Related papers: Distance Assisted Recursive Testing
Deep pre-trained language models (e,g. BERT) are effective at large-scale text retrieval task. Existing text retrieval systems with state-of-the-art performance usually adopt a retrieve-then-reranking architecture due to the high…
Intrinsic susceptibility of deep learning to adversarial examples has led to a plethora of attack techniques with a broad common objective of fooling deep models. However, we find slight compositional differences between the algorithms…
Bayesian Additive Regression Trees (BART) is a powerful statistical model that leverages the strengths of Bayesian inference and regression trees. It has received significant attention for capturing complex non-linear relationships and…
The Transformer, a highly expressive architecture for sequence modeling, has recently been adapted to solve sequential decision-making, most notably through the Decision Transformer (DT), which learns policies by conditioning on desired…
Purpose: To develop a deep-learning-based image reconstruction framework for reproducible research in MRI. Methods: The BART toolbox offers a rich set of implementations of calibration and reconstruction algorithms for parallel imaging and…
In many learning situations, resources at inference time are significantly more constrained than resources at training time. This paper studies a general paradigm, called Differentiable ARchitecture Compression (DARC), that combines model…
Change detection visual question answering (CDVQA) requires answering text queries by reasoning about semantic changes in bi-temporal remote sensing images. A straightforward approach is to boost CDVQA performance with generic…
Inverse reinforcement learning (IRL) aims to explicitly infer an underlying reward function based on collected expert demonstrations. Considering that obtaining expert demonstrations can be costly, the focus of current IRL techniques is on…
In differentiable neural architecture search (NAS) algorithms like DARTS, the training set used to update model weight and the validation set used to update model architectures are sampled from the same data distribution. Thus, the uncommon…
Under stringent model type and variable distribution assumptions, differentiable score-based causal discovery methods learn a directed acyclic graph (DAG) from observational data by evaluating candidate graphs over an average score…
Decision trees are a commonly used class of machine learning models valued for their interpretability and versatility, capable of both classification and regression. We propose ZTree, a novel decision tree learning framework that replaces…
This study aims at making the architecture search process more adaptive for one-shot or online training. It is extended from the existing study on differentiable neural architecture search, and we made the backbone architecture…
In this paper, we present a new algorithm that extends RRT* and RT-RRT* for online path planning in complex, dynamic environments. Sampling-based approaches often perform poorly in environments with narrow passages, a feature common to many…
The objective of dense material segmentation is to identify the material categories for every image pixel. Recent studies adopt image patches to extract material features. Although the trained networks can improve the segmentation…
Present Large Language Models (LLM) self-training methods always under-sample on challenging queries, leading to inadequate learning on difficult problems which limits LLMs' ability. Therefore, this work proposes a difficulty-aware…
Medical image restoration (MedIR) aims to recover high-quality medical images from their low-quality counterparts. Recent advancements in MedIR have focused on All-in-One models capable of simultaneously addressing multiple different MedIR…
Retrieval-Augmented Generation (RAG) systems are widely adopted in knowledge-intensive NLP tasks, but current evaluations often overlook the structural complexity and multi-step reasoning required in real-world scenarios. These benchmarks…
Differentiable neural architecture search (DARTS) has gained much success in discovering flexible and diverse cell types. To reduce the evaluation gap, the supernet is expected to have identical layers with the target network. However, even…
This paper introduces a novel framework for distributed two-sample testing using the Integrated Transportation Distance (ITD), an extension of the Optimal Transport distance. The approach addresses the challenges of detecting distributional…
\textit{Differentiable ARchiTecture Search} (DARTS) has recently become the mainstream of neural architecture search (NAS) due to its efficiency and simplicity. With a gradient-based bi-level optimization, DARTS alternately optimizes the…