Pith. sign in

REVIEW 6 cited by

Parameter-Efficient Orthogonal Finetuning via Butterfly Factorization

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2311.06243 v2 pith:5BB62S33 submitted 2023-11-10 cs.LG cs.AIcs.CLcs.CV

classification cs.LGcs.AIcs.CLcs.CV
keywords orthogonalfinetuninglargemodelsbutterflydownstreamadaptingboft
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Large foundation models are becoming ubiquitous, but training them from scratch is prohibitively expensive. Thus, efficiently adapting these powerful models to downstream tasks is increasingly important. In this paper, we study a principled finetuning paradigm -- Orthogonal Finetuning (OFT) -- for downstream task adaptation. Despite demonstrating good generalizability, OFT still uses a fairly large number of trainable parameters due to the high dimensionality of orthogonal matrices. To address this, we start by examining OFT from an information transmission perspective, and then identify a few key desiderata that enable better parameter-efficiency. Inspired by how the Cooley-Tukey fast Fourier transform algorithm enables efficient information transmission, we propose an efficient orthogonal parameterization using butterfly structures. We apply this parameterization to OFT, creating a novel parameter-efficient finetuning method, called Orthogonal Butterfly (BOFT). By subsuming OFT as a special case, BOFT introduces a generalized orthogonal finetuning framework. Finally, we conduct an extensive empirical study of adapting large vision transformers, large language models, and text-to-image diffusion models to various downstream tasks in vision and language.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 6 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. RefLoRA: Refactored Low-Rank Adaptation for Efficient Fine-Tuning of Large Models

    cs.LG 2025-05 conditional novelty 6.0 of 10

    RefLoRA picks a per-step optimal low-rank factorization (a matrix geometric mean) that balances LoRA's factors, improving fine-tuning convergence and accuracy.

  2. Amplify Adjacent Token Differences: Enhancing Long Chain-of-Thought Reasoning with Shift-FFN

    cs.CL 2025-05 conditional novelty 6.0 of 10

    A gated Shift-FFN adapter that adds the previous token's representation to the current token's before the feedforward layer reduces repetitive looping and improves math accuracy in LoRA fine-tuned models trained on lo...

  3. SOS-LoRA: Static Orthogonal-Subspace Low-Rank Adaptation with Fixed Multi-Scale Scaling

    cs.LG 2026-06 conditional novelty 5.0 of 10

    A LoRA update split into several fixed, differently-scaled low-rank experts with orthogonal input directions improves fine-tuning accuracy at the same parameter count.

  4. Exploring Sparse Adapters for Scalable Merging of Parameter Efficient Experts

    cs.LG 2025-07 conditional novelty 5.0 of 10

    Sparse adapters trained with max connection sensitivity outperform LoRA and full fine-tuning both alone and after merging 20 task experts, but still lag multitask training on unseen tasks.

  5. Efficient Adaptation of Pre-trained Vision Transformer underpinned by Approximately Orthogonal Fine-Tuning Strategy

    cs.CV 2025-07 conditional novelty 4.0 of 10

    AOFT generates approximately orthogonal down/up projection matrices from a single learnable vector, matching the observed near-orthogonality of pre-trained ViT weights, and reports competitive image-classification per...

  6. Universal Adversarial Attack on Aligned Multimodal LLMs

    cs.AI 2025-02 conditional novelty 4.0 of 10

    A single optimized image, trained through the vision and language modules, makes aligned multimodal LLMs produce dangerous responses across diverse prompts and some models.

Pith tools