Search Results for author:
Found 28 papers, 10 papers with code
MedDr: Diagnosis-Guided Bootstrapping for Large-Scale Medical Vision-Language Learning
The rapid advancement of large-scale vision-language models has showcased remarkable capabilities across various tasks.
Dialectical Alignment: Resolving the Tension of 3H and Security Threats of LLMs
With the rise of large language models (LLMs), ensuring they embody the principles of being helpful, honest, and harmless (3H), known as Human Alignment, becomes crucial.
PROMPT-SAW: Leveraging Relation-Aware Graphs for Textual Prompt Compression
Large language models (LLMs) have shown exceptional abilities for multiple different natural language processing tasks.
MambaMIL: Enhancing Long Sequence Modeling with Sequence Reordering in Computational Pathology
Multiple Instance Learning (MIL) has emerged as a dominant paradigm to extract discriminative feature representations within Whole Slide Images (WSIs) in computational pathology.
SDiT: Spiking Diffusion Model with Transformer
In this paper, we explore a novel diffusion model architecture within spiking neural networks.
MoRAL: MoE Augmented LoRA for LLMs' Lifelong Learning
Adapting large language models (LLMs) to new domains/tasks and enabling them to be efficient lifelong learners is a pivotal challenge.
MONAL: Model Autophagy Analysis for Modeling Human-AI Interactions
The increasing significance of large models and their multi-modal variants in societal information processing has ignited debates on social safety and ethics.
Mixed Matrix Completion in Complex Survey Sampling under Heterogeneous Missingness
Modern surveys with large sample sizes and growing mixed-type questionnaires require robust and scalable analysis methods.
A Survey on LLM-Generated Text Detection: Necessity, Methods, and Future Directions
In this survey, we collate recent research breakthroughs in this area and underscore the pressing need to bolster detector research.
Positivity-free Policy Learning with Observational Data
Policy learning utilizing observational data is pivotal across various domains, with the objective of learning the optimal treatment assignment policy while adhering to specific constraints such as fairness, budget, and simplicity.
Is ChatGPT a Highly Fluent Grammatical Error Correction System? A Comprehensive Evaluation
To showcase its capabilities in GEC, we design zero-shot chain-of-thought (CoT) and few-shot CoT settings using in-context learning for ChatGPT.
Efficient and robust transfer learning of optimal individualized treatment regimes with right-censored survival data
We present an efficient and robust transfer learning framework for estimating the optimal ITR with right-censored survival data that generalizes well to the target population.
A Bayesian Semiparametric Method For Estimating Causal Quantile Effects
We adopt a semiparametric conditional distribution regression model that allows inference on any functionals of counterfactual distributions, including PDFs and multiple QTEs.
Self-supervised Denoising via Low-rank Tensor Approximated Convolutional Neural Network
With the proposed design, we are able to characterize our denoiser with fewer parameters and train it based on a single image, which considerably improves the model generalizability and reduces the cost of data acquisition.
Faith: An Efficient Framework for Transformer Verification on GPUs
In this paper, we propose Faith, an efficient framework for transformer verification on GPUs.
UMSNet: An Universal Multi-sensor Network for Human Activity Recognition
Human activity recognition (HAR) based on multimodal sensors has become a rapidly growing branch of biometric recognition and artificial intelligence.
Combining Doubly Robust Methods and Machine Learning for Estimating Average Treatment Effects for Observational Real-world Data
Recently, various doubly robust methods have been proposed for average treatment effect estimation by combining the treatment model and the outcome model via different vehicles, such as matching, weighting, and regression.
Targeted Optimal Treatment Regime Learning Using Summary Statistics
We consider the problem of treatment regime estimation when the source and target populations may be heterogeneous, individual-level data is available from the source population, and only the summary information of covariates, such as moments, is accessible from the target population.
Learning Motion-Appearance Co-Attention for Zero-Shot Video Object Segmentation
How to make the appearance and motion information interact effectively to accommodate complex scenarios is a fundamental issue in flow-based zero-shot video object segmentation.
Semantic Segmentation
Unsupervised Video Object Segmentation
+2
A spectral adjustment for spatial confounding
We show that this assumption in the spectral domain is equivalent to adjusting for global-scale confounding in the spatial domain by adding a spatially smoothed version of the treatment variable to the mean of the response variable.
Methodology
A Distributed Training Algorithm of Generative Adversarial Networks with Quantized Gradients
In this paper, we propose a {distributed GANs training algorithm with quantized gradient, dubbed DQGAN,} which is the first distributed training method with quantized gradient for GANs.
SGQuant: Squeezing the Last Bit on Graph Neural Networks with Specialized Quantization
With the increasing popularity of graph-based learning, Graph Neural Networks (GNNs) win lots of attention from the research and industry field because of their high accuracy.
Double score matching estimators of average and quantile treatment effects
Propensity score matching has a long tradition for handling confounding in causal inference.
Methodology
Multi-cause causal inference with unmeasured confounding and binary outcome
Unobserved confounding presents a major threat to causal inference in observational studies.
Methodology
PCNN: Environment Adaptive Model Without Finetuning
Convolutional Neural Networks (CNNs) have achieved tremendous success for many computer vision tasks, which shows a promising perspective of deploying CNNs on mobile platforms.
Penetrating the Fog: the Path to Efficient CNN Models
In this paper, we are the first in the field to consider how to craft an effective sparse kernel design by eliminating the large design space.
Domain-Adversarial Multi-Task Framework for Novel Therapeutic Property Prediction of Compounds
In this paper, we propose a novel domain-adversarial multi-task framework for integrating shared knowledge from multiple domains.
Semiparametric estimation of structural failure time model in continuous-time processes
We propose a class of continuous-time structural failure time models and semiparametric estimators, which do not restrict to regularly spaced data.
Methodology
