Aggressive compression of recursive reasoners keeps local predictions intact but destroys global reasoning accuracy, recoverable with calibrated INT4 and detectable via carry-trajectory fidelity.
arXiv preprint arXiv:2601.14888 , year=
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.LG 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
ReSET mitigates accuracy degradation in NVFP4-quantized reasoning models via step-aware entropy-based temperature scaling and provides a small-M CUDA kernel for up to 2.5x kernel speedup and 2x end-to-end speedup.
citing papers explorer
-
What Survives When You Compress a Recursive Reasoner for the Edge?
Aggressive compression of recursive reasoners keeps local predictions intact but destroys global reasoning accuracy, recoverable with calibrated INT4 and detectable via carry-trajectory fidelity.
-
ReSET: Accurate Latency-Critical NVFP4 Reasoning via Step-Aware Temperature Scaling
ReSET mitigates accuracy degradation in NVFP4-quantized reasoning models via step-aware entropy-based temperature scaling and provides a small-M CUDA kernel for up to 2.5x kernel speedup and 2x end-to-end speedup.