LSQ (LLM quantization): superseded — cited as a baseline and beaten by newer methods. 0 paper(s) critique it, 2 beat it on benchmarks — #31 of 80 most-superseded. Sub-problem: cluster led by PACT. Newer alternatives in the same sub-problem include GABFusion, MEC-Quant.

LLM quantization

LSQ

LSQ+: Improving low-bit quantization through learnable offsets and better initialization

Superseded baseline#31 of 80 most-superseded · first seen Apr 20, 2020

Superseded — cited as a baseline and beaten by newer methods

0 papers critique it · 2 beat it on benchmarks

Beaten on benchmarks

Head-to-head results where a newer method reports beating LSQ. Values are copied from the source paper's tables — verify against the cited paper.

MEC-Qaunt (Setting (B)) beats LSQ
42.54 vs 31.08
MBV2 · [W/A 2/2]
MEC-Quant: Maximum Entropy Coding for Extremely Low Bit Quantization-Aware Training
+ Ours beats LSQ
66.8 vs 59.9
mAP · [YOLOv5s W3A3]
GABFusion: Rethinking Feature Fusion for Low-Bit Quantization of Multi-Task Networks
MEC-Qaunt (Setting (A)) beats LSQ
81.20 vs 78.15
MBV2 · [W/A 2/4]
MEC-Quant: Maximum Entropy Coding for Extremely Low Bit Quantization-Aware Training

What to use instead

Recent methods in the same sub-problem, not yet superseded in the knowledge base — arXiv benchmark leaders, not vetted production recommendations.