Search Results for author:
Found 27 papers, 10 papers with code
Blind Inverse Problem Solving Made Easy by Text-to-Image Latent Diffusion
Blind inverse problems, where both the target data and forward operator are unknown, are crucial to many computer vision applications.
Subspace Optimization for Large Language Models with Convergence Guarantees
Subspace optimization algorithms, with GaLore (Zhao et al., 2024) as a representative method, have gained popularity for pre-training or fine-tuning large language models (LLMs) due to their memory efficiency.
PianoBART: Symbolic Piano Music Generation and Understanding with Large-Scale Pre-Training
Learning musical structures and composition patterns is necessary for both music generation and understanding, but current methods do not make uniform use of learned features to generate and comprehend music simultaneously.
Automated Black-box Prompt Engineering for Personalized Text-to-Image Generation
Prompt engineering is effective for controlling the output of text-to-image (T2I) generative models, but it is also laborious due to the need for manually crafted prompts.
Weather Prediction with Diffusion Guided by Realistic Forecast Processes
Weather forecasting remains a crucial yet challenging domain, where recently developed models based on deep learning (DL) have approached the performance of traditional numerical weather prediction (NWP) models.
Manifold Preserving Guided Diffusion
Despite the recent advancements, conditional image generation still faces challenges of cost, generalizability, and the need for task-specific training.
Towards reporting bias in visual-language datasets: bimodal augmentation by decoupling object-attribute association
In this paper, we focus on the wide existence of reporting bias in visual-language datasets, embodied as the object-attribute association, which can subsequentially degrade models trained on them.
Consistency Trajectory Models: Learning Probability Flow ODE Trajectory of Diffusion
Consistency Models (CM) (Song et al., 2023) accelerate score-based diffusion model sampling at the cost of sample quality but lack a natural way to trade-off quality for speed.
Ranked #1 on
Image Generation
on ImageNet 64x64
(NFE metric)
Sphere2Vec: A General-Purpose Location Representation Learning over a Spherical Surface for Large-Scale Geospatial Predictions
So when applied to large-scale real-world GPS coordinate datasets, which require distance metric learning on the spherical surface, both types of models can fail due to the map projection distortion problem (2D) and the spherical-to-Euclidean distance approximation error (3D).
Localized Text-to-Image Generation for Free via Cross Attention Control
Despite the tremendous success in text-to-image generative models, localized text-to-image generation (that is, generating objects or features at specific locations in an image while maintaining a consistent overall generation) still requires either explicit training or substantial additional inference time.
Unbiased Compression Saves Communication in Distributed Optimization: When and How Much?
Our results reveal that using independent unbiased compression can reduce the total communication cost by a factor of up to $\Theta(\sqrt{\min\{n, \kappa\}})$ when all local smoothness constants are constrained by a common upper bound, where $n$ is the number of workers and $\kappa$ is the condition number of the functions being minimized.
Lower Bounds and Accelerated Algorithms in Distributed Stochastic Optimization with Communication Compression
In this paper, we investigate the performance limit of distributed stochastic optimization algorithms employing communication compression.
CSP: Self-Supervised Contrastive Spatial Pre-Training for Geospatial-Visual Representations
To directly leverage the abundant geospatial information associated with images in pre-training, fine-tuning, and inference stages, we present Contrastive Spatial Pre-Training (CSP), a self-supervised learning framework for geo-tagged images.
Passive Non-line-of-sight Imaging for Moving Targets with an Event Camera
Non-line-of-sight (NLOS) imaging is an emerging technique for detecting objects behind obstacles or around corners.
Neural Generation Meets Real People: Building a Social, Informative Open-Domain Dialogue Agent
We present Chirpy Cardinal, an open-domain social chatbot.
SatMAE: Pre-training Transformers for Temporal and Multi-Spectral Satellite Imagery
Unsupervised pre-training methods for large vision models have shown to enhance performance on downstream supervised tasks.
Tracking Urbanization in Developing Regions with Remote Sensing Spatial-Temporal Super-Resolution
Automated tracking of urban development in areas where construction information is not available became possible with recent advancements in machine learning and remote sensing.
Comparing Distributions by Measuring Differences that Affect Decision Making
Measuring the discrepancy between two probability distributions is a fundamental problem in machine learning and statistics.
Sphere2Vec: Self-Supervised Location Representation Learning on Spherical Surfaces
Location encoding is valuable for a multitude of tasks where both the absolute positions and local contexts (image, text, and other types of metadata) of spatial objects are needed for accurate predictions.
SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equations
The key challenge is balancing faithfulness to the user input (e. g., hand-drawn colored strokes) and realism of the synthesized image.
Spatial-Temporal Super-Resolution of Satellite Imagery via Conditional Pixel Synthesis
High-resolution satellite imagery has proven useful for a broad range of tasks, including measurement of global human population, local economic livelihoods, and biodiversity, among many others.
Can we observe the QCD phase transition-generated gravitational waves through pulsar timing arrays?
This is further made possible by our findings of shallower spectra proportional to the square root of the frequency for nonhelical hydromagnetic turbulence.
Cosmology and Nongalactic Astrophysics High Energy Physics - Phenomenology Fluid Dynamics
Relic gravitational waves from the chiral magnetic effect
Here we treat magnetic field generation through the chiral magnetic effect (CME) as a generic mechanism and explore its dependence on the speed of generation (the product of magnetic diffusivity and characteristic wavenumber) and the speed characterizing the maximum magnetic field strength expected from the CME.
Cosmology and Nongalactic Astrophysics High Energy Astrophysical Phenomena General Relativity and Quantum Cosmology
Motion-Based Handwriting Recognition and Word Reconstruction
In this project, we leverage a trained single-letter classifier to predict the written word from a continuously written word sequence, by designing a word reconstruction pipeline consisting of a dynamic-programming algorithm and an auto-correction model.
Motion-Based Handwriting Recognition
We attempt to overcome the restriction of requiring a writing surface for handwriting recognition.
H-divergence: A Decision-Theoretic Discrepancy Measure for Two Sample Tests
Based on ideas from decision theory, we investigate a new class of discrepancies that are based on the optimal decision loss.
Fine-grained Image-to-Image Transformation towards Visual Recognition
In this paper, we aim at transforming an image with a fine-grained category to synthesize new images that preserve the identity of the input image, which can thereby benefit the subsequent fine-grained image recognition and few-shot learning tasks.
