QSVD (LLM quantization): superseded — cited as a baseline and beaten by newer methods. 0 paper(s) critique it, 1 beat it on benchmarks — #61 of 80 most-superseded. Sub-problem: cluster led by GPTAQ. Newer alternatives in the same sub-problem include SplitQ, MARR, Quantization-aware Integrated Gradients (QIG), SPEED-Q, Quant-dLLM.

Superseded baseline#61 of 80 most-superseded

QSVD

QSVD: Efficient Low-rank Approximation for Unified Query-Key-Value Weight Compression in Low-Precision Vision-Language Models

LLM quantization · first seen Oct 18, 2025

superseded — cited as a baseline and beaten by newer methods

0 papers critique it · 1 beat it on benchmarks

Beaten on benchmarks

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

SplitQ (Ours) beats QSVD · Avg [W4A8 (7B)]
64.1 vs 58.3
Breaking Modality Heterogeneity in Low-Bit Quantization for Large Vision-Language Models
SplitQ (Ours) beats QSVD · Avg [W4A4 (7B)]
62.9 vs 55.5
Breaking Modality Heterogeneity in Low-Bit Quantization for Large Vision-Language Models
SplitQ (Ours) beats QSVD · Avg [W4A8 (13B)]
66.9 vs 66.2
Breaking Modality Heterogeneity in Low-Bit Quantization for Large Vision-Language Models
SplitQ (Ours) beats QSVD · Avg [W4A4 (13B)]
66.4 vs 63.9
Breaking Modality Heterogeneity in Low-Bit Quantization for Large Vision-Language Models

Newer alternatives

Recent methods in the same sub-problem, not yet superseded in the knowledge base.