No article text was recorded for this version.
low-rank expressivity bottleneck (low-rank representation bottleneck)
Version 2 of 2350 papers415 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Dynamics and Representation Structure of Local Approximations to Gradient-Based Learning in Linear Recurrent Neural Networks
- Blog: LoRA Learns Less and Forgets Less
- Blog: RandLoRA: Full-rank parameter-efficient fine-tuning of large models
- Blog: RidgeLoRA: Matrix Ridge Enhanced Low-Rank Adaptation of Large Language Models
- Blog: Continual Diffuser (CoD): Mastering Continual Offline Reinforcement Learning with Experience Rehearsal
- Blog: LoRA Learns Less and Forgets Less
- Blog: Contrastive-Adversarial and Diffusion: Exploring pre-training and fine-tuning strategies for sulcal identification
- Blog: PoLAR: Polar-Decomposed Low-Rank Adapter Representation
- Blog: QuanTA: Efficient High-Rank Fine-Tuning of LLMs with Quantum-Informed Tensor Adaptation
- Blog: Towards Higher Effective Rank in Parameter-Efficient Fine-tuning using Khatri-Rao Product
- Blog: HD-PiSSA: High-Rank Distributed Orthogonal Adaptation
- Blog: SiRA: Sparse Mixture of Low Rank Adaptation
- Blog: An Orthogonal High-Rank Adaptation for Large Language Models
- Blog: Fine-Tuning and Deploying Large Language Models Over Edges: Issues and Approaches
- Blog: Chain of LoRA: Efficient Fine-tuning of Language Models via Residual Learning
- Blog: Enhancing Low-Rank Adaptation with Structured Nonlinear Transformations
- Blog: Parameter-Efficient Fine-Tuning via Circular Convolution
- Blog: ESE: Espresso Sentence Embeddings
- Blog: See Further for Parameter Efficient Fine-tuning by Standing on the Shoulders of Decomposition
- Blog: LoRA-Pro: Are Low-Rank Adapters Properly Optimized?
- Blog: Mixture-of-Subspaces in Low-Rank Adaptation
- Blog: LoRA Done RITE: Robust Invariant Transformation Equilibration for LoRA Optimization
- Blog: Structured Unrestricted-Rank Matrices for Parameter Efficient Finetuning
- Blog: Sketch to Adapt: Fine-Tunable Sketches for Efficient LLM Adaptation
- Blog: LoRA-Pro: Are Low-Rank Adapters Properly Optimized?
- Blog: CoSA: Compressed Sensing-Based Adaptation of Large Language Models
- Blog: Look Within or Look Beyond? A Theoretical Comparison Between Parameter-Efficient and Full Fine-Tuning
- Blog: NeuroTTT: Bridging Pretraining-Downstream Task Misalignment in EEG Foundation Models via Test-Time Training
- Blog: Asymmetry in Low-Rank Adapters of Foundation Models
- Blog: Beyond Low-Rank Tuning: Model Prior-Guided Rank Allocation for Effective Transfer in Low-Data and Large-Gap Regimes.
- Blog: PeriodicLoRA: Breaking the Low-Rank Bottleneck in LoRA Optimization
- Blog: GraLoRA: Granular Low-Rank Adaptation for Parameter-Efficient Fine-Tuning
- Blog: Low-Rank Rescaled Vision Transformer Fine-Tuning: A Residual Design Approach
- Blog: I3S: Importance Sampling Subspace Selection for Low-Rank Optimization in LLM Pretraining
- Blog: Evaluating Parameter Efficient Methods for RLVR
- Blog: Blockwise Hadamard high-Rank Adaptation for Parameter-Efficient LLM Fine-Tuning
- Blog: Investigating ReLoRA: Effects on the Learning Dynamics of Small Language Models
- Blog: SpaLLM: Unified Compressive Adaptation of Large Language Models with Sketching
- Blog: ScaLoRA: Optimally Scaled Low-Rank Adaptation for Efficient High-Rank Fine-Tuning
- Blog: ROSA: Random Subspace Adaptation for Efficient Fine-Tuning
- Blog: DoRA: Weight-Decomposed Low-Rank Adaptation
- Blog: Training Neural Networks from Scratch with Parallel Low-Rank Adapters
- Blog: Flora: Low-Rank Adapters Are Secretly Gradient Compressors
- Blog: PMSS: Pretrained Matrices Skeleton Selection for LLM Fine-tuning
- Blog: Res-Attn : An Enhanced Res-Tuning Approach with Lightweight Attention Mechanism
- Blog: Is BatchEnsemble a Single Model? On Calibration and Diversity of Efficient Ensembles
- Blog: Multi-Domain Learning with Modulation Adapters
- Blog: LISA: Layerwise Importance Sampling for Memory-Efficient Large Language Model Fine-Tuning
- Blog: Federated Fine-tuning of Large Language Models under Heterogeneous Tasks and Client Resources
- Blog: AuroRA: Breaking Low-Rank Bottleneck of LoRA with Nonlinear Mapping
- Blog: PMSS: Pretrained Matrices Skeleton Selection for LLM Fine-tuning
- Blog: Federated Residual Low-Rank Adaptation of Large Language Models
- Blog: Robust Federated Finetuning of LLMs via Alternating Optimization of LoRA
- Blog: ConsisLoRA: Enhancing Content and Style Consistency for LoRA-based Style Transfer
- Blog: Offline Meta-Reinforcement Learning with Advantage Weighting
- Blog: DyLoRA: Parameter-Efficient Tuning of Pre-trained Models using Dynamic Search-Free Low-Rank Adaptation
- Blog: BlockLLM: Memory-Efficient Adaptation of LLMs by Selecting and Optimizing the Right Coordinate Blocks
- Blog: DiffuseKronA: A Parameter Efficient Fine-tuning Method for Personalized Diffusion Models
- Blog: Knowledge-Preserving Pluggable Modules for Multilingual Speech Translation Tasks
- Blog: The Expressive Power of Low-Rank Adaptation
Showing 60 of 350 papers.
History & citation
Current · Permanent link
- High Rank Training via Sequential Low Rank Updates merged into this direction (80% overlap)
- High-Rank Updates for Parameter-Efficient Fine-Tuning merged into this direction (73% overlap)
- Nonlinear Low-Rank Adaptation for Parameter-Efficient Learning merged into this direction (57% overlap)
- High Rank Adaptation with Low Parameter Budgets merged into this direction (51% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_low_rank_expressivity_bottleneck_low_ran_9f045268,
title = {low-rank expressivity bottleneck (low-rank representation bottleneck)},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/low-rank-expressivity-bottleneck-low-rank-representation-bottleneck/rdr_9f0452685da84d9bb96327e563ae55ab},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-19},
}This exact version (version 2, frozen text):
@misc{lacuna_low_rank_expressivity_bottleneck_low_ran_9f045268_v2,
title = {low-rank expressivity bottleneck (low-rank representation bottleneck)},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/low-rank-expressivity-bottleneck-low-rank-representation-bottleneck/rdr_9f0452685da84d9bb96327e563ae55ab/v/2},
note = {Version 2, frozen 2026-10-04. Accessed 2026-11-19},
}