A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
New approach speeds up DNA sequence alignment.
A Markov Chain approach for aligning generative models from pairwise human preferences.
Pairwise ranking aligns subjective clinical evaluations with objective indicators.
Traditional pairwise sequence alignment is based on matching individual samples from two sequences, under time monotonicity constraints. However, in many application settings matching subsequences (segments) instead of individual samples may bring in additional robustness to noise or local non-causal perturbations. Thi…
RCPO uses ranked choice modeling for better LLM alignment.
The paper explores game-theoretic alignment of LLMs with human preferences, finding limitations and conditions.
A new method reduces preference distortion in LLM alignment.
Develops a statistical framework to measure uncertainty in model rankings based on human preferences.
Adversarial training methods typically align distributions by solving two-player games. However, in most current formulations, even if the generator aligns perfectly with data, a sub-optimal discriminator can still drive the two apart. Absent additional regularization, the instability can manifest itself as a never-end…
RLHF performs well despite violating social choice theory axioms.
Unified framework for aligning LLMs from human feedback.
A new method estimates protein evolutionary fields and couplings from alignments.
The alignment of a set of objects by means of transformations plays an important role in computer vision. Whilst the case for only two objects can be solved globally, when multiple objects are considered usually iterative methods are used. In practice the iterative methods perform well if the relative transformations b…
Paper introduces MSA for weakly supervised covariance alignment in MEG signals.
Interpretable semantic textual similarity (iSTS) task adds a crucial explanatory layer to pairwise sentence similarity. We address various components of this task: chunk level semantic alignment along with assignment of similarity type and score for aligned chunks with a novel system presented in this paper. We propose…
The paper improves alignment methods for deep neural networks using geometric and spectral analysis.
A new slicing method reduces computational cost for cross-domain alignment.
Pair Hidden Markov Models (PHMMs) are probabilistic models used for pairwise sequence alignment, a quintessential problem in bioinformatics. PHMMs include three types of hidden states: match, insertion and deletion. Most previous studies have used one or two hidden states for each PHMM state type. However, few studies …
We show that the classification performance of graph convolutional networks (GCNs) is related to the alignment between features, graph, and ground truth, which we quantify using a subspace alignment measure (SAM) corresponding to the Frobenius norm of the matrix of pairwise chordal distances between three subspaces ass…
Representational similarity analysis (RSA) has been shown to be an effective framework to characterize brain-activity profiles and deep neural network activations as representational geometry by computing the pairwise distances of the response patterns as a representational dissimilarity matrix (RDM). However, how to p…
AOT aligns LLMs on distributional preferences via optimal transport.
A new method for aligning datasets without known correspondences.
Phylogenetic tree reconstruction is traditionally based on multiple sequence alignments (MSAs) and heavily depends on the validity of this information bottleneck. With increasing sequence divergence, the quality of MSAs decays quickly. Alignment-free methods, on the other hand, are based on abstract string comparisons …
We study unsupervised multilingual alignment, the problem of finding word-to-word translations between multiple languages without using any parallel data. One popular strategy is to reduce multilingual alignment to the much simplified bilingual setting, by picking one of the input languages as the pivot language that w…
Unified framework for higher-order network analysis.
SARA uses similarity to learn rewards robustly and adaptively.
New Gromov-Wasserstein metric controls rigidity and incorporates prior knowledge.
We address the problem of image translation between domains or modalities for which no direct paired data is available (i.e. zero-pair translation). We propose mix and match networks, based on multiple encoders and decoders aligned in such a way that other encoder-decoder pairs can be composed at test time to perform u…
Constraint-based clustering algorithms exploit background knowledge to construct clusterings that are aligned with the interests of a particular user. This background knowledge is often obtained by allowing the clustering system to pose pairwise queries to the user: should these two elements be in the same cluster or n…
Foot-mounted inertial positioning (FMIP) can face problems of inertial drifts and unknown initial states in real applications, which renders the estimated trajectories inaccurate and not obtained in a well defined coordinate system for matching trajectories of different users. In this paper, an approach adopting receiv…
Paper investigates monotonicity issues in AI preference learning.
Various applications involve assigning discrete label values to a collection of objects based on some pairwise noisy data. Due to the discrete---and hence nonconvex---structure of the problem, computing the optimal assignment (e.g.~maximum likelihood assignment) becomes intractable at first sight. This paper makes prog…
This study explores how feature graphs enhance GNNs' performance in modeling interactions.
Bispectral OT improves dataset comparison by preserving intrinsic coherence.
Unified framework for SSL methods linking contrastive and non-contrastive approaches.
Dynamic time warping (DTW) can be used to compute the similarity between two sequences of generally differing length. We propose a modification to DTW that performs individual and independent pairwise alignment of feature trajectories. The modified technique, termed feature trajectory dynamic time warping (FTDTW), is a…
Geometric stability predicts steerability and detects drift in language models.
iREPA shows spatial structure, not global semantic, drives generation performance in REPA.
RLHF uses human feedback to train AI models, posing statistical challenges.
New system constructs cell-type taxonomy across multiple samples.
New method improves consistency in preference learning for neural networks.
Paper solves robust multi-dimensional scaling with accelerated projections.
Proposes supervised method for whole DAG causal structure learning.
Parametric spatial transformation models have been successfully applied to image registration tasks. In such models, the transformation of interest is parameterized by a fixed set of basis functions as for example B-splines. Each basis function is located on a fixed regular grid position among the image domain, because…
The paper addresses calibration in label ranking, a structured prediction task.
A new method for analyzing latent space models without reference configurations.
Global pairwise network alignment (GPNA) aims to find a one-to-one node mapping between two networks that identifies conserved network regions. GPNA algorithms optimize node conservation (NC) and edge conservation (EC). NC quantifies topological similarity between nodes. Graphlet-based degree vectors (GDVs) are a state…
We consider the problem of consistently matching multiple sets of elements to each other, which is a common task in fields such as computer vision. To solve the underlying NP-hard objective, existing methods often relax or approximate it, but end up with unsatisfying empirical performance due to a misaligned objective.…