No article text was recorded for this version.
parameter-efficient scaling limits
Version 1 of 1297 papers299 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Astraios: Parameter-Efficient Instruction Tuning Code Large Language Models
- Blog: CLIPA-v2: Scaling CLIP Training with 81.1% Zero-shot ImageNet Accuracy within a $10,000 Budget
- Blog: A Prompt Learning Framework for Source Code Summarization
- Blog: IGU-LoRA: Adaptive Rank Allocation via Integrated Gradients and Uncertainty-Aware Scoring
- Blog: Fine-tune Language Models to Approximate Unbiased In-context Learning
- Blog: Adaptation with Self-Evaluation to Improve Selective Prediction in LLMs
- Blog: MoST: Efficient Monarch Sparse Tuning for 3D Representation Learning
- Blog: UniPELT: A Unified Framework for Parameter-Efficient Language Model Tuning
- Blog: DyLoRA: Parameter-Efficient Tuning of Pre-trained Models using Dynamic Search-Free Low-Rank Adaptation
- Blog: Dial BeInfo for Faithfulness: Improving Factuality of Information-Seeking Dialogue via Behavioural Fine-Tuning
- Blog: Delving into Parameter-Efficient Fine-Tuning in Code Change Learning: An Empirical Study
- Blog: E²LoRA: Efficient and Effective Low-Rank Adaptation with Entropy-Guided Adaptive Sharing
- Blog: KaSA: Knowledge-Aware Singular-Value Adaptation of Large Language Models
- Blog: LiST: Lite Prompted Self-training Makes Parameter-efficient Few-shot Learners
- Blog: MKT: A Multi-Stage Knowledge Transfer Framework to Mitigate Catastrophic Forgetting in Multi-Domain Chinese Spelling Correction
- Blog: $π$-Tuning: Transferring Multimodal Foundation Models with Optimal Multi-task Interpolation
- Blog: Recover-LoRA: Data-Free Accuracy Recovery of Degraded Language Models via Low-Rank Adaptation
- Blog: FinLoRA: Benchmarking LoRA Methods for Fine-Tuning LLMs on Financial Datasets
- Blog: Revisiting LoRA through the Lens of Parameter Redundancy: Spectral Encoding Helps
- Blog: An Equal-Size Hard EM Algorithm for Diverse Dialogue Generation
- Blog: Mix-Initiative Response Generation with Dynamic Prefix Tuning
- Blog: A Bayesian Hybrid Parameter-Efficient Fine-Tuning Method for Large Language Models
- Blog: CAVL: Learning Contrastive and Adaptive Representations of Vision and Language
- Blog: Uni-LoRA: One Vector is All You Need
- Blog: AdaMergeX: Cross-Lingual Transfer with Large Language Models via Adaptive Adapter Merging
- Blog: PIP: Parse-Instructed Prefix for Syntactically Controlled Paraphrase Generation
- Blog: Beyond Tokens: Concept-Level Training Objectives for LLMs
- Blog: SoundLoCD: An Efficient Conditional Discrete Contrastive Latent Diffusion Model for Text-to-Sound Generation
- Blog: GrowLength: Accelerating LLMs Pretraining by Progressively Growing Training Length
- Blog: NeuroAda: Activating Each Neuron’s Potential for Parameter-Efficient Fine-Tuning
- Blog: Empowering parameter-efficient transfer learning by recognizing the kernel structure in self-attention
- Blog: One Model for All Domains: Collaborative Domain-Prefix Tuning for Cross-Domain NER
- Blog: Low-Rank Adaptation of Large Language Model Rescoring for Parameter-Efficient Speech Recognition
- Blog: SECURA: Sigmoid-Enhanced CUR Decomposition with Uninterrupted Retention and Low-Rank Adaptation in Large Language Models
- Blog: MiLoRA: Efficient Mixture of Low-Rank Adaptation for Large Language Models Fine-tuning
- Blog: PAVE: Patching and Adapting Video Large Language Models
- Blog: PAL: Probing Audio Encoders via LLMs - A Study of Information Transfer from Audio Encoders to LLMs
- Blog: Editing Commonsense Knowledge in GPT
- Blog: BERT and PALs: Projected Attention Layers for Efficient Adaptation in Multi-Task Learning
- Blog: Label-Aware Automatic Verbalizer for Few-Shot Text Classification in Mid-To-Low Resource Languages
- Blog: Detoxifying Large Language Models via Knowledge Editing
- Blog: AutoRank: MCDA Based Rank Personalization for LoRA-Enabled Distributed Learning
- Blog: Learned Adapters Are Better Than Manually Designed Adapters
- Blog: Learning to Route for Dynamic Adapter Composition in Continual Learning with Language Models
- Blog: Model-Generated Pretraining Signals Improves Zero-Shot Generalization of Text-to-Text Transformers
- Blog: KG-Adapter: Enabling Knowledge Graph Integration in Large Language Models through Parameter-Efficient Fine-Tuning
- Blog: SPIRE: Conditional Personalization for Federated Diffusion Generative Models
- Blog: Towards Versatile and Efficient Visual Knowledge Injection into Pre-trained Language Models with Cross-Modal Adapters
- Blog: DoRA: Enhancing Parameter-Efficient Fine-Tuning with Dynamic Rank Distribution
- Blog: QLoRA: Efficient Finetuning of Quantized LLMs
- Blog: Editing Language Model-based Knowledge Graph Embeddings
- Blog: UniICL: An Efficient ICL Framework Unifying Compression, Selection, and Generation
- Blog: Mini-batch Coresets for Memory-efficient Language Model Training on Data Mixtures
- Blog: MoRE: A Mixture of Low-Rank Experts for Adaptive Multi-Task Learning
- Blog: FALQON: Accelerating LoRA Fine-tuning with Low-Bit Floating-Point Arithmetic
- Blog: SuLoRA: Subspace Low-Rank Adaptation for Parameter-Efficient Fine-Tuning
- Blog: DeFINE: Deep Factorized Input Token Embeddings for Neural Sequence Modeling
- Blog: Weight Spectra Induced Efficient Model Adaptation
- Blog: Adaptation with Self-Evaluation to Improve Selective Prediction in LLMs
- Blog: Few-shot Unified Question Answering: Tuning Models or Prompts?
Showing 60 of 297 papers.
History & citation
Current · Permanent link
- This direction split from Scaling Efficient Optimization and Alignment to Frontier Models (71% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_parameter_efficient_scaling_limits_4d77523b,
title = {parameter-efficient scaling limits},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/parameter-efficient-scaling-limits/rdr_4d77523b97884539ba411c080181ce84},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-22},
}This exact version (version 1, frozen text):
@misc{lacuna_parameter_efficient_scaling_limits_4d77523b_v1,
title = {parameter-efficient scaling limits},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/parameter-efficient-scaling-limits/rdr_4d77523b97884539ba411c080181ce84/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-22},
}