Search Results for author:
Found 31 papers, 20 papers with code
Analyzing and Improving Model Collapse in Rectified Flow Models
Generative models aim to produce synthetic data indistinguishable from real distributions, but iterative training on self-generated data can lead to \emph{model collapse (MC)}, where performance degrades over time.
OFER: Occluded Face Expression Reconstruction
In this paper we introduce OFER, a novel approach for single image 3D face reconstruction that can generate plausible, diverse, and expressive 3D faces, even under strong occlusions.
HESSO: Towards Automatic Efficient and User Friendly Any Neural Network Training and Pruning
Meanwhile, CRIC can effectively prevent the irreversible performance collapse and further enhance the performance of HESSO on certain applications.
Probing the Robustness of Vision-Language Pretrained Models: A Multimodal Adversarial Attack Approach
In this paper, we study the adversarial vulnerability of recent VLP transformers and design a novel Joint Multimodal Transformer Feature Attack (JMTFA) that concurrently introduces adversarial perturbations in both visual and textual modalities under white-box settings.
VERA: Validation and Evaluation of Retrieval-Augmented Systems
The increasing use of Retrieval-Augmented Generation (RAG) systems in various applications necessitates stringent protocols to ensure RAG systems accuracy, safety, and alignment with user intentions.
3D Gaussian Splatting: Survey, Technologies, Challenges, and Opportunities
3D Gaussian Splatting (3DGS) has emerged as a prominent technique with the potential to become a mainstream method for 3D representations.
FORA: Fast-Forward Caching in Diffusion Transformer Acceleration
Diffusion transformers (DiT) have become the de facto choice for generating high-quality images and videos, largely due to their scalability, which enables the construction of larger models for enhanced performance.
AdaContour: Adaptive Contour Descriptor with Hierarchical Representation
Existing angle-based contour descriptors suffer from lossy representation for non-starconvex shapes.
S3Editor: A Sparse Semantic-Disentangled Self-Training Framework for Face Video Editing
S3Editor is model-agnostic and compatible with various editing approaches.
ONNXPruner: ONNX-Based General Model Pruning Adapter
However, the practical application of these algorithms across various models and platforms remains a significant challenge.
Exploiting Inter-sample and Inter-feature Relations in Dataset Distillation
However, these methods face two primary limitations: the dispersed feature distribution within the same class in synthetic datasets, reducing class discrimination, and an exclusive focus on mean feature consistency, lacking precision and comprehensiveness.
OTOv3: Automatic Architecture-Agnostic Neural Network Training and Compression from Structured Pruning to Erasing Operators
Compressing a predefined deep neural network (DNN) into a compact sub-network with competitive performance is crucial in the efficient machine learning realm.
The Efficiency Spectrum of Large Language Models: An Algorithmic Survey
The rapid growth of Large Language Models (LLMs) has been a driving force in transforming various domains, reshaping the artificial general intelligence landscape.
DREAM: Diffusion Rectification and Estimation-Adaptive Models
We present DREAM, a novel training framework representing Diffusion Rectification and Estimation Adaptive Models, requiring minimal code changes (just three lines) yet significantly enhancing the alignment of training with sampling in diffusion models.
CaesarNeRF: Calibrated Semantic Representation for Few-shot Generalizable Neural Rendering
Generalizability and few-shot learning are key challenges in Neural Radiance Fields (NeRF), often due to the lack of a holistic understanding in pixel-level rendering.
LoRAShear: Efficient Large Language Model Structured Pruning and Knowledge Recovery
Large Language Models (LLMs) have transformed the landscape of artificial intelligence, while their enormous size presents significant challenges in terms of computational costs.
InsertNeRF: Instilling Generalizability into NeRF with HyperNet Modules
By utilizing multiple plug-and-play HyperNet modules, InsertNeRF dynamically tailors NeRF's weights to specific reference scenes, transforming multi-scale sampling-aware features into scene-specific representations.
Where and How: Mitigating Confusion in Neural Radiance Fields from Sparse Inputs
Neural Radiance Fields from Sparse input} (NeRF-S) have shown great potential in synthesizing novel views with a limited number of observed viewpoints.
Automated Search-Space Generation Neural Architecture Search
To search an optimal sub-network within a general deep neural network (DNN), existing neural architecture search (NAS) methods typically rely on handcrafting a search space beforehand.
OTOV2: Automatic, Generic, User-Friendly
We propose the second generation of Only-Train-Once (OTOv2), which first automatically trains and compresses a general DNN only once from scratch to produce a more compact model with competitive performance without fine-tuning.
Sparsity-guided Network Design for Frame Interpolation
As a result, we achieve a considerable performance gain with a quarter of the size of the original AdaCoF.
RSTT: Real-time Spatial Temporal Transformer for Space-Time Video Super-Resolution
Space-time video super-resolution (STVSR) is the task of interpolating videos with both Low Frame Rate (LFR) and Low Resolution (LR) to produce High-Frame-Rate (HFR) and also High-Resolution (HR) counterparts.
Ranked #2 on
Space-time Video Super-resolution
on Vimeo90K-Medium
On the Optimization Landscape of Neural Collapse under MSE Loss: Global Optimality with Unconstrained Features
When training deep neural networks for classification tasks, an intriguing empirical phenomenon has been widely observed in the last-layer classifiers and features, where (i) the class means and the last-layer classifiers all collapse to the vertices of a Simplex Equiangular Tight Frame (ETF) up to scaling, and (ii) cross-example within-class variability of last-layer activations collapses to zero.
Only Train Once: A One-Shot Neural Network Training And Pruning Framework
Structured pruning is a commonly used technique in deploying deep neural networks (DNNs) onto resource-constrained devices.
A Geometric Analysis of Neural Collapse with Unconstrained Features
In contrast to existing landscape analysis for deep neural networks which is often disconnected from practice, our analysis of the simplified model not only does it explain what kind of features are learned in the last layer, but it also shows why they can be efficiently optimized in the simplified settings, matching the empirical observations in practical deep network architectures.
CDFI: Compression-Driven Network Design for Frame Interpolation
DNN-based frame interpolation--that generates the intermediate frames given two consecutive frames--typically relies on heavy model architectures with a huge number of features, preventing them from being deployed on systems with limited resources, e. g., mobile devices.
Ranked #1 on
Video Frame Interpolation
on Middlebury
(LPIPS metric)
A Half-Space Stochastic Projected Gradient Method for Group Sparsity Regularization
Optimizing with group sparsity is significant in enhancing model interpretability in machining learning applications, e. g., feature selection, compressed sensing and model compression.
Neural Network Compression Via Sparse Optimization
The compression of deep neural networks (DNNs) to reduce inference cost becomes increasingly important to meet realistic deployment requirements of various applications.
Early Detection of Sepsis using Ensemblers
This paper describes a methodology to detect sepsis ahead of time by analyzing hourly patient records.
Orthant Based Proximal Stochastic Gradient Method for $\ell_1$-Regularized Optimization
Sparsity-inducing regularization problems are ubiquitous in machine learning applications, ranging from feature selection to model compression.
A Linearly Convergent Method for Non-Smooth Non-Convex Optimization on the Grassmannian with Applications to Robust Subspace and Dictionary Learning
Minimizing a non-smooth function over the Grassmannian appears in many applications in machine learning.
