Search Results for author:
Found 53 papers, 20 papers with code
Survey of Video Diffusion Models: Foundations, Implementations, and Applications
Recent advances in diffusion models have revolutionized video generation, offering superior temporal consistency and visual quality compared to traditional generative adversarial networks-based approaches.
FreSca: Unveiling the Scaling Space in Diffusion Models
Diffusion models offer impressive controllability for image tasks, primarily through noise predictions that encode task-specific information and classifier-free guidance enabling adjustable scaling.
Lux Post Facto: Learning Portrait Performance Relighting with Conditional Video Diffusion and a Hybrid Dataset
In this work, we introduce Lux Post Facto, a novel portrait video relighting method that produces both photorealistic and temporally consistent lighting effects.
Go-with-the-Flow: Motion-Controllable Video Diffusion Models Using Real-Time Warped Noise
The efficiency of our algorithm enables us to fine-tune modern video diffusion base models using warped noise with minimal overhead, and provide a one-stop solution for a wide range of user-friendly motion control: local object motion control, global camera movement control, and motion transfer.
A partial likelihood approach to tree-based density modeling and its application in Bayesian inference
Tree-based priors for probability distributions are usually specified using a predetermined, data-independent collection of candidate recursive partitions of the sample space.
Fitting Spherical Gaussians to Dynamic HDRI Sequences
We present a technique for fitting high dynamic range illumination (HDRI) sequences using anisotropic spherical Gaussians (ASGs) while preserving temporal consistency in the compressed HDRI maps.
Boosting 3D Object Generation through PBR Materials
By analyzing the components of PBR materials, we choose to consider albedo, roughness, metalness, and bump maps.
DifFRelight: Diffusion-Based Facial Performance Relighting
We present a novel framework for free-viewpoint facial performance relighting using diffusion-based image-to-image translation.
Stream-level flow matching with Gaussian processes
Conditional flow matching (CFM) exploits the fact that the marginal vector field of a CNF can be learned by fitting least-squares regression to the conditional vector field specified given one or both ends of the flow path.
Fisheye-GS: Lightweight and Extensible Gaussian Splatting Module for Fisheye Cameras
However, adapting 3DGS to different camera models, particularly fisheye lenses, poses challenges due to the unique 3D to 2D projection calculation.
EA-RAS: Towards Efficient and Accurate End-to-End Reconstruction of Anatomical Skeleton
In this work, we also develop a progressive training strategy and integrated it with an enhanced optimization process, enabling the network to obtain initial weights using only a small skin dataset and achieve self-supervision in skeleton reconstruction.
Histology Virtual Staining with Mask-Guided Adversarial Transfer Learning for Tertiary Lymphoid Structure Detection
Capitalizing on the prevalence of H&E staining slides, we introduce a novel Mask-Guided Adversarial Transfer Learning method designed for virtual pathological staining.
P/D-Serve: Serving Disaggregated Large Language Model at Scale
To overcome previous problems, this paper proposes an end-to-end system P/D-Serve, complying with the paradigm of MLOps (machine learning operations), which models end-to-end (E2E) P/D performance and enables: 1) fine-grained P/D organization, mapping the service with RoCE (RDMA over converged ethernet) as needed, to facilitate similar processing and dynamic adjustments on P/D ratios; 2) on-demand forwarding upon rejections for idle prefill, decoupling the scheduler from regular inaccurate reports and local queues, to avoid timeouts in prefill; and 3) efficient KVCache transfer via optimized D2D access.
Efficient Decision Trees for Tensor Regressions
We proposed the tensor-input tree (TT) method for scalar-on-tensor and tensor-on-tensor regression problems.
An Application of Large Language Models to Coding Negotiation Transcripts
In recent years, Large Language Models (LLM) have demonstrated impressive capabilities in the field of natural language processing (NLP).
Establishing Rigorous and Cost-effective Clinical Trials for Artificial Intelligence Models
We envision DC-AI RCTs and VC-MedAI as pivotal advancements, presenting innovative and transformative evaluation methodologies for AI models in clinical practice, offering a preclinical-like setting mirroring conventional medicine, and reshaping development paradigms in a cost-effective and fast-iterative manner.
Turbo Sparse: Achieving LLM SOTA Performance with Minimal Activated Parameters
By applying our neuron sparsification method to the Mistral and Mixtral models, only 2. 5 billion and 4. 3 billion parameters are activated per inference iteration, respectively, while achieving even more powerful model performance.
Generative modeling of density regression through tree flows
A common objective in the analysis of tabular data is estimating the conditional distribution (in contrast to only producing predictions) of a set of "outcome" variables given a set of "covariates", which is sometimes referred to as the "density regression" problem.
Experimental investigation of trans-scale displacement responses of wrinkle defects in fiber reinforced composite laminates
Wrinkle defects were found widely exist in the field of industrial products, i. e. wind turbine blades and filament-wound composite pressure vessels.
Sensitivity Decouple Learning for Image Compression Artifacts Reduction
Different from these methods, we propose to decouple the intrinsic attributes into two complementary features for artifacts reduction, ie, the compression-insensitive features to regularize the high-level semantic representations during training and the compression-sensitive features to be aware of the compression degree.
InternLM2 Technical Report
The evolution of Large Language Models (LLMs) like ChatGPT and GPT-4 has sparked discussions on the advent of Artificial General Intelligence (AGI).
Ranked #5 on
Long-Context Understanding
on Ada-LEval (BestAnswer)
UV Gaussians: Joint Learning of Mesh Deformation and Gaussian Textures for Human Avatar Modeling
Therefore, we propose UV Gaussians, which models the 3D human body by jointly learning mesh deformations and 2D UV-space Gaussian textures.
Mixture of Link Predictors on Graphs
Link prediction, which aims to forecast unseen connections in graphs, is a fundamental task in graph machine learning.
SpecNeRF: Gaussian Directional Encoding for Specular Reflections
We show that our Gaussian directional encoding and geometry prior significantly improve the modeling of challenging specular reflections in neural radiance fields, which helps decompose appearance into more physically meaningful components.
Alteration Detection of Tensor Dependence Structure via Sparsity-Exploited Reranking Algorithm
Tensor-valued data arise frequently from a wide variety of scientific applications, and many among them can be translated into an alteration detection problem of tensor dependence structures.
OpenClinicalAI: An Open and Dynamic Model for Alzheimer's Disease Diagnosis
Thus, the AD diagnosis task is tangled and coupled with the diagnosis strategy formulation.
OpenAPMax: Abnormal Patterns-based Model for Real-World Alzheimer's Disease Diagnosis
Alzheimer's disease (AD) cannot be reversed, but early diagnosis will significantly benefit patients' medical treatment and care.
Picking Up Quantization Steps for Compressed Image Classification
The sensitivity of deep neural networks to compressed images hinders their usage in many real applications, which means classification networks may fail just after taking a screenshot and saving it as a compressed file.
3D Video Loops from Asynchronous Input
Looping videos are short video clips that can be looped endlessly without visible seams or artifacts.
Neural Parameterization for Dynamic Human Head Editing
Implicit radiance functions emerged as a powerful scene representation for reconstructing and rendering photo-realistic views of a 3D scene.
TVConv: Efficient Translation Variant Convolution for Layout-aware Visual Processing
Extensive experiments on face recognition show that TVConv reduces the computational cost by up to 3. 1x and improves the corresponding throughput by 2. 3x while maintaining a high accuracy compared to the depthwise convolution.
Deblur-NeRF: Neural Radiance Fields from Blurry Images
We demonstrate that our method can be used on both camera motion blur and defocus blur: the two most common types of blur in real scenes.
Microbiome subcommunity learning with logistic-tree normal latent Dirichlet allocation
As a result, LDA can produce inference which is highly sensitive to the specification of the number of subcommunities and often divides a single subcommunity into multiple artificial ones.
OpenClinicalAI: enabling AI to diagnose diseases in real-world clinical settings
In the real-world clinical setting, OpenClinicalAI significantly outperforms the state-of-the-art AI system.
Amplitude-Phase Recombination: Rethinking Robustness of Convolutional Neural Networks in Frequency Domain
This observation leads to more explanations of the CNN's generalization behaviors in both robustness to common perturbations and out-of-distribution detection, and motivates a new perspective on data augmentation designed by re-combing the phase spectrum of the current image and the amplitude spectrum of the distracter image.
Ranked #7 on
Out-of-Distribution Detection
on CIFAR-10
SciConceptMiner: A system for large-scale scientific concept discovery
In this paper, we introduce a self-supervised end-to-end system, SciConceptMiner, for the automatic capture of emerging scientific concepts from both independent knowledge sources (semi-structured data) and academic publications (unstructured documents).
Distillation based Multi-task Learning: A Candidate Generation Model for Improving Reading Duration
One solution to this problem is to model the click and the reading duration simultaneously under the multi-task learning (MTL) framework.
Unsupervised tree boosting for learning probability distributions
We propose an unsupervised tree boosting algorithm for inferring the underlying sampling distribution of an i. i. d.
Stability property and Dirichlet problem for translating solitons
In this paper, we prove that the infimum of the mean curvature is zero for a translating solitons of hypersurface in $\re^{n+k}$.
Differential Geometry Analysis of PDEs translating solitons, stability, non-splitting, Dirichlet problem
Yamabe metrics, Fine solutions to the Yamabe flow, and local L1-stability
In this paper, we study the existence of complete Yamabe metric with zero scalar curvature on an n-dimensional complete Riemannian manifold $(M, g_0)$, $n\geq 3$.
Differential Geometry Analysis of PDEs 53C44, 53C20, 35Jxx, 35K50, 58J20
Two solutions to Kazdan-Warner's problem on surfaces
In this paper, we study the sign-changing Kazdan-Warner's problem on two dimensional closed Riemannian manifold with negative Euler number $\chi(M)<0$.
Differential Geometry Analysis of PDEs 53C20, 35J60, 58G99
Dirichlet-tree multinomial mixtures for clustering microbiome compositions
A common routine in microbiome research is to identify reproducible patterns in the population through unsupervised clustering of samples.
Methodology Applications
Privacy-preserving collaborative machine learning on genomic data using TensorFlow
Machine learning (ML) methods have been widely used in genomic studies.
Cryptography and Security
CARP: Compression through Adaptive Recursive Partitioning for Multi-dimensional Images
Fast and effective image compression for multi-dimensional images has become increasingly important for efficient storage and transfer of massive amounts of high-resolution images and videos.
Extreme Learning Machine-Based Heterogeneous Domain Adaptation for Classification of Hyperspectral Images
An extreme learning machine (ELM)-based heterogeneous domain adaptation (HDA) algorithm is proposed for the classification of remote sensing images.
Kingsoft's Neural Machine Translation System for WMT19
This paper describes the Kingsoft AI Lab{'}s submission to the WMT2019 news translation shared task.
POI Semantic Model with a Deep Convolutional Structure
An accurate similarity calculation is challenging since the mismatch between a query and a retrieval text may exist in the case of a mistyped query or an alias inquiry.
Multiscale Fisher's Independence Test for Multivariate Dependence
Identifying dependency in multivariate data is a common inference task that arises in numerous applications.
Bayesian graphical compositional regression for microbiome data
An important task in microbiome studies is to test the existence of and give characterization to differences in the microbiome composition across groups of samples.
Methodology Applications Computation
Learning Asymmetric and Local Features in Multi-Dimensional Data through Wavelets with Recursive Partitioning
Effective learning of asymmetric and local features in images and other data observed on multi-dimensional grids is a challenging objective critical for a wide range of image processing applications involving biomedical and natural images.
Mixture modeling on related samples by $ψ$-stick breaking and kernel perturbation
We introduce two techniques for incorporating these features in modeling related data samples using kernel mixtures.
Recursive partitioning and multi-scale modeling on conditional densities
We introduce a nonparametric prior on the conditional distribution of a (univariate or multivariate) response given a set of predictors.
Methodology Statistics Theory Computation Statistics Theory
Efficient functional ANOVA through wavelet-domain Markov groves
We introduce a wavelet-domain functional analysis of variance (fANOVA) method based on a Bayesian hierarchical model.
