paperarXivTrust 82 · PrimaryPublished 7d agoLive · 4d ago
From Tokens to States: LLMs as a Special Case of World Models and the Continuous Path Beyond
The AI community has framed the relationship between large language models (LLMs) and world models as a dichotomy: LLMs predict tokens; world models simulate reality. Yann LeCun argues in 2022 that reaching general intelligence requires abandoning autoregressive token prediction in favour of latent-space architectures. This framing is unnecessarily binary. Two claims will be defended. First, LLMs are a degenerate special case of world models: the state space is the set of all token sequences, the only action is appending one token, and world models are therefore a strict generalisation of LLMs
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Covers
newsNew Server Hopes to Break Through AI’s “Memory Wall”newsPrompt injection is exploiting enterprise AI's biggest design flaws by targeting agents, RAG pipelines and model routersnewsWould having a dedicated programming language specifically for LLMs be a viable solution? [D]newsIdentifying Interactions at Scale for LLMsnewsIEEE Rolls Out Large Language Models Virtual Training Course
Covers (incoming)
Implements (incoming)
Related across the graph
newsDoes intelligence ‘emerge’ in large language models? - Santa Fe InstitutenewsDeepSeek open sources DSpark, a new framework to speed up LLM inference by up to 85%newsWould having a dedicated programming language specifically for LLMs be a viable solution? [D]newsNew Server Hopes to Break Through AI’s “Memory Wall”newsPrompt injection is exploiting enterprise AI's biggest design flaws by targeting agents, RAG pipelines and model routersnewsIEEE Rolls Out Large Language Models Virtual Training Coursereposileod/llm-theory-of-mindnewsIdentifying Interactions at Scale for LLMs