We propose DISC-LawLLM, an intelligent legal system utilizing large language models (LLMs) to provide a wide range of legal services.
At pretraining stage, we propose an effective pretraining method that employs both query and multiple fields of document as inputs, including an effective information compression method for lengthy fields.
We introduce a method for flexible continual learning in open-vocabulary image classification, drawing inspiration from the complementary learning systems observed in human cognition.
In this paper, based on causal analysis of the aforementioned problems, we propose a novel fine-tuning method, which uses masked images as counterfactual samples that help improve the robustness of the fine-tuning model.
This paper introduces a new sparse Bayesian learning (SBL) algorithm that jointly recovers a temporal sequence of edge maps from noisy and under-sampled Fourier data.
Graph Convolutional Networks (GCNs) have been proved successful in the field of semi-supervised node classification by extracting structural information from graph data.
Optimal leading forest (OLF) has been observed to have the advantage of revealing the difference evolution along a path within a subtree.
We use human experiments to confirm that both HVE and humans predominantly use some specific features to support the classification of specific classes (e. g., texture is the dominant feature to distinguish a zebra from other quadrupeds, both for humans and HVE).
In this paper, we focus on the information transfer from ranking to pre-ranking stage.
Despite the diversity in attack patterns, adversarial patches tend to be highly textured and different in appearance from natural images.
We specifically consider the case where each data set is missing vital information, which prevents the accurate recovery of the individual images.
no code implementations • 24 May 2022 • Yao Xiao, Carlos Cardenas, Dong Joo Rhee, Tucker Netherton, Lifei Zhang, Callistus Nguyen, Raphael Douglas, Raymond Mumme, Stephen Skett, Tina Patel, Chris Trauernicht, Caroline Chung, Hannah Simonds, Ajay Aggarwal, Laurence Court
In this work, we developed and evaluated a novel pipeline consisting of two landmark-based field aperture generation approaches for WBRT treatment planning; they are fully automated and customizable.
However, the retrieval-based methods are sub-optimal and would cause more or less information losses, and it's difficult to balance the effectiveness and efficiency of the retrieval algorithm.
Industrial search and recommendation systems mostly follow the classic multi-stage information retrieval paradigm: matching, pre-ranking, ranking, and re-ranking stages.
To enable heterogeneous computing systems with autonomous programming and optimization capabilities, we propose a unified, end-to-end, programmable graph representation learning (PGL) framework that is capable of mining the complexity of high-level programs down to the universal intermediate representation, extracting the specific computational patterns and predicting which code segments would run best on a specific core in heterogeneous hardware platforms.
(2) They lack convexity constraints, which is important for meaningfully manipulating specific attributes for downstream tasks.
Take image classification as an example, HNI visualizes the reasoning logic of a NN with class-specific Structural Concept Graphs (c-SCG), which are human-interpretable.
Intercellular heterogeneity is a major obstacle to successful precision medicine.
Dialogue-based relation extraction (DiaRE) aims to detect the structural information from unstructured utterances in dialogues.
2) Meanwhile, we introduce a dual contrastive learning approach (DCL) to better align the text and video by maximizing the mutual information (MI) between query and video clips, and the MI between start/end frames of a target moment and the others within a video to learn more informative visual representations.
Despite substantial progress in applying neural networks (NN) to a wide variety of areas, they still largely suffer from a lack of transparency and interpretability.
DEAE can become a generative model and synthesis semantic controllable samples by interpolating latent code, which can even synthesis novel attribute value never is shown in the original dataset.
We have conducted extensive autonomous landing experiments in a variety of familiar or completely unknown environments, verifying that our model can adaptively balance the accuracy and speed, and the UAV can robustly select a safe landing site.
We trained our model using the publicly available UTKFace dataset and evaluated our model by simulating up to 100 years of aging on 1, 156 male and 1, 207 female infant and toddler face photos.
High-level applications, such as machine learning, are evolving from simple models based on multilayer perceptrons for simple image recognition to much deeper and more complex neural networks for self-driving vehicle control systems. The rapid increase in the consumption of memory and computational resources by these models demands the use of multi-core parallel systems to scale the execution of the complex emerging applications that depend on them.
The long-standing challenges for offline handwritten Chinese character recognition (HCCR) are twofold: Chinese characters can be very diverse and complicated while similarly looking, and cursive handwriting (due to increased writing speed and infrequent pen lifting) makes strokes and even characters connected together in a flowing manner.
Neural networks have shown great potential in many applications like speech recognition, drug discovery, image classification, and object detection.
Distance metric plays a key role in grouping superpixels to produce object proposals for object detection.
We participated in the object detection track of ILSVRC 2014 and received the fourth place among the 38 teams.