LLM reasoning / chain-of-thought
DualHSIC
DualHSIC: HSIC-Bottleneck and Alignment for Continual Learning
Superseded baseline#45 of 772 most-superseded · first seen Apr 30, 2023
Superseded — cited as a baseline and beaten by newer methods
1 papers critique it · 1 beat it on benchmarks
What papers say
Verbatim critique sentences, each from a paper that cites DualHSIC as a baseline.
In contrast to STAR, OCM and DualHSIC do not consider the change in model outputs in the local parameter neighbourhood
Beaten on benchmarks
Head-to-head results where a newer method reports beating DualHSIC. Values are copied from the source paper's tables — verify against the cited paper.
STAR+DER++ beats DualHSIC
27.64 vs 22.44
accuracy · [DER++ + buffer size 200]
STAR: Stability-Inducing Weight Perturbation for Continual LearningSTAR+ER-ACE beats DualHSIC
60.69 vs 57.03
accuracy · [ER-ACE + buffer size 100]
STAR: Stability-Inducing Weight Perturbation for Continual Learning