Search Results for author:
Found 44 papers, 28 papers with code
GarmageNet: A Dataset and Scalable Representation for Generic Garment Modeling
High-fidelity garment modeling remains challenging due to the lack of large-scale, high-quality datasets and efficient representations capable of handling non-watertight, multi-layer geometries.
Denoising Score Distillation: From Noisy Diffusion Pretraining to One-Step High-Quality Generation
DSD first pretrains a diffusion model exclusively on noisy, corrupted samples and then distills it into a one-step generator capable of producing refined, clean outputs.
DesignDiffusion: High-Quality Text-to-Design Image Generation with Diffusion Models
In this paper, we present DesignDiffusion, a simple yet effective framework for the novel task of synthesizing design images from textual descriptions.
SmartEraser: Remove Anything from Images using Masked-Region Guidance
This paradigm retains the masked region in the input, using it as guidance for the removal process.
Enhancing and Accelerating Diffusion-Based Inverse Problem Solving through Measurements Optimization
Diffusion models have recently demonstrated notable success in solving inverse problems.
One-Step Diffusion Policy: Fast Visuomotor Policies via Diffusion Distillation
Diffusion models, praised for their success in generative tasks, are increasingly being applied to robotics, demonstrating exceptional performance in behavior cloning.
Adversarial Score identity Distillation: Rapidly Surpassing the Teacher in One Step
SiDA utilizes the encoder from the generator's score network as a discriminator, allowing it to distinguish between real images and those generated by SiD.
Ranked #1 on
Image Generation
on FFHQ 64x64
Diffusion-RPO: Aligning Diffusion Models through Relative Preference Optimization
Aligning large language models with human preferences has emerged as a critical focus in language modeling research.
Long and Short Guidance in Score identity Distillation for One-Step Text-to-Image Generation
Specifically, its data-free distillation of Stable Diffusion 1. 5 achieves a record low FID of 8. 15 on the COCO-2014 validation set, with a CLIP score of 0. 304 at an LSG scale of 1. 5, and an FID of 9. 56 with a CLIP score of 0. 313 at an LSG scale of 2.
Ranked #22 on
Text-to-Image Generation
on MS COCO
Self-Augmented Preference Optimization: Off-Policy Paradigms for Language Model Alignment
Traditional language model alignment methods, such as Direct Preference Optimization (DPO), are limited by their dependence on static, pre-collected paired preference data, which hampers their adaptability and practical applicability.
Score identity Distillation: Exponentially Fast Distillation of Pretrained Diffusion Models for One-Step Generation
This achievement not only redefines the benchmarks for efficiency and effectiveness in diffusion distillation but also in the broader field of diffusion-based generation.
Ranked #2 on
Image Generation
on AFHQ-v2 64x64
Take the Bull by the Horns: Hard Sample-Reweighted Continual Training Improves LLM Generalization
Our study starts from an empirical strategy for the light continual training of LLMs using their original pre-training data sets, with a specific focus on selective retention of samples that incur moderately high losses.
Relative Preference Optimization: Enhancing LLM Alignment through Contrasting Responses across Identical and Diverse Prompts
In the field of large language models (LLMs), aligning models with the diverse preferences of users is a critical challenge.
Anything in Any Scene: Photorealistic Video Object Insertion
Our proposed general framework encompasses three key processes: 1) integrating a realistic object into a given scene video with proper placement to ensure geometric realism; 2) estimating the sky and environmental lighting distribution and simulating realistic shadows to enhance the light realism; 3) employing a style transfer network that refines the final video output to maximize photorealism.
Improving In-Context Learning in Diffusion Models with Visual Context-Modulated Prompts
In light of the remarkable success of in-context learning in large language models, its potential extension to the vision domain, particularly with visual foundation models like Stable Diffusion, has sparked considerable interest.
Counterfactual Explanations for Time Series Forecasting
In this paper, we formulate the novel problem of counterfactual generation for time series forecasting, and propose an algorithm, called ForecastCF, that solves the problem by applying gradient-based perturbations to the original time series.
Learning Stackable and Skippable LEGO Bricks for Efficient, Reconfigurable, and Variable-Resolution Diffusion Modeling
Diffusion models excel at generating photo-realistic images but come with significant computational costs in both training and sampling.
Ranked #13 on
Image Generation
on CelebA 64x64
Beta Diffusion
We introduce beta diffusion, a novel generative modeling method that integrates demasking and denoising to generate data within bounded ranges.
AltFreezing for More General Video Face Forgery Detection
In this paper, we propose to capture both spatial and temporal artifacts in one model for face forgery detection.
MPPN: Multi-Resolution Periodic Pattern Network For Long-Term Time Series Forecasting
To capture the intrinsic patterns of time series, we propose a novel deep learning network architecture, named Multi-resolution Periodic Pattern Network (MPPN), for long-term series forecasting.
In-Context Learning Unlocked for Diffusion Models
We present Prompt Diffusion, a framework for enabling in-context learning in diffusion-based generative models.
Patch Diffusion: Faster and More Data-Efficient Training of Diffusion Models
Patch Diffusion meanwhile improves the performance of diffusion models trained on relatively small datasets, $e. g.$, as few as 5, 000 images to train from scratch.
Collaborative Multi-BS Power Management for Dense Radio Access Network using Deep Reinforcement Learning
Network energy efficiency is a main pillar in the design and operation of wireless communication systems.
SuperpixelGraph: Semi-automatic generation of building footprint through semantic-sensitive superpixel and neural graph networks
Most urban applications necessitate building footprints in the form of concise vector graphics with sharp boundaries rather than pixel-wise raster images.
DIRE for Diffusion-Generated Image Detection
We find that existing detectors struggle to detect images generated by diffusion models, even if we include generated images from a specific diffusion model in their training data.
Adaptive Hybrid Spatial-Temporal Graph Neural Network for Cellular Traffic Prediction
First, we apply adaptive hybrid graph learning to learn the compound spatial correlations among cell towers.
Style-transfer counterfactual explanations: An application to mortality prevention of ICU patients
In this paper, we propose a counterfactual solution MedSeqCF for preventing the mortality of three cohorts of ICU patients, by representing their electronic health records as medical event sequences, and generating counterfactuals by adopting and employing a text style-transfer technique.
Diffusion Policies as an Expressive Policy Class for Offline Reinforcement Learning
In our approach, we learn an action-value function and we add a term maximizing action-values into the training loss of the conditional diffusion model, which results in a loss that seeks optimal actions that are near the behavior policy.
Probabilistic Conformal Prediction Using Conditional Random Samples
This paper proposes probabilistic conformal prediction (PCP), a predictive inference algorithm that estimates a target variable by a discontinuous predictive set.
Diffusion-GAN: Training GANs with Diffusion
Both the observed and generated data are diffused by the same adaptive diffusion process.
Ranked #1 on
Image Generation
on LSUN Bedroom 256 x 256
Network Topology Optimization via Deep Reinforcement Learning
A2C-GS consists of three novel components, including a verifier to validate the correctness of a generated network topology, a graph neural network (GNN) to efficiently approximate topology rating, and a DRL actor layer to conduct a topology search.
Learning Enriched Illuminants for Cross and Single Sensor Color Constancy
Color constancy aims to restore the constant colors of a scene under different illuminants.
Enabling Efficient Deep Convolutional Neural Network-based Sensor Fusion for Autonomous Driving
We also propose a Layer-sharing technique in the deep layer that can achieve better accuracy with less computational overhead.
A Behavior Regularized Implicit Policy for Offline Reinforcement Learning
For training more effective agents, we propose a framework that supports learning a flexible yet well-regularized fully-implicit policy.
Learning Time Series Counterfactuals via Latent Space Representations
Counterfactual explanations can provide sample-based explanations of features required to modify from the original sample to change the classification result from an undesired state to a desired state; hence it provides interpretability of the model.
State-Action Joint Regularized Implicit Policy for Offline Reinforcement Learning
For training more effective agents, we propose a framework that supports learning a flexible and well-regularized policy, which consists of a fully implicit policy and a regularization through the state-action visitation frequency induced by the current policy and that induced by the data-collecting behavior policy.
Counterfactual Explanations for Survival Prediction of Cardiovascular ICU Patients
In recent years, machine learning methods have been rapidly implemented in the medical domain.
Uformer: A General U-Shaped Transformer for Image Restoration
Powered by these two designs, Uformer enjoys a high capability for capturing both local and global dependencies for image restoration.
Ranked #3 on
Deblurring
on RealBlur-R (trained on GoPro)
LID 2020: The Learning from Imperfect Data Challenge Results
The purpose of the Learning from Imperfect Data (LID) workshop is to inspire and facilitate the research in developing novel approaches that would harness the imperfect data and improve the data-efficiency during training.
Implicit Distributional Reinforcement Learning
To improve the sample efficiency of policy-gradient based reinforcement learning algorithms, we propose implicit distributional actor-critic (IDAC) that consists of a distributional critic, built on two deep generator networks (DGNs), and a semi-implicit actor (SIA), powered by a flexible policy distribution.
Leveraging Photogrammetric Mesh Models for Aerial-Ground Feature Point Matching Toward Integrated 3D Reconstruction
Second, aerial models are rendered to the initial ground views, in which the color, depth and normal images are obtained.
Adaptive Correlated Monte Carlo for Contextual Categorical Sequence Generation
To stabilize this method, we adapt to contextual generation of categorical sequences a policy gradient estimator, which evaluates a set of correlated Monte Carlo (MC) rollouts for variance control.
Thompson Sampling via Local Uncertainty
Variational inference is used to approximate the posterior of the local variable, and semi-implicit structure is further introduced to enhance its expressiveness.
