Viewing profile — kk58

https://papers.ssrn.com/sol3/papers.cfm?abstract_id=5409063 AI for science is much bigger than RL or Generative AI in science. There are several classes of models Like operator lea…

Im curious I've seen very different results for automation of business processes. Could you share an example of what you're dealing with?

Does this work on mac

What's the angle you're thinking?

Reasoning models aren't really reasoners, its basically neural style transfer protocol where you force a model "decoder" to emit tokens in a style that appears to be Reasoning like…

Curious what's your questions that's really unanswered?

Using LLMs as Optimizers: A new population-based method called LEO that leverages large language models for numerical optimization tasks like nozzle shape and windfarm layout desig…

classic NN takes a vector of data through layers to make a prediction. Backprop adjusts network weights till predictions are right. These network weights form a vector, and trainin…

Very curious, we are getting good results with PiNN and operators, what's your domain?

Doesn't even work. 500 error

LLM are fundamentally stateless. The exoskeleton of agents is essentially a work around to enable a state that resides externally to a LLM. This is required in some manner for crea…

The hallucination may not be a bug but a form regularisation that will helps sample behaviour and that itself might be of great use as it might act as a proxy for focus groups

Interesting what kind of toxic politics and what were the greener pastures for such scientific minds

Great stuff

Honestly the conversation of AI researchers on climate science seems so superficial and removed from reality of climate change. It's like they are trying to solve a drought by capt…

Check out nplan.com use AI for planning

App doesn't work at all

Agree. So attention is like hierarchy of graphs where nodes are tokens and edges are attention scores per head. Now what's trippy is this node has position data. So node feature an…

In CNN the layers seem to learn geometric primitive and deeper layers seem to learn more complex geometric patterns loosely speaking. In transformer what do query key matrices lear…

Doesn't work

Perhaps it's time to call this synthetic intelligence instead of AI which has an implicit understanding of an alternative method to construct a human like AI. What is clear is that…

Try harder the racism feels underpowered

How does your model illustrate specific feature combination for deep learning models - let's say instance segmentation