手术中的视觉问题回答（VQA）在很大程度上没有探索。专家外科医生稀缺，经常被临床和学术工作负载超负荷。这种超负荷通常会限制他们从患者，医学生或初级居民与手术程序有关的时间回答问卷。有时，学生和初级居民也不要在课堂上提出太多问题以减少干扰。尽管计算机辅助的模拟器和过去的手术程序记录已经可以让他们观察和提高技能，但他们仍然非常依靠医学专家来回答他们的问题。将手术VQA系统作为可靠的“第二意见”可以作为备份，并减轻医疗专家回答这些问题的负担。缺乏注释的医学数据和特定于域的术语的存在限制了对手术程序的VQA探索。在这项工作中，我们设计了一项外科VQA任务，该任务根据外科手术场景回答有关手术程序的问卷。扩展MICCAI内窥镜视觉挑战2018数据集和工作流识别数据集，我们介绍了两个具有分类和基于句子的答案的手术VQA数据集。为了执行手术VQA，我们采用视觉文本变压器模型。我们进一步介绍了一个基于MLP的剩余Visualbert编码器模型，该模型可以在视觉令牌和文本令牌之间进行相互作用，从而改善了基于分类的答案的性能。此外，我们研究了输入图像贴片数量和时间视觉特征对分类和基于句子的答案中模型性能的影响。

多项研究表明，从孕妇中期超声检查（USG）检查获得标准化的胎儿脑生物特征？获得这些测量值是高度主观的，专业驱动的，需要多年的培训经验，从而限制了所有怀孕母亲的优质产前护理。在这项研究中，我们提出了一种深度学习方法（DL）方法，以通过准确和自动化的卡钳放置（每次生物测量法）将其作为地标建模，从而从跨炉平面（TC）的2D USG图像（TC）计算3个关键的胎儿脑生物特征。检测问题。我们利用了临床相关的生物识别约束（卡尺点之间的关系）和与域相关的数据增强，以提高U-NET DL模型的准确性（经过训练/测试：596张图像，473个受试者/143张图像，143个受试者）。我们进行了多个实验，证明了DL主链，数据增强，推广性和基准测试，通过广泛的临床验证（DL与7位经验丰富的临床医生）对最新的最新方法进行了测试。在所有情况下，单个卡尺点和计算生物特征的放置的平均误差都与临床医生之间的错误率相当。所提出的框架的临床翻译可以帮助新手用户在可靠和标准化的胎儿大脑超声图评估中的新手使用者。

Deep learning techniques with neural networks have been used effectively in computational fluid dynamics (CFD) to obtain solutions to nonlinear differential equations. This paper presents a physics-informed neural network (PINN) approach to solve the Blasius function. This method eliminates the process of changing the non-linear differential equation to an initial value problem. Also, it tackles the convergence issue arising in the conventional series solution. It is seen that this method produces results that are at par with the numerical and conventional methods. The solution is extended to the negative axis to show that PINNs capture the singularity of the function at $\eta=-5.69$

The generalisation performance of a convolutional neural networks (CNN) is majorly predisposed by the quantity, quality, and diversity of the training images. All the training data needs to be annotated in-hand before, in many real-world applications data is easy to acquire but expensive and time-consuming to label. The goal of the Active learning for the task is to draw most informative samples from the unlabeled pool which can used for training after annotation. With total different objective, self-supervised learning which have been gaining meteoric popularity by closing the gap in performance with supervised methods on large computer vision benchmarks. self-supervised learning (SSL) these days have shown to produce low-level representations that are invariant to distortions of the input sample and can encode invariance to artificially created distortions, e.g. rotation, solarization, cropping etc. self-supervised learning (SSL) approaches rely on simpler and more scalable frameworks for learning. In this paper, we unify these two families of approaches from the angle of active learning using self-supervised learning mainfold and propose Deep Active Learning using BarlowTwins(DALBT), an active learning method for all the datasets using combination of classifier trained along with self-supervised loss framework of Barlow Twins to a setting where the model can encode the invariance of artificially created distortions, e.g. rotation, solarization, cropping etc.

Generative AI has matured to a point where large-scale models can generate text that seems indistinguishable from human-written text and remarkably photorealistic images. Automatically measuring how close the distribution of generated data is to the target real data distribution is a key step in diagnosing existing models and developing better models. We present MAUVE, a family of comparison measures between pairs of distributions such as those encountered in the generative modeling of text or images. These scores are statistical summaries of divergence frontiers capturing two types of errors in generative modeling. We explore four approaches to statistically estimate these scores: vector quantization, non-parametric estimation, classifier-based estimation, and parametric Gaussian approximations. We provide statistical bounds for the vector quantization approach. Empirically, we find that the proposed scores paired with a range of $f$-divergences and statistical estimation methods can quantify the gaps between the distributions of human-written text and those of modern neural language models by correlating with human judgments and identifying known properties of the generated texts. We conclude the paper by demonstrating its applications to other AI domains and discussing practical recommendations.

Agile robotics presents a difficult challenge with robots moving at high speeds requiring precise and low-latency sensing and control. Creating agile motion that accomplishes the task at hand while being safe to execute is a key requirement for agile robots to gain human trust. This requires designing new approaches that are flexible and maintain knowledge over world constraints. In this paper, we consider the problem of building a flexible and adaptive controller for a challenging agile mobile manipulation task of hitting ground strokes on a wheelchair tennis robot. We propose and evaluate an extension to work done on learning striking behaviors using a probabilistic movement primitive (ProMP) framework by (1) demonstrating the safe execution of learned primitives on an agile mobile manipulator setup, and (2) proposing an online primitive refinement procedure that utilizes evaluative feedback from humans on the executed trajectories.

Code generation models have achieved impressive performance. However, they tend to be brittle as slight edits to a prompt could lead to very different generations; these robustness properties, critical for user experience when deployed in real-life applications, are not well understood. Most existing works on robustness in text or code tasks have focused on classification, while robustness in generation tasks is an uncharted area and to date there is no comprehensive benchmark for robustness in code generation. In this paper, we propose ReCode, a comprehensive robustness evaluation benchmark for code generation models. We customize over 30 transformations specifically for code on docstrings, function and variable names, code syntax, and code format. They are carefully designed to be natural in real-life coding practice, preserve the original semantic meaning, and thus provide multifaceted assessments of a model's robustness performance. With human annotators, we verified that over 90% of the perturbed prompts do not alter the semantic meaning of the original prompt. In addition, we define robustness metrics for code generation models considering the worst-case behavior under each type of perturbation, taking advantage of the fact that executing the generated code can serve as objective evaluation. We demonstrate ReCode on SOTA models using HumanEval, MBPP, as well as function completion tasks derived from them. Interesting observations include: better robustness for CodeGen over InCoder and GPT-J; models are most sensitive to syntax perturbations; more challenging robustness evaluation on MBPP over HumanEval.

While pre-trained language models (LM) for code have achieved great success in code completion, they generate code conditioned only on the contents within the file, i.e., in-file context, but ignore the rich semantics in other files within the same project, i.e., cross-file context, a critical source of information that is especially useful in modern modular software development. Such overlooking constrains code language models' capacity in code completion, leading to unexpected behaviors such as generating hallucinated class member functions or function calls with unexpected arguments. In this work, we develop a cross-file context finder tool, CCFINDER, that effectively locates and retrieves the most relevant cross-file context. We propose CoCoMIC, a framework that incorporates cross-file context to learn the in-file and cross-file context jointly on top of pretrained code LMs. CoCoMIC successfully improves the existing code LM with a 19.30% relative increase in exact match and a 15.41% relative increase in identifier matching for code completion when the cross-file context is provided.

The evaluation of abstractive summarization models typically uses test data that is identically distributed as training data. In real-world practice, documents to be summarized may contain input noise caused by text extraction artifacts or data pipeline bugs. The robustness of model performance under distribution shift caused by such noise is relatively under-studied. We present a large empirical study quantifying the sometimes severe loss in performance (up to 12 ROUGE-1 points) from different types of input noise for a range of datasets and model sizes. We then propose a light-weight method for detecting and removing such noise in the input during model inference without requiring any extra training, auxiliary models, or even prior knowledge of the type of noise. Our proposed approach effectively mitigates the loss in performance, recovering a large fraction of the performance drop, sometimes as large as 11 ROUGE-1 points.

A fundamental characteristic common to both human vision and natural language is their compositional nature. Yet, despite the performance gains contributed by large vision and language pretraining, we find that - across 6 architectures trained with 4 algorithms on massive datasets - they exhibit little compositionality. To arrive at this conclusion, we introduce a new compositionality evaluation benchmark CREPE which measures two important aspects of compositionality identified by cognitive science literature: systematicity and productivity. To measure systematicity, CREPE consists of three test datasets. The three test sets are designed to test models trained on three of the popular training datasets: CC-12M, YFCC-15M, and LAION-400M. They contain 385K, 385K, and 373K image-text pairs and 237K, 210K, and 178K hard negative captions. To test productivity, CREPE contains 17K image-text pairs with nine different complexities plus 246K hard negative captions with atomic, swapping, and negation foils. The datasets are generated by repurposing the Visual Genome scene graphs and region descriptions and applying handcrafted templates and GPT-3. For systematicity, we find that model performance decreases consistently when novel compositions dominate the retrieval set, with Recall@1 dropping by up to 8%. For productivity, models' retrieval success decays as complexity increases, frequently nearing random chance at high complexity. These results hold regardless of model and training dataset size.