Edward Grefenstette

Planning in visual world models can be accelerated by $5\times$ by pruning $50\%$ of spatial tokens based on their influence on the planning cost gradient, without sacrificing performance on most control tasks.

LLMs can be taught to proactively seek and effectively use conversational feedback, generalizing across tasks and improving their ability to handle ambiguity.

Forget scaling laws: teaching LLMs to learn from feedback lets smaller models rival giants and generalize to new tasks.