Search Results for author:
Found 19 papers, 12 papers with code
Impact of Trip Distance Distribution Time Dependency and Aggregation Levels in Bathtub Models -- A Comparative Simulation Analysis
The emergence of different bathtub models has raised the question of which model can provide more robust and accurate results under different demand scenarios and network properties.
ENAT: Rethinking Spatial-temporal Interactions in Token-based Image Synthesis
At the spatial level, we disentangle the computations of visible and mask tokens by encoding visible tokens independently, while decoding mask tokens conditioned on the fully encoded visible tokens.
Taming Rectified Flow for Inversion and Editing
To address this issue, we propose RF-Solver, a novel training-free sampler that effectively enhances inversion precision by mitigating the errors in the ODE-solving process of rectified flow.
UniAutoML: A Human-Centered Framework for Unified Discriminative and Generative AutoML with Large Language Models
Additionally, these frameworks lack interpretability and user engagement during the training process, primarily due to the absence of human-centered design.
AdaNAT: Exploring Adaptive Policy for Token-Based Image Generation
As a representative work, non-autoregressive Transformers (NATs) are able to synthesize images with decent quality in a small number of steps.
On the KL-Divergence-based Robust Satisficing Model
Empirical risk minimization, a cornerstone in machine learning, is often hindered by the Optimizer's Curse stemming from discrepancies between the empirical and true data-generating distributions. To address this challenge, the robust satisficing framework has emerged recently to mitigate ambiguity in the true distribution.
Efficient Diffusion Transformer with Step-wise Dynamic Attention Mediators
In response to this observation, we present a novel diffusion transformer framework incorporating an additional set of mediator tokens to engage with queries and keys separately.
UniTTA: Unified Benchmark and Versatile Framework Towards Realistic Test-Time Adaptation
To this end, we propose a Unified Test-Time Adaptation (UniTTA) benchmark, which is comprehensive and widely applicable.
COVE: Unleashing the Diffusion Feature Correspondence for Consistent Video Editing
Specifically, we propose an efficient sliding-window-based strategy to calculate the similarity among tokens in the diffusion features of source videos, identifying the tokens with high correspondence across frames.
Revisiting Non-Autoregressive Transformers for Efficient Image Synthesis
In this paper, we aim to re-evaluate the full potential of NATs by revisiting the design of their training and inference strategies.
Everything to the Synthetic: Diffusion-driven Test-time Adaptation via Synthetic-Domain Alignment
The recently proposed diffusion-driven TTA methods mitigate this by adapting model inputs instead of weights, where an unconditional diffusion model, trained on the source domain, transforms target-domain data into a synthetic domain that is expected to approximate the source domain.
GRA: Detecting Oriented Objects through Group-wise Rotating and Attention
GRA can adaptively capture fine-grained features of objects with diverse orientations, comprising two key components: Group-wise Rotating and Group-wise Attention.
Smooth Diffusion: Crafting Smooth Latent Spaces in Diffusion Models
Specifically, we introduce Step-wise Variation Regularization to enforce the proportion between the variations of an arbitrary input latent and that of the output image is a constant at any diffusion training step.
Prompt-Free Diffusion: Taking "Text" out of Text-to-Image Diffusion Models
Text-to-image (T2I) research has grown explosively in the past year, owing to the large-scale pre-trained diffusion models and many emerging personalization and editing approaches.
Zero-shot Generative Model Adaptation via Image-specific Prompt Learning
Recently, CLIP-guided image synthesis has shown appealing performance on adapting a pre-trained source-domain generator to an unseen target domain.
Assessing a Single Image in Reference-Guided Image Synthesis
For Reference-guided Image Synthesis (RIS) tasks, i. e., rendering a source image in the style of another reference image, where assessing the quality of a single generated image is crucial, these metrics are not applicable.
Privacy-Preserving Representation Learning on Graphs: A Mutual Information Perspective
Existing representation learning methods on graphs have achieved state-of-the-art performance on various graph-related tasks such as node classification, link prediction, etc.
Meta-Semi: A Meta-learning Approach for Semi-supervised Learning
In this paper, we propose a novel meta-learning based SSL algorithm (Meta-Semi) that requires tuning only one additional hyper-parameter, compared with a standard supervised deep learning algorithm, to achieve competitive performance under various conditions of SSL.
DeepObfuscator: Obfuscating Intermediate Representations with Privacy-Preserving Adversarial Learning on Smartphones
Our experiments on CelebA and LFW datasets show that the quality of the reconstructed images from the obfuscated features of the raw image is dramatically decreased from 0. 9458 to 0. 3175 in terms of multi-scale structural similarity.
