paperarXivTrust 82 · PrimaryPublished 1mo agoLive · 1mo 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).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- LinkedLinked via unknownNew Server Hopes to Break Through AI’s “Memory Wall” →
- LinkedLinked via unknownWould having a dedicated programming language specifically for LLMs be a viable solution? [D] →
- LinkedLinked via unknownIdentifying Interactions at Scale for LLMs →
- LinkedLinked via unknownIEEE Rolls Out Large Language Models Virtual Training Course →
- LinkedLinked via unknownDeepSeek open sources DSpark, a new framework to speed up LLM inference by up to 85% →
- PossiblePossibly related (embedding) · 48%Does intelligence ‘emerge’ in large language models? - Santa Fe Institute →
- PossiblePossibly related (embedding) · 49%sileod/llm-theory-of-mind →
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)
newsDeepSeek open sources DSpark, a new framework to speed up LLM inference by up to 85%newsDoes intelligence ‘emerge’ in large language models? - Santa Fe InstitutenewsThe Large Language Model (LLM) understands the world through human texts. A world model is needed f.. - 매일경제newsAnthropic says it can read Claude's 'thoughts,' as detailed in new research paper — models observed to have a global workspace, revealing more of what makes LLMs tick - Tom's HardwarenewsAI Without Representation Is Just Inequity at Scale: On the Exportation of Unrepresentative Artificial Intelligence Models to the Global South - FrontiersnewsSouth Korea making its own security-centric AI modelnewsDo Large Language Models Think Like Us? - Psychology Today
Implements (incoming)
Related across the graph
newsAnthropic says it can read Claude's 'thoughts,' as detailed in new research paper — models observed to have a global workspace, revealing more of what makes LLMs tick - Tom's HardwarenewsDo Large Language Models Think Like Us? - Psychology TodaynewsThe Large Language Model (LLM) understands the world through human texts. A world model is needed f.. - 매일경제newsDoes 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 routersreposophgo/LLM-TPUnewsSouth Korea making its own security-centric AI modelnewsAI Without Representation Is Just Inequity at Scale: On the Exportation of Unrepresentative Artificial Intelligence Models to the Global South - FrontiersnewsIEEE Rolls Out Large Language Models Virtual Training CourserepoVectorPeak/LLM-Wikireposileod/llm-theory-of-mindrepoXiaohao-Liu/Awesome-Multi-Token-PredictionrepoFuryton/awesome-language-model-analysisnewsIdentifying Interactions at Scale for LLMs