Research
On-device research index

arXiv research

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.

168,742 papers · 148 categories

Trend · papers per month

count% of corpus
0111 · Jan 202319922001200920172026
3 results for “modality-agnostic”
Modality-Agnostic Variational Compression of Implicit Neural Representationsstat.ML

Modality-agnostic compression improves across diverse data types.

problem Efficiently compressing data across multiple modalities.
method Functional view of data, Implicit Neural Representation (INR), modality-agnostic latent representations, variational compression.
result Improved performance compared to existing methods, especially for diverse modalities.
modality-agnosticcompressionImplicit Neural Representationvariationaldata efficiency
2023-01-23abs ↗pdf ↗
RNE: plug-and-play diffusion inference-time control and energy-based trainingcs.LG

RNE provides a flexible framework for diffusion models, enabling inference-time control and energy-based training.

problem Insufficient knowledge of marginal densities in diffusion models.
method Introduces Radon-Nikodym Estimator (RNE) to reveal the connection between marginal densities and transition kernels.
result RNE delivers strong results in inference-time control and energy-based diffusion training.
diffusion modelsinference-time controlenergy-based trainingdensity ratioplug-and-play framework
2025-06-06abs ↗pdf ↗
Learning Context-conditioned Gaussian Overbounds for Convolution-Based Uncertainty Propagationcs.LG

Unified neural network framework for context-aware Gaussian overbounds in uncertainty propagation.

problem Uncertainty quantification in safety-critical settings requires conservative bounds, but existing methods often fail to compose and are overly conservative.
method Proposes a learning framework that trains neural networks to produce context-aware Gaussian overbounds with provable conservatism.
result The method yields tighter bounds while maintaining conservatism on the enforced grid and in experiments.
uncertainty quantificationGaussian overboundsconvolutionconservatismneural networks
2026-05-15abs ↗pdf ↗