Per-tensor 4-bit quantization of weight-tied recursive reasoners induces accumulating activation bias that kills accuracy; per-block scaling (MXInt4) restores it.
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing , pages =
1 Pith paper cite this work, alongside 12 external citations. Polarity classification is still indexing.
1
Pith paper citing it
12
external citations · OpenAlex
fields
cs.LG 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Quantizing Recursive Reasoning Models
Per-tensor 4-bit quantization of weight-tied recursive reasoners induces accumulating activation bias that kills accuracy; per-block scaling (MXInt4) restores it.