相关论文: Towards Robust Neural Retrieval Models with Synthe…

Deep learning models in recommender systems are usually trained in the batch mode, namely iteratively trained on a fixed-size window of training data. Such batch mode training of deep learning models suffers from low training efficiency,…

This paper introduces a new generative deep learning network for human motion synthesis and control. Our key idea is to combine recurrent neural networks (RNNs) and adversarial training for human motion modeling. We first describe an…

Recent advances in learning-based perception systems have led to drastic improvements in the performance of robotic systems like autonomous vehicles and surgical robots. These perception systems, however, are hard to analyze and errors in…

Neural text generation, including neural machine translation, image captioning, and summarization, has been quite successful recently. However, during training time, typically only one reference is considered for each example, even though…

Decision trees are widely used in high-stakes fields like finance and healthcare due to their interpretability. This work introduces an efficient, scalable method for generating synthetic pre-training data to enable meta-learning of…

Programming-by-example is the task of synthesizing a program that is consistent with a set of user-provided input-output examples. As examples are often an under-specification of one's intent, a good synthesizer must choose the intended…

Robot perception systems need to perform reliable image segmentation in real-time on noisy, raw perception data. State-of-the-art segmentation approaches use large CNN models and carefully constructed datasets; however, these models focus…

Neural Networks (NNs) are vulnerable to adversarial examples. Such inputs differ only slightly from their benign counterparts yet provoke misclassifications of the attacked NNs. The required perturbations to craft the examples are often…

Composed Image Retrieval (CIR) is a challenging multimodal task that retrieves a target image based on a reference image and accompanying modification text. Due to the high cost of annotating CIR triplet datasets, zero-shot (ZS) CIR has…

Language models have demonstrated remarkable performance in solving reasoning tasks; however, even the strongest models still occasionally make reasoning mistakes. Recently, there has been active research aimed at improving reasoning…

Catastrophic forgetting is a problem caused by neural networks' inability to learn data in sequence. After learning two tasks in sequence, performance on the first one drops significantly. This is a serious disadvantage that prevents many…

Generative text-to-image models enable us to synthesize unlimited amounts of images in a controllable manner, spurring many recent efforts to train vision models with synthetic data. However, every synthetic image ultimately originates from…

Legal professionals need to write analyses that rely on citations to relevant precedents, i.e., previous case decisions. Intelligent systems assisting legal professionals in writing such documents provide great benefits but are challenging…

Pre-trained models are nowadays a fundamental component of machine learning research. In continual learning, they are commonly used to initialize the model before training on the stream of non-stationary data. However, pre-training is…

Effective information retrieval (IR) in settings with limited training data, particularly for complex queries, remains a challenging task. This paper introduces IR2, Information Regularization for Information Retrieval, a technique for…

Synthetic data is being used lately for training deep neural networks in computer vision applications such as object detection, object segmentation and 6D object pose estimation. Domain randomization hereby plays an important role in…

Modern information retrieval (IR) models, trained exclusively on standard <query, passage> pairs, struggle to effectively interpret and follow explicit user instructions. We introduce InF-IR, a large-scale, high-quality training corpus…

It is often desirable to distill the capabilities of large language models (LLMs) into smaller student models due to compute and memory constraints. One way to do this for classification tasks is via dataset synthesis, which can be…

Remarkable success has been achieved in the last few years on some limited machine reading comprehension (MRC) tasks. However, it is still difficult to interpret the predictions of existing MRC models. In this paper, we focus on extracting…

Synthetic data offers a compelling path to scalable pretraining when real-world data is scarce, but models pretrained on synthetic data often fail to transfer reliably to deployment settings. We study this problem in full-body human motion,…