concept
active
concept:update-stageUpdate Stage
Second stage of DiffLogic CA where a DLGN computes each cell's new binary state from perception output and current state
Neighborhood — ranked by edge-count
Frameworks (1)
framework
- The novel framework introduced in this paper, combining DLGN and NCA for fully differentiable discrete CA learning
Related by similarity (8)
cosine ≥ 0.65 · no typed edgeEntities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.
- Stage 2 of character training: DPO from teacher model to student model to transfer desired behavioral expressions
- Recursive inference of hidden states and parameters using free energy minimization.
- First stage of DiffLogic CA update where each cell gathers information from neighboring cells via logic gate kernels
- Default update strategy where all cells update simultaneously; contrasted with asynchronous updates
- The perspective that LLM inference decomposes into distinct computational stages, which the paper extends to looped models
- Stage 3 of character training: SFT on synthetic introspective data generated by post-distillation checkpoint
- Update strategy where random subsets of cells are updated per step, simulating independent cell clocks