arXiv research

Paper presents a Transformer model for automatic domain adaptation.

ADAPT improves robustness of Vision Transformers without full model fine-tuning.

ABHT boosts regression by filtering regions with different smoothness.

New Hermite approximations accelerate convergence with adaptive coordinate transformations.

Vision transformers benefit from non-smooth components in adaptation.

Improves MCMC performance with adaptive affine transformations.

New bounds adaptively control spectral complexity of trained Transformers.

Adapts to estimate functions from noisy ERT data.

ALT transforms time series data for better classification.

We analyze the computational limits of LoRA for transformer models using fine-grained complexity theory.

This paper improves test-time adaptation for distribution shifts using confidence maximization and input transformation.

LOFT separates subspace rotation and transformation for orthogonal fine-tuning.

In many state-of-the-art compression systems, signal transformation is an integral part of the encoding and decoding process, where transforms provide compact representations for the signals of interest. This paper introduces a class of transforms called graph-based transforms (GBTs) for video compression, and proposes…

ARM improves multivariate time series forecasting by better capturing series-wise relationships.

Study aggregation of statistical evidence under unknown dependence using group-invariance.

Attention mechanisms have become ubiquitous in NLP. Recent architectures, notably the Transformer, learn powerful context-aware word representations through layered, multi-headed attention. The multiple heads learn diverse types of word relationships. However, with standard softmax attention, all attention heads are de…

Few-shot domain adaptation improves autoencoder performance in changing wireless channels.

New method adapts neural networks without losing prior knowledge.

Images seen during test time are often not from the same distribution as images used for learning. This problem, known as domain shift, occurs when training classifiers from object-centric internet image databases and trying to apply them directly to scene understanding tasks. The consequence is often severe performanc…

Transformer learns to infer partial MDPs for efficient in-context adaptation and exploration.

New method makes CP intervals locally adaptive using trainable transformations.

Graph transformation framework improves graph neural network performance.

LoRA enhances model adaptability without increasing parameters.

Adaptive framework predicts stock prices better during volatile periods.

How can deep learning systems flexibly reuse their knowledge? Toward this goal, we propose a new class of challenges, and a class of architectures that can solve them. The challenges are meta-mappings, which involve systematically transforming task behaviors to adapt to new tasks zero-shot. The key to achieving these c…

ALT improves TSC by capturing complex patterns in time series data.

Study proposes adaptive RL for dynamic portfolio optimization.

SPARTAN learns sparse interaction graphs between objects in scenes.

Transformer pretraining yields strong EB performance without explicit adaptation.

Transformers adapted to spherical geometry using space-filling curves.

New framework transforms labeled datasets for various machine learning tasks.

Transformer models show robustness across domains with domain adversarial training.

New origami structures adapt to over 100 shapes with minimal actuation.

Transformer adapts to graphs with adaptive attention and auto-regressive decoding.

A multi-step framework tackles online unsupervised domain adaptation with novel mean-target subspace computation.

SplitWise enhances stepwise regression by adaptively encoding numeric predictors into binary features.

We use the dressing method to construct transformations of constrained Willmore surfaces in arbitrary codimension. An adaptation of the Terng--Uhlenbeck theory of dressing by simple factors to this context leads us to define Bäcklund transforms of these surfaces for which we prove Bianchi permutability. Specialising to…

Sparse Inverse Covariance Estimation (SICE) is useful in many practical data analyses. Recovering the connectivity, non-connectivity graph of covariates is classified amongst the most important data mining and learning problems. In this paper, we introduce a novel SICE approach using adaptive thresholding. Our method i…

This study proposes a trainable adaptive window switching (AWS) method and apply it to a deep-neural-network (DNN) for speech enhancement in the modified discrete cosine transform domain. Time-frequency (T-F) mask processing in the short-time Fourier transform (STFT)-domain is a typical speech enhancement method. To re…

Adaptive TFTs improve cryptocurrency price prediction accuracy.

We define a twistor-like transform of the equations of eleven-dimensional supergravity. More precisely these equations are encoded by the CR-structure on the twistor space P^{2*15+11|8*2+16}. In addition equations of the linearized eleven-dimensional supergravity adapted to the 3-form potential can be transformed into …

TSLANet improves time series models by capturing long-term and short-term interactions.

Paper tackles continual learning with Transformers, maintaining performance and speed.

Pre-trained LLM adapted with LoRA improves offline RL for quantitative trading.

Adaptive denoising models adjust the number of steps based on noise level.

In this paper we prove mixed norm estimates for Riesz transforms related to Laplace--Beltrami operators on compact Riemannian symmetric spaces of rank one. These operators are closely related to the Riesz transforms for Jacobi polynomials expansions. The key point is to obtain sharp estimates for the kernel of the Jaco…

MaxVA improves Adam's step sizes by maximizing gradient variance.

The classical Liouville Theorem on conformal transformations determines local conformal transformations on the Euclidean space of dimension $\geq 3$. Its natural adaptation to the general framework of Riemannian structures is the 2-rigidity of conformal transformations, that is such a transformation is fully determined…