Search Results for author:
Found 27 papers, 16 papers with code
Intrinsic Gradient Compression for Scalable and Efficient Federated Learning
Federated learning is a rapidly growing area of research, holding the promise of privacy-preserving distributed training on edge devices.
DreamBeast: Distilling 3D Fantastical Animals with Part-Aware Knowledge Transfer
Existing SDS methods often struggle with this generation task due to a limited understanding of part-level semantics in text-to-image diffusion models.
Modeling Real-Time Interactive Conversations as Timed Diarized Transcripts
Chatbots built upon language models have exploded in popularity, but they have largely been limited to synchronous, turn-by-turn dialogues.
GES: Generalized Exponential Splatting for Efficient Radiance Field Rendering
With the aid of a frequency-modulated loss, GES achieves competitive performance in novel-view synthesis benchmarks while requiring less than half the memory storage of Gaussian Splatting and increasing the rendering speed by up to 39%.
IM-3D: Iterative Multiview Diffusion and Reconstruction for High-Quality 3D Generation
A mitigation is to fine-tune the 2D generator to be multi-view aware, which can help distillation or can be combined with reconstruction networks to output 3D objects directly.
Fixed Point Diffusion Models
We introduce the Fixed Point Diffusion Model (FPDM), a novel approach to image generation that integrates the concept of fixed point solving into the framework of diffusion-based generative modeling.
GES : Generalized Exponential Splatting for Efficient Radiance Field Rendering
With the aid of a frequency-modulated loss GES achieves competitive performance in novel-view synthesis benchmarks while requiring less than half the memory storage of Gaussian Splatting and increasing the rendering speed by up to 39%.
Understanding Self-Supervised Features for Learning Unsupervised Instance Segmentation
Self-supervised learning (SSL) can be used to solve complex visual tasks without human labels.
Ranked #3 on
Unsupervised Instance Segmentation
on COCO val2017
A Benchmark for Learning to Translate a New Language from One Grammar Book
In this paper, we introduce MTOB (Machine Translation from One Book), a benchmark for learning to translate between English and Kalamang -- a language with less than 200 speakers and therefore virtually no presence on the web -- using several hundred pages of field linguistics reference materials.
Augmenting medical image classifiers with synthetic data from latent diffusion models
While hundreds of artificial intelligence (AI) algorithms are now approved or cleared by the US Food and Drugs Administration (FDA), many studies have shown inconsistent generalization or latent bias, particularly for underrepresented populations.
$PC^2$: Projection-Conditioned Point Cloud Diffusion for Single-Image 3D Reconstruction
Reconstructing the 3D shape of an object from a single RGB image is a long-standing and highly challenging problem in computer vision.
RealFusion: 360° Reconstruction of Any Object from a Single Image
We consider the problem of reconstructing a full 360{\deg} photographic model of an object from a single image of it.
RealFusion: 360deg Reconstruction of Any Object From a Single Image
We consider the problem of reconstructing a full 360deg photographic model of an object from a single image of it.
PC2: Projection-Conditioned Point Cloud Diffusion for Single-Image 3D Reconstruction
Reconstructing the 3D shape of an object from a single RGB image is a long-standing problem in computer vision.
Follow the Wisdom of the Crowd: Effective Text Generation via Minimum Bayes Risk Decoding
In open-ended natural-language generation, existing text decoding methods typically struggle to produce text which is both diverse and high-quality.
The Harvard USPTO Patent Dataset: A Large-Scale, Well-Structured, and Multi-Purpose Corpus of Patent Applications
Innovation is a major driver of economic and social development, and information about many kinds of innovation is embedded in semi-structured data from patents and patent applications.
Prompt-and-Rerank: A Method for Zero-Shot and Few-Shot Arbitrary Textual Style Transfer with Small Language Models
We propose a method for arbitrary textual style transfer (TST)--the task of transforming a text into any given style--utilizing general-purpose pre-trained language models.
Deep Spectral Methods: A Surprisingly Strong Baseline for Unsupervised Semantic Segmentation and Localization
We find that these eigenvectors already decompose an image into meaningful segments, and can be readily used to localize objects in a scene.
Intrinisic Gradient Compression for Federated Learning
Federated learning is a rapidly-growing area of research which enables a large number of clients to jointly train a machine learning model on privately-held data.
PixMatch: Unsupervised Domain Adaptation via Pixelwise Consistency Training
In this work, we present a novel framework for unsupervised domain adaptation based on the notion of target-domain consistency training.
Ranked #29 on
Synthetic-to-Real Translation
on SYNTHIA-to-Cityscapes
Finding an Unsupervised Image Segmenter in Each of Your Deep Generative Models
Recent research has shown that numerous human-interpretable directions exist in the latent space of GANs.
Do You Even Need Attention? A Stack of Feed-Forward Layers Does Surprisingly Well on ImageNet
These results indicate that aspects of vision transformers other than attention, such as the patch embedding, may be more responsible for their strong performance than previously thought.
Ranked #967 on
Image Classification
on ImageNet
The Mathematical Foundations of Manifold Learning
Manifold learning is a popular and quickly-growing subfield of machine learning based on the assumption that one's observed data lie on a low-dimensional manifold embedded in a higher-dimensional space.
Show, Edit and Tell: A Framework for Editing Image Captions
Specifically, our caption-editing model consisting of two sub-modules: (1) EditNet, a language module with an adaptive copy mechanism (Copy-LSTM) and a Selective Copy Memory Attention mechanism (SCMA), and (2) DCNet, an LSTM-based denoising auto-encoder.
Generation-Distillation for Efficient Natural Language Understanding in Low-Data Settings
Recent research points to knowledge distillation as a potential solution, showing that when training data for a given task is abundant, it is possible to distill a large (teacher) LM into a small task-specific (student) network with minimal loss of performance.
Encoder-Agnostic Adaptation for Conditional Language Generation
Large pretrained language models have changed the way researchers approach discriminative natural language understanding tasks, leading to the dominance of approaches that adapt a pretrained model for arbitrary downstream tasks.
Training for Diversity in Image Paragraph Captioning
Image paragraph captioning models aim to produce detailed descriptions of a source image.
