Search Results for author:
Found 28 papers, 15 papers with code
APEER: Automatic Prompt Engineering Enhances Large Language Model Reranking
Existing automatic prompt engineering algorithms primarily focus on language modeling and classification tasks, leaving the domain of IR, particularly reranking, underexplored.
BLoB: Bayesian Low-Rank Adaptation by Backpropagation for Large Language Models
Large Language Models (LLMs) often suffer from overconfidence during inference, particularly when adapted to downstream domain-specific tasks with limited data.
Spectrum-Aware Parameter Efficient Fine-Tuning for Diffusion Models
We introduce Spectral Orthogonal Decomposition Adaptation (SODA), which balances computational efficiency and representation capacity.
Implicit In-context Learning
In-context Learning (ICL) empowers large language models (LLMs) to adapt to unseen tasks during inference by prefixing a few demonstration examples prior to test queries.
Score-Guided Diffusion for 3D Human Recovery
We present Score-Guided Human Mesh Recovery (ScoreHMR), an approach for solving inverse problems for 3D human pose and shape reconstruction.
DMCVR: Morphology-Guided Diffusion Model for 3D Cardiac Volume Reconstruction
However, current cardiac MRI-based reconstruction technology used in clinical settings is 2D with limited through-plane resolution, resulting in low-quality reconstructed cardiac volumes.
Improving Tuning-Free Real Image Editing with Proximal Guidance
Null-text inversion (NTI) optimizes null embeddings to align the reconstruction and inversion trajectories with larger CFG scales, enabling real image editing with cross-attention control.
Learning Articulated Shape with Keypoint Pseudo-labels from Web Images
It is based on two key insights: (1) 2D keypoint estimation networks trained on as few as 50-150 images of a given object category generalize well and generate reliable pseudo-labels; (2) a data selection mechanism can automatically create a "curated" subset of the unlabeled web images that can be used for training -- we evaluate four data selection methods.
Constructive Assimilation: Boosting Contrastive Learning Performance through View Generation Strategies
Recently, several attempts have been made to replace such domain-specific, human-designed transformations with generated views that are learned.
SVDiff: Compact Parameter Space for Diffusion Fine-Tuning
Diffusion models have achieved remarkable success in text-to-image generation, enabling the creation of high-quality images from text prompts or other modalities.
Learning Complementary Policies for Human-AI Teams
We then extend our approach to leverage opportunities and mitigate risks that arise in important contexts in practice: 1) when a team is composed of multiple humans with differential and potentially complementary abilities, 2) when the observational data includes consistent deterministic actions, and 3) when the covariate distribution of future decisions differ from that in the historical data.
SINE: SINgle Image Editing with Text-to-Image Diffusion Models
We propose a novel model-based guidance built upon the classifier-free guidance so that the knowledge from the model trained on a single image can be distilled into the pre-trained diffusion model, enabling content creation even with one given image.
Diffusion Guided Domain Adaptation of Image Generators
Can a text-to-image diffusion model be used as a training objective for adapting a GAN generator to another domain?
On the Importance of Calibration in Semi-supervised Learning
State-of-the-art (SOTA) semi-supervised learning (SSL) methods have been highly successful in leveraging a mix of labeled and unlabeled data by combining techniques of consistency regularization and pseudo-labeling.
Hierarchically Self-Supervised Transformer for Human Skeleton Representation Learning
Despite the success of fully-supervised human skeleton sequence modeling, utilizing self-supervised pre-training for skeleton sequence representation learning has been an active field because acquiring task-specific skeleton annotations at large scales is difficult.
TransFusion: Multi-view Divergent Fusion for Medical Image Segmentation with Transformers
Combining information from multi-view images is crucial to improve the performance and robustness of automated methods for disease diagnosis.
Region Proposal Rectification Towards Robust Instance Segmentation of Biological Images
Top-down instance segmentation framework has shown its superiority in object detection compared to the bottom-up framework.
Show Me What and Tell Me How: Video Synthesis via Multimodal Conditioning
In addition, our model can extract visual information as suggested by the text prompt, e. g., "an object in image one is moving northeast", and generate corresponding videos.
Enhancing Counterfactual Classification via Self-Training
We approach this task as a domain adaptation problem and propose a self-training algorithm which imputes outcomes with categorical values for finite unseen actions in the observational data to simulate a randomized trial through pseudolabeling, which we refer to as Counterfactual Self-Training (CST).
AE-StyleGAN: Improved Training of Style-Based Auto-Encoders
StyleGANs have shown impressive results on data generation and manipulation in recent years, thanks to its disentangled style latent space.
Dual Projection Generative Adversarial Networks for Conditional Image Generation
We then propose an improved cGAN model with Auxiliary Classification that directly aligns the fake and real conditionals $P(\text{class}|\text{image})$ by minimizing their $f$-divergence.
Disentangled Recurrent Wasserstein Autoencoder
Learning disentangled representations leads to interpretable models and facilitates data generation with style transfer, which has been extensively studied on static data such as images in an unsupervised learning framework.
Counterfactual Self-Training
We approach this task as a domain adaptation problem and propose a self-training algorithm which imputes outcomes for the unseen actions in the observational data to simulate a randomized trial.
Unbiased Auxiliary Classifier GANs with MINE
To remedy this, Twin Auxiliary Classifier GAN (TAC-GAN) introduces a twin classifier to the min-max game.
Learning Generative Models of Tissue Organization with Supervised GANs
A key step in understanding the spatial organization of cells and tissues is the ability to construct generative models that accurately reflect that organization.
Robust Conditional GAN from Uncertainty-Aware Pairwise Comparisons
Conditional generative adversarial networks have shown exceptional generation performance over the past few years.
Unsupervised Domain Adaptation via Calibrating Uncertainties
Unsupervised domain adaptation (UDA) aims at inferring class labels for unlabeled target domain given a related labeled source dataset.
Deep Contextual Recurrent Residual Networks for Scene Labeling
Designed as extremely deep architectures, deep residual networks which provide a rich visual representation and offer robust convergence behaviors have recently achieved exceptional performance in numerous computer vision problems.
