Pith. sign in

REVIEW 26 cited by

Towards a Unified View of Parameter-Efficient Transfer Learning

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 2110.04366 v3 pith:EYCV5NY6 submitted 2021-10-08 cs.CL cs.LG

Towards a Unified View of Parameter-Efficient Transfer Learning

classification cs.CL cs.LG
keywords methodsdesignlearningparameter-efficientparameterstransferunifiedfine-tuning
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Fine-tuning large pre-trained language models on downstream tasks has become the de-facto learning paradigm in NLP. However, conventional approaches fine-tune all the parameters of the pre-trained model, which becomes prohibitive as the model size and the number of tasks grow. Recent work has proposed a variety of parameter-efficient transfer learning methods that only fine-tune a small number of (extra) parameters to attain strong performance. While effective, the critical ingredients for success and the connections among the various methods are poorly understood. In this paper, we break down the design of state-of-the-art parameter-efficient transfer learning methods and present a unified framework that establishes connections between them. Specifically, we re-frame them as modifications to specific hidden states in pre-trained models, and define a set of design dimensions along which different methods vary, such as the function to compute the modification and the position to apply the modification. Through comprehensive empirical studies across machine translation, text summarization, language understanding, and text classification benchmarks, we utilize the unified view to identify important design choices in previous methods. Furthermore, our unified framework enables the transfer of design elements across different approaches, and as a result we are able to instantiate new parameter-efficient fine-tuning methods that tune less parameters than previous methods while being more effective, achieving comparable results to fine-tuning all parameters on all four tasks.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 26 Pith papers

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

  1. From Efficiency to Leakage -- Privacy Backdoor in Federated Language Model Fine-Tuning

    cs.CR 2026-06 conditional novelty 7.0

    NeuroImprint attack assigns isolated memorization neurons to training samples in PEFT adapters, enabling closed-form reconstruction of 59-79% of samples across BERT, GPT-2, Qwen2, and Llama3.2 on multiple datasets.

  2. Neutral-Reference Prompting for Vision-Language Models

    cs.CV 2026-05 unverdicted novelty 7.0

    NeRP corrects asymmetric class confusion in VLMs for unseen classes by combining neutral-prompt priors with sample likelihood to flip predictions on confusable pairs, improving new-class accuracy while preserving base...

  3. LoRA-DA: Data-Aware Initialization for Low-Rank Adaptation via Asymptotic Analysis

    cs.LG 2025-10 conditional novelty 7.0

    LoRA-DA derives an optimal data-aware LoRA initialization by solving an optimization problem from asymptotic analysis of parameter discrepancy using Fisher-gradient bias and Fisher-information variance terms.

  4. Continual Learning for VLMs: A Survey and Taxonomy Beyond Forgetting

    cs.CV 2025-08 unverdicted novelty 7.0

    The paper offers a comprehensive survey and proposes a new taxonomy for continual learning strategies in VLMs and MLLMs to combat catastrophic forgetting beyond traditional methods.

  5. Dual-Branch Cross-Projection Debiasing through Diffusion-based Disentanglement

    cs.CV 2026-06 unverdicted novelty 6.0

    Proposes CBCM for diffusion-based spurious attribute mining and DCD for cross-projection debiasing, claiming SOTA worst-group accuracy on four benchmarks while tuning at most 0.22% of parameters.

  6. Polaris: Scaling Up Instruction-Guided Image Generation Towards Millions of Personalized Style Needs

    cs.CV 2026-06 unverdicted novelty 6.0

    Polaris retrieves and integrates relevant models from a large library of checkpoints and adapters to enable scalable instruction-guided image generation and editing without additional training.

  7. PEML: Parameter-efficient Multi-Task Learning with Optimized Continuous Prompts

    cs.CL 2026-05 unverdicted novelty 6.0

    PEML co-optimizes continuous prompts and low-rank adaptations to deliver up to 6.67% average accuracy gains over existing multi-task PEFT methods on GLUE, SuperGLUE, and other benchmarks.

  8. Pretraining Induces a Reusable Spectral Basis for Downstream Task Adaptation

    cs.LG 2026-05 unverdicted novelty 6.0

    Pretraining induces stable leading singular vectors that form a reusable spectral basis inherited by downstream tasks, enabling competitive performance with 0.2% trainable parameters on GLUE.

  9. Plug-and-play Class-aware Knowledge Injection for Prompt Learning with Visual-Language Model

    cs.CV 2026-05 unverdicted novelty 6.0

    CAKI generates class-specific prompts from few-shot samples of the same class, stores them in a knowledge bank, and uses query-key matching to inject relevant class knowledge into test instance predictions for improve...

  10. TLoRA: Task-aware Low Rank Adaptation of Large Language Models

    cs.CL 2026-04 unverdicted novelty 6.0

    TLoRA jointly optimizes LoRA initialization via task-data SVD and sensitivity-driven rank allocation, delivering stronger results than standard LoRA across NLU, reasoning, math, code, and chat tasks while using fewer ...

  11. SOLARIS: Speculative Offloading of Latent-bAsed Representation for Inference Scaling

    cs.LG 2026-04 unverdicted novelty 6.0

    Speculative precomputation of foundation-model user–item embeddings decouples heavy inference from the serving path and yields 0.67% revenue gain at Meta ads scale.

  12. Visual prompting reimagined: The power of the Activation Prompts

    cs.CV 2026-04 unverdicted novelty 6.0

    Activation prompts on intermediate layers outperform input-level visual prompting and parameter-efficient fine-tuning in accuracy and efficiency across 29 datasets.

  13. CeRA: Breaking the Linear Ceiling of Low-Rank Adaptation with Non-linearity Retained at Inference

    cs.LG 2026-02 unverdicted novelty 6.0

    CeRA overcomes LoRA's linear ceiling by injecting non-linear SiLU gating and dropout, outperforming high-rank LoRA on complex math reasoning with 1/8 the parameters.

  14. Histogram-based Parameter-efficient Tuning for Passive and Active Sonar Classification

    cs.LG 2025-04 unverdicted novelty 6.0

    HPT uses histograms of feature embeddings to modulate pre-trained models for sonar classification, achieving higher accuracy than standard adapters on passive sonar datasets like VTUAD.

  15. LLaVA-Video: Video Instruction Tuning With Synthetic Data

    cs.CV 2024-10 unverdicted novelty 6.0

    LLaVA-Video-178K is a new synthetic video instruction dataset that, when combined with existing data to train LLaVA-Video, produces strong results on video understanding benchmarks.

  16. Mixture-of-Depths: Dynamically allocating compute in transformer-based language models

    cs.LG 2024-04 conditional novelty 6.0

    Mixture-of-Depths enables transformers to dynamically allocate compute by routing only the top-k tokens through each layer's full computations, matching baseline performance with a fraction of the FLOPs per forward pa...

  17. ReWOO: Decoupling Reasoning from Observations for Efficient Augmented Language Models

    cs.CL 2023-05 conditional novelty 6.0

    ReWOO decouples reasoning from tool observations in augmented language models, delivering 5x token efficiency and 4% higher accuracy on multi-step reasoning benchmarks like HotpotQA.

  18. Geometry-Preserving Orthonormal Initialization for Low-Rank Adaptation in RLVR

    cs.LG 2026-06 unverdicted novelty 5.0

    Orthonormal initialization for LoRA in RLVR achieves the minimal gap to full fine-tuning, stabilizes training, and outperforms standard LoRA and prior variants on mathematical reasoning benchmarks.

  19. Deep Reprogramming Distillation for Medical Foundation Models

    cs.CV 2026-05 unverdicted novelty 5.0

    DRD introduces a reprogramming module and CKA-based distillation to enable efficient, robust adaptation of medical foundation models to downstream 2D/3D classification and segmentation tasks, outperforming prior PEFT ...

  20. FedProxy: Federated Fine-Tuning of LLMs via Proxy SLMs and Heterogeneity-Aware Fusion

    cs.LG 2026-04 unverdicted novelty 5.0

    FedProxy replaces weak adapters with a proxy SLM for federated LLM fine-tuning, outperforming prior methods and approaching centralized performance via compression, heterogeneity-aware aggregation, and training-free fusion.

  21. SEATrack: Simple, Efficient, and Adaptive Multimodal Tracker

    cs.CV 2026-04 unverdicted novelty 5.0

    SEATrack combines AMG-LoRA for cross-modal attention alignment with HMoE for global relation modeling to improve the performance-efficiency trade-off in multimodal tracking.

  22. SOLARIS: Speculative Offloading of Latent-bAsed Representation for Inference Scaling

    cs.LG 2026-04 unverdicted novelty 5.0

    SOLARIS speculatively precomputes user-item latent representations to decouple large-model inference from real-time serving, delivering 0.67% revenue gain when deployed in Meta's ad system.

  23. Parameter-Efficient Fine-Tuning for Large Models: A Comprehensive Survey

    cs.LG 2024-03 accept novelty 4.0

    A comprehensive survey of PEFT algorithms for large models, covering their performance, overhead, applications, and real-world system implementations.

  24. The nextAI Solution to the NeurIPS 2023 LLM Efficiency Challenge

    cs.LG 2026-04 unverdicted novelty 2.0

    A competition entry achieved efficient fine-tuning of LLaMa2 70B on one GPU in 24 hours with competitive QA benchmark performance.

  25. Small Language Models (SLMs) Can Still Pack a Punch: A survey (updated 2026)

    cs.CL 2025-01 unverdicted novelty 2.0

    A literature survey of Small Language Models (1-8B parameters) that can perform comparably or better than larger models, covering general-purpose and task-specific approaches plus creation techniques.

  26. A Comprehensive Overview of Large Language Models

    cs.CL 2023-07 unverdicted novelty 2.0

    A survey paper providing an overview of Large Language Models, their background, and recent advances in the field.