arXiv research

Paper introduces Manifold Probe for discovering representation manifolds in superposition.

This two-part work puts forth the idea of engaging power electronics to probe an electric grid to infer non-metered loads. Probing can be accomplished by commanding inverters to perturb their power injections and record the induced voltage response. Once a probing setup is deemed topologically observable by the tests o…

Paper analyzes why deeper layers of ViTs perform worse on out-of-distribution tasks.

We identify spectral conditions for reliable neural probe interpretation.

PROBE algorithm efficiently solves sparse high-dimensional linear regression.

This work defines idealized SSL representations and improves existing methods.

Neural network models have a reputation for being black boxes. We propose to monitor the features at every layer of a model and measure how suitable they are for classification. We use linear classifiers, which we refer to as "probes", trained entirely independently of the model itself. This helps us better understand …

CwA optimizes search performance by jointly learning a balanced database partition and a neural probing function.

Noise Injection probes deep learning dynamics during training phases.

Probe-level models have led to improved performance in microarray studies but the various sources of probe-level contamination are still poorly understood. Data-driven analysis of probe performance can be used to quantify the uncertainty in individual probes and to highlight the relative contribution of different noise…

New method predicts aphasia severity with narrower uncertainty intervals.

We propose a novel confidence scoring mechanism for deep neural networks based on a two-model paradigm involving a base model and a meta-model. The confidence score is learned by the meta-model observing the base model succeeding/failing at its task. As features to the meta-model, we investigate linear classifier probe…

Self-supervised research improved greatly over the past half decade, with much of the growth being driven by objectives that are hard to quantitatively compare. These techniques include colorization, cyclical consistency, and noise-contrastive estimation from image patches. Consequently, the field has settled on a hand…

The paper explores linear representations in language models using counterfactuals.

A probing scheme is considered with an accessible and controllable qubit, used to probe an out-of equilibrium system consisting of a second qubit interacting with an environment. Quantum spontaneous synchronization between the probe and the system emerges in this model and, by tuning the probe frequency, can occur both…

Proves accuracy guarantees for self-supervised learning with correlated positive pairs.

Optimal probing framework for scalable network monitoring.

Accumulation of standardized data collections is opening up novel opportunities for holistic characterization of genome function. The limited scalability of current preprocessing techniques has, however, formed a bottleneck for full utilization of contemporary microarray collections. While short oligonucleotide arrays …

OLPA optimizes online user-centric selection with probing, achieving near-optimal regret bounds.

This paper explores what causal structures can be distinguished by observational and interventional probing schemes.

The paper explores how AI systems use information geometry to encode semantic structure.

We present a sparse knowledge gradient (SpKG) algorithm for adaptively selecting the targeted regions within a large RNA molecule to identify which regions are most amenable to interactions with other molecules. Experimentally, such regions can be inferred from fluorescence measurements obtained by binding a complement…

Researchers propose a new SSL risk decomposition method to evaluate and improve self-supervised learning models.

This is a brief review of some of the uses of nonlinear sigma models. After a short general discussion touching on point particles, strings and condensed matter systems, focus is shifted to sigma models as probes of target space geometries. The relation of supersymmetric non-linear sigma models to Kähler, hyperkähler, …

System guides freehand obstetric ultrasound probe movements.

The ability of modeling the other agents, such as understanding their intentions and skills, is essential to an agent's interactions with other agents. Conventional agent modeling relies on passive observation from demonstrations. In this work, we propose an interactive agent modeling scheme enabled by encouraging an a…

ZDP detects drift in large language models without labels, proving key theorems and metrics.

LP-FT improves personalized model training in FL by balancing generalization and personalization.

This paper focuses on the problem of estimating historical traffic volumes between sparsely-located traffic sensors, which transportation agencies need to accurately compute statewide performance measures. To this end, the paper examines applications of vehicle probe data, automatic traffic recorder counts, and neural …

Study examines flaws in probing LLMs' knowledge and introduces a new method.

We study the statistical behavior of reasoning probes in a stylized model of iterative computation inspired by neural algorithmic reasoning. The underlying computation is given by a looped Boolean circuit whose graph is a perfect $ν$-ary tree ($ν\ge 2$), with outputs recursively fed back as inputs across computation ro…

Distribution grids currently lack comprehensive real-time metering. Nevertheless, grid operators require precise knowledge of loads and renewable generation to accomplish any feeder optimization task. At the same time, new grid technologies, such as solar photovoltaics and energy storage units are interfaced via invert…

New algorithm catches moving subspaces in bandit problems.

Improved unsupervised probing for ranking tasks using Contrast-Consistent Ranking.

This research discovers model architecture and training dataset characteristics through strategic input probing.

New construction reveals SU(2)-flavor fields in heterotic M5-brane model.

Researchers create holographic super-embeddings for M5 and M2 branes.

New RL method learns value function for many policies using few key states.

New method tightens federated probe-logit distillation rates under varying bandwidths.

We study supersymmetric probe M5-branes in the AdS_4 solution that arises from M5-branes wrapped on a hyperbolic 3-manifold M_3. This amounts to introducing internal defects within the framework of the 3d-3d correspondence. The BPS condition for a probe M5-brane extending along all of AdS_4 requires it to wrap a surfac…

This work analyzes the role of data augmentation in self-supervised learning using RKHS approximation and regression.

Higher gauge theory via differential nonabelian cohomology

Improved scalability and interpretability in training data attribution.

An accurate and fast estimation of the available bandwidth in a network with varying cross-traffic is a challenging task. The accepted probing tools, based on the fluid-flow model of a bottleneck link with first-in, first-out multiplexing, estimate the available bandwidth by measuring packet dispersions. The estimation…

Concept Hierarchies and Formal Concept Analysis are theoretically well grounded and largely experimented methods. They rely on line diagrams called Galois lattices for visualizing and analysing object-attribute sets. Galois lattices are visually seducing and conceptually rich for experts. However they present important…

This paper addresses missing covariates in stochastic linear bandits, providing a high-probability regret bound.

SiamJEPA uses Siamese student encoders to improve JEPA-based representation learning.

This paper enhances language models with knowledge awareness.