Search Results for author:
Found 15 papers, 5 papers with code
F\^2-Softmax: Diversifying Neural Text Generation via Frequency Factorized Softmax
Despite recent advances in neural text generation, encoding the rich diversity in human language remains elusive.
Spectral Motion Alignment for Video Motion Transfer using Diffusion Models
The evolution of diffusion models has greatly impacted video generation and understanding.
Energy-Based Cross Attention for Bayesian Context Update in Text-to-Image Diffusion Models
Despite the remarkable performance of text-to-image diffusion models in image generation tasks, recent studies have raised the issue that generated images sometimes cannot capture the intended semantic contents of the text prompts, which phenomenon is often called semantic misalignment.
Training Debiased Subnetworks with Contrastive Weight Pruning
Neural networks are often biased to spuriously correlated features that provide misleading statistical evidence that does not generalize.
Ranked #2 on
Facial Attribute Classification
on bFFHQ
Self-supervised debiasing using low rank regularization
Specifically, we first pretrain a biased encoder in a self-supervised manner with the rank regularization, serving as a semantic bottleneck to enforce the encoder to learn the spuriously correlated attributes.
SAICL: Student Modelling with Interaction-level Auxiliary Contrastive Tasks for Knowledge Tracing and Dropout Prediction
Knowledge tracing and dropout prediction are crucial for online education to estimate students' knowledge states or to prevent dropout rates.
The emergence of division of labor through decentralized social sanctioning
Here we show that by introducing a model of social norms, which we regard as emergent patterns of decentralized social sanctioning, it becomes possible for groups of self-interested individuals to learn a productive division of labor involving all critical roles.
InfoGCN: Representation Learning for Human Skeleton-Based Action Recognition
Human skeleton-based action recognition offers a valuable means to understand the intricacies of human behavior because it can handle the complex relationships between physical constraints and intention.
Ranked #7 on
Skeleton Based Action Recognition
on N-UCLA
Meta-control of social learning strategies
Based on these findings, we hypothesized that meta-control of individual and social learning strategies provides effective and sample-efficient learning in volatile and uncertain environments.
Information-theoretic regularization for Multi-source Domain Adaptation
Here we adopt an information-theoretic approach to identify and resolve the potential adverse effect of the multiple domain discriminators on MDA: disintegration of domain-discriminative information, limited computational scalability, and a large variance in the gradient of the loss during training.
Reliably fast adversarial training via latent adversarial perturbation
To overcome such limitations, we deviate from the existing input-space-based adversarial training regime and propose a single-step latent adversarial training method (SLAT), which leverages the gradients of latent representation as the latent adversarial perturbation.
A Simple Unified Information Regularization Framework for Multi-Source Domain Adaptation
Our framework shows that the information shared across domains cannot be gleaned with multiple discriminators.
F^2-Softmax: Diversifying Neural Text Generation via Frequency Factorized Softmax
Despite recent advances in neural text generation, encoding the rich diversity in human language remains elusive.
End-to-End Trainable Self-Attentive Shallow Network for Text-Independent Speaker Verification
We demonstrate that the proposed model is highly efficient, and provides more accurate speaker verification than GE2E.
On the Reliability and Generalizability of Brain-inspired Reinforcement Learning Algorithms
In the reliability test, which includes the latent behavior profile and the parameter recoverability test, we showed that the prefrontal RL reliably learned the latent policies of the humans, while all the other models failed.
