Scholar Feed

Parameter-efficient fine-tuning (LoRA family)

FlexLoRA

FlexLoRA: Entropy-Guided Flexible Low-Rank Adaptation

Superseded baseline#17 of 1,113 most-superseded · first seen Jan 30, 2026

Superseded — cited as a baseline and beaten by newer methods

3 papers critique it · 9 beat it on benchmarks

What papers say

Verbatim critique sentences, each from a paper that cites FlexLoRA as a baseline.

FlexLoRA~bai2024federated reconstructs global updates via SVD; and FFA-LoRA~sunimproving freezes one LoRA matrix to suppress cross-client interference. While effective, these methods trade off scalability, flexibility, or representational capacity.
— ADF-LoRA: Alternating Low-Rank Aggregation for Decentralized Federated Fine-Tuning
“Notably, combining direct weight aggregation with GaLore as an optimizer for local training steps significantly outperforms leading state-of-the-art LoRA methods like FlexLoRA and FFA-LoRA.”
— Exploring Gradient Subspaces: Addressing and Overcoming LoRA's Limitations in Federated Fine-Tuning of Large Language Models
“A straightforward repair for gauge ambiguity in federated LoRA is to aggregate induced updates $ W_i = B_iA_i$ directly and then refactorize the result for redistribution~FlexLoRA. This avoids the semantic defect of raw factor aggregation, but it also forces the server back into dense-update materialization and matrix factorization.”
— Beyond Factor Aggregation: Gauge-Aware Low-Rank Server Representations for Federated LoRA

Beaten on benchmarks

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

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Recent methods in the same sub-problem, not yet superseded in the knowledge base — arXiv benchmark leaders, not vetted production recommendations.