Chenlin Meng
YOU?
Author Swipe
View article: LOCA: Logical Chain Augmentation for Scientific Corpus Cleaning
LOCA: Logical Chain Augmentation for Scientific Corpus Cleaning Open
While Large Language Models (LLMs) excel in general domains, their reliability often falls short in scientific problem-solving. The advancement of scientific AI depends on large-scale, high-quality corpora. However, existing scientific que…
View article: Image Regeneration: Evaluating Text-to-Image Model via Generating Identical Image with Multimodal Large Language Models
Image Regeneration: Evaluating Text-to-Image Model via Generating Identical Image with Multimodal Large Language Models Open
Diffusion models have revitalized the image generation domain, playing crucial roles in both academic research and artistic expression. With the emergence of new diffusion models, assessing the performance of text-to-image models has becom…
View article: Image Regeneration: Evaluating Text-to-Image Model via Generating Identical Image with Multimodal Large Language Models
Image Regeneration: Evaluating Text-to-Image Model via Generating Identical Image with Multimodal Large Language Models Open
Diffusion models have revitalized the image generation domain, playing crucial roles in both academic research and artistic expression. With the emergence of new diffusion models, assessing the performance of text-to-image models has becom…
View article: SVDQuant: Absorbing Outliers by Low-Rank Components for 4-Bit Diffusion Models
SVDQuant: Absorbing Outliers by Low-Rank Components for 4-Bit Diffusion Models Open
Diffusion models can effectively generate high-quality images. However, as they scale, rising memory demands and higher latency pose substantial deployment challenges. In this work, we aim to accelerate diffusion models by quantizing their…
View article: AuroraCap: Efficient, Performant Video Detailed Captioning and a New Benchmark
AuroraCap: Efficient, Performant Video Detailed Captioning and a New Benchmark Open
Video detailed captioning is a key task which aims to generate comprehensive and coherent textual descriptions of video content, benefiting both video understanding and generation. In this paper, we propose AuroraCap, a video captioner bas…
View article: Consistency Flow Matching: Defining Straight Flows with Velocity Consistency
Consistency Flow Matching: Defining Straight Flows with Velocity Consistency Open
Flow matching (FM) is a general framework for defining probability paths via Ordinary Differential Equations (ODEs) to transform between noise and data samples. Recent approaches attempt to straighten these flow trajectories to generate hi…
View article: Improving Diffusion Inverse Problem Solving with Decoupled Noise Annealing
Improving Diffusion Inverse Problem Solving with Decoupled Noise Annealing Open
Diffusion models have recently achieved success in solving Bayesian inverse problems with learned data priors. Current methods build on top of the diffusion sampling process, where each denoising step makes small modifications to samples f…
View article: HarvestNet: A Dataset for Detecting Smallholder Farming Activity Using Harvest Piles and Remote Sensing
HarvestNet: A Dataset for Detecting Smallholder Farming Activity Using Harvest Piles and Remote Sensing Open
Small farms contribute to a large share of the productive land in developing countries. In regions such as sub-Saharan Africa, where 80% of farms are small (under 2 ha in size), the task of mapping smallholder cropland is an important part…
View article: Mastering Text-to-Image Diffusion: Recaptioning, Planning, and Generating with Multimodal LLMs
Mastering Text-to-Image Diffusion: Recaptioning, Planning, and Generating with Multimodal LLMs Open
Diffusion models have exhibit exceptional performance in text-to-image generation and editing. However, existing methods often face challenges when handling complex text prompts that involve multiple objects with multiple attributes and re…
View article: DiffusionSat: A Generative Foundation Model for Satellite Imagery
DiffusionSat: A Generative Foundation Model for Satellite Imagery Open
Diffusion models have achieved state-of-the-art results on many modalities including images, speech, and video. However, existing models are not tailored to support remote sensing data, which is widely used in important applications includ…
View article: DreamPropeller: Supercharge Text-to-3D Generation with Parallel Sampling
DreamPropeller: Supercharge Text-to-3D Generation with Parallel Sampling Open
Recent methods such as Score Distillation Sampling (SDS) and Variational Score Distillation (VSD) using 2D diffusion models for text-to-3D generation have demonstrated impressive generation quality. However, the long generation time of suc…
View article: Holistic Evaluation of Text-To-Image Models
Holistic Evaluation of Text-To-Image Models Open
The stunning qualitative improvement of recent text-to-image models has led to their widespread attention and adoption. However, we lack a comprehensive quantitative understanding of their capabilities and risks. To fill this gap, we intro…
View article: Discrete Diffusion Modeling by Estimating the Ratios of the Data Distribution
Discrete Diffusion Modeling by Estimating the Ratios of the Data Distribution Open
Despite their groundbreaking performance for many generative modeling tasks, diffusion models have fallen short on discrete data domains such as natural language. Crucially, standard diffusion models rely on the well-established theory of …
View article: SSIF: Learning Continuous Image Representation for Spatial-Spectral Super-Resolution
SSIF: Learning Continuous Image Representation for Spatial-Spectral Super-Resolution Open
Existing digital sensors capture images at fixed spatial and spectral resolutions (e.g., RGB, multispectral, and hyperspectral images), and each combination requires bespoke machine learning models. Neural Implicit Functions partially over…
View article: HarvestNet: A Dataset for Detecting Smallholder Farming Activity Using Harvest Piles and Remote Sensing
HarvestNet: A Dataset for Detecting Smallholder Farming Activity Using Harvest Piles and Remote Sensing Open
Small farms contribute to a large share of the productive land in developing countries. In regions such as sub-Saharan Africa, where 80\% of farms are small (under 2 ha in size), the task of mapping smallholder cropland is an important par…
View article: Building Coverage Estimation with Low-resolution Remote Sensing Imagery
Building Coverage Estimation with Low-resolution Remote Sensing Imagery Open
Building coverage statistics provide crucial insights into the urbanization, infrastructure, and poverty level of a region, facilitating efforts towards alleviating poverty, building sustainable cities, and allocating infrastructure invest…
View article: Efficient Spatially Sparse Inference for Conditional GANs and Diffusion Models
Efficient Spatially Sparse Inference for Conditional GANs and Diffusion Models Open
During image editing, existing deep generative models tend to re-synthesize the entire output from scratch, including the unedited regions. This leads to a significant waste of computation, especially for minor editing operations. In this …
View article: Concrete Score Matching: Generalized Score Matching for Discrete Data
Concrete Score Matching: Generalized Score Matching for Discrete Data Open
Representing probability distributions by the gradient of their density functions has proven effective in modeling a wide range of continuous data modalities. However, this representation is not applicable in discrete domains where the gra…
View article: On Distillation of Guided Diffusion Models
On Distillation of Guided Diffusion Models Open
Classifier-free guided diffusion models have recently been shown to be highly effective at high-resolution image generation, and they have been widely used in large-scale diffusion frameworks including DALLE-2, Stable Diffusion and Imagen.…
View article: Generalizing Bayesian Optimization with Decision-theoretic Entropies
Generalizing Bayesian Optimization with Decision-theoretic Entropies Open
Bayesian optimization (BO) is a popular method for efficiently inferring optima of an expensive black-box function via a sequence of queries. Existing information-theoretic BO procedures aim to make queries that most reduce the uncertainty…
View article: ButterflyFlow: Building Invertible Layers with Butterfly Matrices
ButterflyFlow: Building Invertible Layers with Butterfly Matrices Open
Normalizing flows model complex probability distributions using maps obtained by composing invertible layers. Special linear layers such as masked and 1x1 convolutions play a key role in existing architectures because they increase express…
View article: SatMAE: Pre-training Transformers for Temporal and Multi-Spectral Satellite Imagery
SatMAE: Pre-training Transformers for Temporal and Multi-Spectral Satellite Imagery Open
Unsupervised pre-training methods for large vision models have shown to enhance performance on downstream supervised tasks. Developing similar techniques for satellite imagery presents significant opportunities as unlabelled data is plenti…
View article: IS-Count: Large-Scale Object Counting from Satellite Images with Covariate-Based Importance Sampling
IS-Count: Large-Scale Object Counting from Satellite Images with Covariate-Based Importance Sampling Open
Object detection in high-resolution satellite imagery is emerging as a scalable alternative to on-the-ground survey data collection in many environmental and socioeconomic monitoring applications. However, performing object detection over …
View article: Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models
Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models Open
Language models demonstrate both quantitative improvement and new qualitative capabilities with increasing scale. Despite their potentially transformative impact, these new capabilities are as yet poorly characterized. In order to inform f…
View article: Self-Similarity Priors: Neural Collages as Differentiable Fractal Representations
Self-Similarity Priors: Neural Collages as Differentiable Fractal Representations Open
Many patterns in nature exhibit self-similarity: they can be compactly described via self-referential transformations. Said patterns commonly appear in natural and artificial objects, such as molecules, shorelines, galaxies and even images…
View article: Tracking Urbanization in Developing Regions with Remote Sensing Spatial-Temporal Super-Resolution
Tracking Urbanization in Developing Regions with Remote Sensing Spatial-Temporal Super-Resolution Open
Automated tracking of urban development in areas where construction information is not available became possible with recent advancements in machine learning and remote sensing. Unfortunately, these solutions perform best on high-resolutio…
View article: IS-COUNT: Large-scale Object Counting from Satellite Images with Covariate-based Importance Sampling
IS-COUNT: Large-scale Object Counting from Satellite Images with Covariate-based Importance Sampling Open
Object detection in high-resolution satellite imagery is emerging as a scalable alternative to on-the-ground survey data collection in many environmental and socioeconomic monitoring applications. However, performing object detection over …
View article: Density Ratio Estimation via Infinitesimal Classification
Density Ratio Estimation via Infinitesimal Classification Open
Density ratio estimation (DRE) is a fundamental machine learning technique for comparing two probability distributions. However, existing methods struggle in high-dimensional settings, as it is difficult to accurately compare probability d…
View article: Estimating High Order Gradients of the Data Distribution by Denoising.
Estimating High Order Gradients of the Data Distribution by Denoising. Open
The first order derivative of a data density can be estimated efficiently by denoising score matching, and has become an important component in many applications, such as image generation and audio synthesis. Higher order derivatives provi…
View article: SustainBench: Benchmarks for Monitoring the Sustainable Development Goals with Machine Learning
SustainBench: Benchmarks for Monitoring the Sustainable Development Goals with Machine Learning Open
Progress toward the United Nations Sustainable Development Goals (SDGs) has been hindered by a lack of data on key environmental and socioeconomic indicators, which historically have come from ground surveys with sparse temporal and spatia…