LESSViT introduces a low-rank efficient spatial-spectral attention mechanism and a hyperspectral masked autoencoder to improve generalization across spectral configuration shifts in hyperspectral imagery.
Mora: High-rank updating for parameter- efficient fine-tuning
9 Pith papers cite this work. Polarity classification is still indexing.
9
Pith papers citing it
citation-role summary
other 1
citation-polarity summary
roles
other 1polarities
unclear 1representative citing papers
Counterfactual prompting effects on LLMs are often indistinguishable from those caused by meaning-preserving paraphrases, causing most previously reported demographic sensitivities to disappear under proper statistical comparison.
BaLoRA is a Bayesian LoRA variant with input-adaptive noise that improves accuracy over standard LoRA and supplies well-calibrated uncertainty estimates on language, vision, and scientific prediction tasks.
ScaLoRA analytically derives per-update column scalings that let low-rank increments accumulate into high-rank weight updates, yielding faster convergence and higher accuracy than prior LoRA variants on LLMs up to 12B parameters.
TeRA parametrizes high-rank LLM weight updates via a random Tucker-like tensor network with shared frozen factors and layer-specific scaling vectors, matching high-rank adapter performance at vector-level parameter counts.
Alpha in LoRA outperforms learning-rate scaling, follows a square-root law with rank, and enables a minimalist LoRA-alpha method that improves performance across tasks.
SMoA is a new PEFT adapter that uses block-wise Hadamard-modulated low-rank branches on spectral partitions to cover more pretrained spectral directions than standard LoRA under a smaller parameter budget.
LoCO is a PEFT technique that constructs orthogonal transformations via low-rank skew-symmetric matrices and compositional rotation chains with a parallelizable approximation, validated on transformer adaptations.
Convergence analysis shows Muon outperforms gradient descent by exploiting low-rank structure in neural network Hessians.
citing papers explorer
-
LESSViT: Robust Hyperspectral Representation Learning under Spectral Configuration Shift
LESSViT introduces a low-rank efficient spatial-spectral attention mechanism and a hyperspectral masked autoencoder to improve generalization across spectral configuration shifts in hyperspectral imagery.
-
Compared to What? Baselines and Metrics for Counterfactual Prompting
Counterfactual prompting effects on LLMs are often indistinguishable from those caused by meaning-preserving paraphrases, causing most previously reported demographic sensitivities to disappear under proper statistical comparison.
-
BaLoRA: Bayesian Low-Rank Adaptation of Large Scale Models
BaLoRA is a Bayesian LoRA variant with input-adaptive noise that improves accuracy over standard LoRA and supplies well-calibrated uncertainty estimates on language, vision, and scientific prediction tasks.
-
ScaLoRA: Optimally Scaled Low-Rank Adaptation for Efficient High-Rank Fine-Tuning
ScaLoRA analytically derives per-update column scalings that let low-rank increments accumulate into high-rank weight updates, yielding faster convergence and higher accuracy than prior LoRA variants on LLMs up to 12B parameters.
-
TeRA: Vector-based Random Tensor Network for High-Rank Adaptation of Large Language Models
TeRA parametrizes high-rank LLM weight updates via a random Tucker-like tensor network with shared frozen factors and layer-specific scaling vectors, matching high-rank adapter performance at vector-level parameter counts.
-
The Hidden Power of Scaling Factor in LoRA Optimization
Alpha in LoRA outperforms learning-rate scaling, follows a square-root law with rank, and enables a minimalist LoRA-alpha method that improves performance across tasks.
-
SMoA: Spectrum Modulation Adapter for Parameter-Efficient Fine-Tuning
SMoA is a new PEFT adapter that uses block-wise Hadamard-modulated low-rank branches on spectral partitions to cover more pretrained spectral directions than standard LoRA under a smaller parameter budget.
-
LoCO: Low-rank Compositional Rotation Fine-tuning
LoCO is a PEFT technique that constructs orthogonal transformations via low-rank skew-symmetric matrices and compositional rotation chains with a parallelizable approximation, validated on transformer adaptations.
-
On the Convergence Analysis of Muon
Convergence analysis shows Muon outperforms gradient descent by exploiting low-rank structure in neural network Hessians.