A multi-mode quantum annealing approach enables VAEs with Boltzmann priors, showing faster training and better generation than Gaussian-prior VAEs on MNIST, Fashion-MNIST, and CelebA plus improved out-of-distribution detection.
A learning algorithm for Boltzmann machines.Cognitive Science, 9(1):147–169
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
background 1representative citing papers
AMBer applies reinforcement learning with physics feedback to automate construction of neutrino flavor models that minimize free parameters, validated on known cases and extended to a new symmetry group.
Varying the number of simultaneous parses in RNNGs increases predicted garden-path effects but does not fully reconcile LM surprisal with human reading times.
A single energy-based model trained on LAPD plasma data enables diagnostic reconstruction, inverse inference of probe position, conditional trend sampling, and unconditional mode reproduction for potential anomaly detection.
TOFU loss mitigates the narrowing of generative diversity in LLMs after supervised fine-tuning by addressing neglect of low-frequency patterns and forgetting of prior knowledge.
A two-step agentic system for extracting insights from VSM simulations achieves up to 86% accuracy with top LLMs by using progressive data discovery and slim context.
citing papers explorer
-
Multi-Mode Quantum Annealing for Generative Representation Learning with Boltzmann Priors
A multi-mode quantum annealing approach enables VAEs with Boltzmann priors, showing faster training and better generation than Gaussian-prior VAEs on MNIST, Fashion-MNIST, and CelebA plus improved out-of-distribution detection.
-
Towards AI-assisted Neutrino Flavor Theory Design
AMBer applies reinforcement learning with physics feedback to automate construction of neutrino flavor models that minimize free parameters, validated on known cases and extended to a new symmetry group.
-
Why are language models less surprised than humans? Testing the Parse Multiplicity Mismatch Hypothesis
Varying the number of simultaneous parses in RNNGs increases predicted garden-path effects but does not fully reconcile LM surprisal with human reading times.
-
Energy-based models for diagnostic reconstruction and analysis in a laboratory plasma device
A single energy-based model trained on LAPD plasma data enables diagnostic reconstruction, inverse inference of probe position, conditional trend sampling, and unconditional mode reproduction for potential anomaly detection.
-
Diversity in Large Language Models under Supervised Fine-Tuning
TOFU loss mitigates the narrowing of generative diversity in LLMs after supervised fine-tuning by addressing neglect of low-frequency patterns and forgetting of prior knowledge.
-
Agentic Insight Generation in VSM Simulations
A two-step agentic system for extracting insights from VSM simulations achieves up to 86% accuracy with top LLMs by using progressive data discovery and slim context.