community
active
leiden_hybrid_concepts
label: sonnet
community:leiden_hybrid_concepts-run2-c128Functional tokens as visual operators
Tokens encode visual operations learned from reasoning context without explicit visual supervision.
2 members. Each node is clickable.
Loading graph…
Drawn from 2 sources
The papers/notes whose extracted claims & findings make up this cluster.
- ATLAS: Agentic or Latent Visual Reasoning? One Word is Enough for Both1 member
- guo-atlas-2026.md1 member
Bridges (3)
Other communities that share members with this one — cross-cutting threads or papers that sit at the seam between two themes.
Claims (2)
- Each functional token is associated with an internalized visual operation, yet requires no visual supervision and remains a standard token in the tokenizer vocabulary.Describes the properties of the functional token.
- Token-level supervision enables models to learn functional-token invocation from reasoning contextATLAS author's assertion that functional tokens optimized via standard cross-entropy loss learn when and how to invoke operations from surrounding text.