🛰️ Daily AI Frontier
‹ back to 2026-08-23

Nothing Changed but the Model: CellFill -- Bounded In-Cell Learning for Bit-Identical, Revocable Updates to Quantized LLMs

Research LLMs & Foundation Models

Ranking

Overall 82
Content 100
Popularity 41

Observed public metrics from 1 member.

Merged summary

TL;DR - CellFill updates quantized LLMs by learning bounded residuals within each weight’s quantization cell, leaving the released 4-bit checkpoint bit-identical after re-quantization. This enables verifiable, exactly revocable knowledge updates while limiting model drift and cross-domain forgetting.

  • The integer codes and scales remain frozen; removing the learned residual fully revokes an update.
  • Constrained dense training nearly matched unconstrained fact recall across paired seeds: 58.9% versus 59.3%, a -0.5-point paired difference with 95% CI [-5.0, +4.0].
  • Cell projection reduced cross-domain forgetting relative to unmerged adapters in every converged run, acting as a trust region rather than fixing unstable training.
  • The method scaled to a 27B hybrid linear-attention model with 24 billion constrained weights and verified bit-identical re-quantization.

Sources (1)

Nothing Changed but the Model: CellFill -- Bounded In-Cell Learning for Bit-Identical, Revocable Updates to Quantized LLMs

arXiv cs.LG Zifeng Liu, Zhiyong Du, Yaxin Lu, Yiming Mao, Zhenhe Wang, Wenqi Shi, Zhengkun Jing 2026-08-21 arXiv:2608.20873
Public signals Semantic Scholar citations 0 · Semantic Scholar influential citations 0
Providers: Hugging Face · N/A OpenAlex · N/A Publisher · N/A Semantic Scholar · Citations 0 · Influential citations 0 X · N/A Fetched 2026-09-12 14:21:56.709244 UTC

TL;DR - CellFill updates quantized LLMs by learning bounded residuals within each weight’s quantization cell, leaving the released 4-bit checkpoint bit-identical after re-quantization. This enables verifiable, exactly revocable knowledge updates while limiting model drift and cross-domain forgetting.

  • The integer codes and scales remain frozen; removing the learned residual fully revokes an update.
  • Constrained dense training nearly matched unconstrained fact recall across paired seeds: 58.9% versus 59.3%, a -0.5-point paired difference with 95% CI [-5.0, +4.0].
  • Cell projection reduced cross-domain forgetting relative to unmerged adapters in every converged run, acting as a trust region rather than fixing unstable training.
  • The method scaled to a 27B hybrid linear-attention model with 24 billion constrained weights and verified bit-identical re-quantization.
item →