BioMatrix unifies sequences, structures, and language for molecules and proteins inside one decoder-only foundation model via shared discrete tokens and achieves SOTA or competitive results on 77 of 80 downstream tasks.
hub
Adversarial Autoencoders
15 Pith papers cite this work. Polarity classification is still indexing.
15
Pith papers citing it
abstract
In this paper, we propose the "adversarial autoencoder" (AAE), which is a probabilistic autoencoder that uses the recently proposed generative adversarial networks (GAN) to perform variational inference by matching the aggregated posterior of the hidden code vector of the autoencoder with an arbitrary prior distribution. Matching the aggregated posterior to the prior ensures that generating from any part of prior space results in meaningful samples. As a result, the decoder of the adversarial autoencoder learns a deep generative model that maps the imposed prior to the data distribution. We show how the adversarial autoencoder can be used in applications such as semi-supervised classification, disentangling style and content of images, unsupervised clustering, dimensionality reduction and data visualization. We performed experiments on MNIST, Street View House Numbers and Toronto Face datasets and show that adversarial autoencoders achieve competitive results in generative modeling and semi-supervised classification tasks.
hub tools
citation-role summary
background 2
citation-polarity summary
roles
background 2polarities
background 2representative citing papers
MirrorCheck detects adversarial attacks on VLMs via T2I regeneration for semantic consistency checks, using stochastic model selection and one-time perturbations for robustness against adaptive attacks.
BERT stores relational knowledge extractable via cloze queries without fine-tuning and matches supervised baselines on open-domain QA tasks.
Adversarial fine-tuning lets single-cell foundation models translate between unpaired ST and scRNA-seq, outperforming existing multi-omics translation methods.
Generative sequence models for physical tasks exhibit physical misgeneralization where local prediction errors propagate through physical measurements to distort aggregate distributions over quantities like distance or energy; a data deviation kernel explains and predicts the shifts and supports a内核
Disentangled representations enable a new auditing procedure to identify proxy features and quantify their influence on model outcomes more effectively than prior methods.
CoOD decomposes inputs into components and applies Component Shift Score plus Compositional Consistency Score to improve detection of both standard and compositional out-of-distribution data.
MetaGPT embeds human SOPs into LLM prompts to create role-specialized agent teams that produce more coherent solutions on collaborative software engineering tasks than prior chat-based multi-agent systems.
The paper introduces a unified formulation for representation learning with task and constraint components, arguing for mutual benefits between causal and traditional approaches and showing via experiments that causal constraint effectiveness depends on paired tasks.
AEQ-RVAE-ST combines approximate equivariance and progressive sequence lengthening in a recurrent VAE to match or exceed prior generative models on quasi-periodic time series benchmarks.
Y-Autoencoders disentangle latent factors by splitting the encoder output into implicit and explicit branches before decoding, with added losses enforcing independence and label correlation.
AMAD is an end-to-end model using adversarial autoencoders and RNNs with attention for multiscale anomaly detection on time-evolving high-dimensional categorical data.
X-VAE uses empirical statistics from a pretrained autoencoder to set a data-adaptive Gaussian prior and introduces a latent scaling factor for controllable generation.
Deep recurrent autoencoders convert images to shortened audio signals that incorporate hearing models, enabling above-chance hand posture discrimination and object reaching after a few hours of training instead of months.
A 2019 survey that categorizes and intuitively explains major deep learning techniques for image segmentation, progressing from classical methods to modern neural architectures.
citing papers explorer
-
BioMatrix: Towards a Comprehensive Biological Foundation Model Spanning the Modality Matrix of Sequences, Structures, and Language
BioMatrix unifies sequences, structures, and language for molecules and proteins inside one decoder-only foundation model via shared discrete tokens and achieves SOTA or competitive results on 77 of 80 downstream tasks.
-
MirrorCheck: Efficient Adversarial Defense for Vision-Language Models
MirrorCheck detects adversarial attacks on VLMs via T2I regeneration for semantic consistency checks, using stochastic model selection and one-time perturbations for robustness against adaptive attacks.
-
Language Models as Knowledge Bases?
BERT stores relational knowledge extractable via cloze queries without fine-tuning and matches supervised baselines on open-domain QA tasks.
-
Single-Cell Cross-Modal Transfer by Adversarial Fine-Tuning of Foundation Models
Adversarial fine-tuning lets single-cell foundation models translate between unpaired ST and scRNA-seq, outperforming existing multi-omics translation methods.
-
Mechanisms of Misgeneralization in Physical Sequence Modeling
Generative sequence models for physical tasks exhibit physical misgeneralization where local prediction errors propagate through physical measurements to distort aggregate distributions over quantities like distance or energy; a data deviation kernel explains and predicts the shifts and supports a内核
-
Disentangling Influence: Using Disentangled Representations to Audit Model Predictions
Disentangled representations enable a new auditing procedure to identify proxy features and quantify their influence on model outcomes more effectively than prior methods.
-
Component-Based Out-of-Distribution Detection
CoOD decomposes inputs into components and applies Component Shift Score plus Compositional Consistency Score to improve detection of both standard and compositional out-of-distribution data.
-
MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework
MetaGPT embeds human SOPs into LLM prompts to create role-specialized agent teams that produce more coherent solutions on collaborative software engineering tasks than prior chat-based multi-agent systems.
-
A Dialogue between Causal and Traditional Representation Learning: Toward Mutual Benefits in a Unified Formulation
The paper introduces a unified formulation for representation learning with task and constraint components, arguing for mutual benefits between causal and traditional approaches and showing via experiments that causal constraint effectiveness depends on paired tasks.
-
Approximately Equivariant Recurrent Generative Models for Quasi-Periodic Time Series with a Progressive Training Scheme
AEQ-RVAE-ST combines approximate equivariance and progressive sequence lengthening in a recurrent VAE to match or exceed prior generative models on quasi-periodic time series benchmarks.
-
Y-Autoencoders: disentangling latent representations via sequential-encoding
Y-Autoencoders disentangle latent factors by splitting the encoder output into implicit and explicit branches before decoding, with added losses enforcing independence and label correlation.
-
AMAD: Adversarial Multiscale Anomaly Detection on High-Dimensional and Time-Evolving Categorical Data
AMAD is an end-to-end model using adversarial autoencoders and RNNs with attention for multiscale anomaly detection on time-evolving high-dimensional categorical data.
-
eXact-Prior Variational Autoencoder (X-VAE): Learning Data-Adaptive Gaussian Mixture Priors for Latent Distributions
X-VAE uses empirical statistics from a pretrained autoencoder to set a data-adaptive Gaussian prior and introduces a latent scaling factor for controllable generation.
-
Autoencoding sensory substitution
Deep recurrent autoencoders convert images to shortened audio signals that incorporate hearing models, enabling above-chance hand posture discrimination and object reaching after a few hours of training instead of months.
-
Understanding Deep Learning Techniques for Image Segmentation
A 2019 survey that categorizes and intuitively explains major deep learning techniques for image segmentation, progressing from classical methods to modern neural architectures.