SARLO-80 is a new public dataset of 119566 complex SAR-optical-text triplets standardized to 80cm slant-range resolution from 257 locations across 72 countries.
hub
Estimate and Replace: A Novel Approach to Integrating Deep Neural Networks with Existing Applications
16 Pith papers cite this work. Polarity classification is still indexing.
16
Pith papers citing it
abstract
Existing applications include a huge amount of knowledge that is out of reach for deep neural networks. This paper presents a novel approach for integrating calls to existing applications into deep learning architectures. Using this approach, we estimate each application's functionality with an estimator, which is implemented as a deep neural network (DNN). The estimator is then embedded into a base network that we direct into complying with the application's interface during an end-to-end optimization process. At inference time, we replace each estimator with its existing application counterpart and let the base network solve the task by interacting with the existing application. Using this 'Estimate and Replace' method, we were able to train a DNN end-to-end with less data and outperformed a matching DNN that did not interact with the external application.
hub tools
citation-role summary
method 1
citation-polarity summary
roles
method 1polarities
use method 1representative citing papers
KARMA constructs minimal-K Markov transition kernels as surrogates to deliver global explanations for multivariate time series forecasting models and recovers known causal structure on synthetic data.
Muon succeeds by guaranteeing local step-size optimality rather than by tracking any ideal global geometry, as random-spectrum and quasi-norm variants match its performance on language models.
Graph-PRefLexOR fine-tunes graph-native models with GRPO to organize reasoning into phases, yielding 40-65% gains in traceable hypothesis generation and 2-3x semantic diversity on 100 materials science questions.
Proposes capability slices with dual taxonomies and mapping rules to form a closed loop converting benchmark failures into targeted data interventions, validated via two opposing case studies on BBH and math reasoning.
Framework learns control-affine reduced-order models via jointly trained autoencoders on high-dimensional data, extended to sequence-based models and assessed on numerical examples for prediction and feedback linearization.
MD simulations yield silicate grain shattering thresholds of ~6 km/s and post-collision size distributions inconsistent with power-law predictions from Jones et al. (1996) and Hirashita & Kobayashi (2013).
LLM responses mirror venting with higher regulation and escalation; therapist personas lower escalation while preserving regulation, and lay raters miss escalation.
Introduces spSSA extending SSA to spatial data via three generalized eigenvalue procedures and a data augmentation method to estimate nonstationary subspace dimension.
Symplectic Neural Operators preserve symplectic structure for learning infinite-dimensional Hamiltonian PDEs and deliver improved long-term energy stability in theory and experiments.
Natural language descriptions generated via a closed-loop pipeline with digital twins capture the selectivity of most neurons in macaque V1 and V4, with synthesized images driving 96% of V4 neurons into the top or bottom 5% of natural-image response distributions.
Derives optimality constraints for nonnegative joint dictionary learning that explain observed SAE behaviors such as feature splitting, absorption, and dense antipodal features.
Jailbreak prompts with adversarial suffixes have high GPT-2 perplexity, and a LightGBM model on perplexity and length detects most attacks.
Liberata introduces a graph-based system using continuous contribution shares and weighted citations to derive metrics for impact, risk, collaboration, and quality control in academic publishing.
A review consolidating zero-handling methods for compositional count data, critiquing log-ratio assumptions, and comparing imputation strategies adapted to discrete zero-inflated counts.
An updated YOLOv8s detector improves student behavior recognition in crowded classrooms by 1.8-2.1% mAP through added feature modules and a reweighted loss.
citing papers explorer
No citing papers match the current filters.