Signed in
We value your privacy
This site uses cookies to improve your browsing experience, analyze site traffic, and show personalized content.
Welcome to Pump.fun!
Pump lets anyone create coins, giving everyone equal access to buy and sell from the start. Prices can move quickly, so trade carefully.
By clicking this button, you agree to the Terms and Conditions, Privacy Policy, and certify that you are over 18 years old.
We value your privacy
This site uses cookies to improve your browsing experience, analyze site traffic, and show personalized content.
LLMs have revolutionized the field of artificial intelligence and have emerged as the de-facto tool formany tasks, The current established technology of LLMs is to process input and generate output atthe token level. This is in sharp contrast to humans who operate at multiple levels of abstraction, welbeyond single words, to analyze information and to generate creative content. In this paper, we presentan attempt at an architectureon an explicit higher-level semantic representationwhich we name a “concept”. Concepts are language-and modality-agnostic and represent a highetevel idea or action in a fow, Hence, we build a “LARGE CONCEPT MODEL". In this study, asproof of feasibility, we assume that a concept corresponds to a sentence, and use an existing sentenceembedding space, SONAR, which supports up to 200 languages in both text and speech modalities