arXiv research

New method aligns brain data across individuals for better brain decoding.

The study explains how neural networks align their kernels to target functions during training.

New method aligns brain surfaces based on functional signatures.

SrvfNet aligns multiple functional data to templates without supervision.

A function that optimally aligns a timelike vector field with its gradients

We present a probabilistic model for unsupervised alignment of high-dimensional time-warped sequences based on the Dirichlet Process Mixture Model (DPMM). We follow the approach introduced in (Kazlauskaite, 2018) of simultaneously representing each data sequence as a composition of a true underlying function and a time…

Algorithm aligns 3D density maps using Wasserstein distance.

The paper proposes a method to align AI models using conformal risk control.

Multi-subject fMRI data analysis is an interesting and challenging problem in human brain decoding studies. The inherent anatomical and functional variability across subjects make it necessary to do both anatomical and functional alignment before classification analysis. Besides, when it comes to big data, time complex…

This paper studies aligning knowledge graphs from different sources or languages. Most existing methods train supervised methods for the alignment, which usually require a large number of aligned knowledge triplets. However, such a large number of aligned knowledge triplets may not be available or are expensive to obta…

Inter-subject registration of cortical areas is necessary in functional imaging (fMRI) studies for making inferences about equivalent brain function across a population. However, many high-level visual brain areas are defined as peaks of functional contrasts whose cortical position is highly variable. As such, most ali…

TKRR improves KRR performance by aligning target functions with kernels.

Align-RUDDER improves reinforcement learning with few demonstrations by redistributing rewards.

Joint alignment of a collection of functions is the process of independently transforming the functions so that they appear more similar to each other. Typically, such unsupervised alignment algorithms fail when presented with complex data sets arising from multiple modalities or make restrictive assumptions about the …

Novel alignment framework for text-to-image generation using diffusion models and flow matching.

Kernel alignment measures the degree of similarity between two kernels. In this paper, inspired from kernel alignment, we propose a new Linear Discriminant Analysis (LDA) formulation, kernel alignment LDA (kaLDA). We first define two kernels, data kernel and class indicator kernel. The problem is to find a subspace to …

We propose a method for unsupervised domain adaptation that trains a shared embedding to align the joint distributions of inputs (domain) and outputs (classes), making any classifier agnostic to the domain. Joint alignment ensures that not only the marginal distributions of the domain are aligned, but the labels as wel…

Demon aligns diffusion models without retraining or backpropagation.

One obstacle to applying reinforcement learning algorithms to real-world problems is the lack of suitable reward functions. Designing such reward functions is difficult in part because the user only has an implicit understanding of the task objective. This gives rise to the agent alignment problem: how do we create age…

Global existence and convergence proved for Kazdan-Warner equation with non-negative prescribed function.

Deep neural networks show some layers better align with data than others.

Document alignment aims to identify pairs of documents in two distinct languages that are of comparable content or translations of each other. Such aligned data can be used for a variety of NLP tasks from training cross-lingual representations to mining parallel data for machine translation. In this paper we develop an…

DFA trains deep networks by aligning weights then memorizing data.

Improves inference-time alignment for diffusion models without updating weights.

GTBO uses group testing to optimize high-dimensional functions efficiently.

Aggregating multi-subject functional magnetic resonance imaging (fMRI) data is indispensable for generating valid and general inferences from patterns distributed across human brains. The disparities in anatomical structures and functional topographies of human brains warrant aligning fMRI data across subjects. However…

The paper approaches the task of handwritten text recognition (HTR) with attentional encoder-decoder networks trained on sequences of characters, rather than words. We experiment on lines of text from popular handwriting datasets and compare different activation functions for the attention mechanism used for aligning i…

Paper addresses online alignment of large language models under uncertain preference feedback.

SONA improves conditional generation by balancing authenticity and alignment.

DET unifies geometric and functional alignment for high-dimensional scientific data.

DeepFRC learns both alignment and classification of functional data in one model.

Unified framework simplifies DPO algorithms for LLM alignment.

This paper establishes risk convergence and asymptotic weight matrix alignment --- a form of implicit regularization --- of gradient flow and gradient descent when applied to deep linear networks on linearly separable data. In more detail, for gradient flow applied to strictly decreasing loss functions (with similar re…

MFMs enable efficient reward alignment for generative models.

New method for finding function correspondences in binary programs.

Efficiently learns Single-Index Models with constant factor approximation.

Multivariate Pattern (MVP) classification can map different cognitive states to the brain tasks. One of the main challenges in MVP analysis is validating the generated results across subjects. However, analyzing multi-subject fMRI data requires accurate functional alignments between neuronal activities of different sub…

Geometric approach improves motion alignment accuracy and efficiency.

A new method reduces the computational burden of safety alignment for large language models.

New framework aligns latent representations over-the-air using intelligent metasurfaces.

New method aligns diffusion models for inference-time properties without retraining.

DHGAK aligns substructures for better graph kernel performance.

We propose a novel framework for combining datasets via alignment of their intrinsic geometry. This alignment can be used to fuse data originating from disparate modalities, or to correct batch effects while preserving intrinsic data structure. Importantly, we do not assume any pointwise correspondence between datasets…

New method removes pseudo-label bias for unsupervised domain adaptation.

New method optimizes policies without assuming known link functions between preferences and rewards.

Training a source model optimally for its own task is suboptimal for downstream transfer.

SAIL-RevKL improves SAIL's convergence by regularizing the objective function.

New method groups similar functional covariates for better modeling.