
submitted 2 papers to Daily Papers about 2 months ago
AntonioTepsich
posted an
update over 1 year ago
Post
446
Convolutional KAN - Feedback before send to a journal +700⭐
Repository: https://github.com/AntonioTepsich/Convolutional-KANs
After publishing the Convolutional Kolmogorov-Arnold Networks, we were mentioned by the IEEE Spectrum, congratulated by the universities of Stanford, NorthWestern, Cornell, among others. Surpassing the +700⭐ and the paper was cited more than 12 times. We were presented with the opportunity to submit our idea to a journal to be formalised.
We know that CKANs have their problems due to the amount of computational power and ram memory it uses, but based on what we have what should we do to get a Q1 in a journal?
Paper: https://arxiv.org/pdf/2406.13155
Repository: https://github.com/AntonioTepsich/Convolutional-KANs
After publishing the Convolutional Kolmogorov-Arnold Networks, we were mentioned by the IEEE Spectrum, congratulated by the universities of Stanford, NorthWestern, Cornell, among others. Surpassing the +700⭐ and the paper was cited more than 12 times. We were presented with the opportunity to submit our idea to a journal to be formalised.
We know that CKANs have their problems due to the amount of computational power and ram memory it uses, but based on what we have what should we do to get a Q1 in a journal?
Paper: https://arxiv.org/pdf/2406.13155
AntonioTepsich
authored a paper over 1 year ago