Deep neural networks are incredibly vulnerable to crafted, human-imperceptible adversarial perturbations. Although adversarial training (AT) has proven to be an effective defense approach, we find that the AT-trained models heavily rely on the input low-frequency content for judgment, accounting for the low standard accuracy. To close the large gap between the standard and robust accuracies during AT, we investigate the frequency difference between clean and adversarial inputs, and propose a frequency regularization (FR) to align the output difference in the spectral domain. Besides, we find Stochastic Weight Averaging (SWA), by smoothing the kernels over epochs, further improves the robustness. Among various defense schemes, our method achieves the strongest robustness against attacks by PGD-20, C\&W and Autoattack, on a WideResNet trained on CIFAR-10 without any extra data.

We introduce Patch Aligned Contrastive Learning (PACL), a modified compatibility function for CLIP's contrastive loss, intending to train an alignment between the patch tokens of the vision encoder and the CLS token of the text encoder. With such an alignment, a model can identify regions of an image corresponding to a given text input, and therefore transfer seamlessly to the task of open vocabulary semantic segmentation without requiring any segmentation annotations during training. Using pre-trained CLIP encoders with PACL, we are able to set the state-of-the-art on the task of open vocabulary zero-shot segmentation on 4 different segmentation benchmarks: Pascal VOC, Pascal Context, COCO Stuff and ADE20K. Furthermore, we show that PACL is also applicable to image-level predictions and when used with a CLIP backbone, provides a general improvement in zero-shot classification accuracy compared to CLIP, across a suite of 12 image classification datasets.

Generalist models, which are capable of performing diverse multi-modal tasks in a task-agnostic way within a single model, have been explored recently. Being, hopefully, an alternative to approaching general-purpose AI, existing generalist models are still at an early stage, where modality and task coverage is limited. To empower multi-modal task-scaling and speed up this line of research, we release a generalist model learning system, OFASys, built on top of a declarative task interface named multi-modal instruction. At the core of OFASys is the idea of decoupling multi-modal task representations from the underlying model implementations. In OFASys, a task involving multiple modalities can be defined declaratively even with just a single line of code. The system automatically generates task plans from such instructions for training and inference. It also facilitates multi-task training for diverse multi-modal workloads. As a starting point, we provide presets of 7 different modalities and 23 highly-diverse example tasks in OFASys, with which we also develop a first-in-kind, single model, OFA+, that can handle text, image, speech, video, and motion data. The single OFA+ model achieves 95% performance in average with only 16% parameters of 15 task-finetuned models, showcasing the performance reliability of multi-modal task-scaling provided by OFASys. Available at https://github.com/OFA-Sys/OFASys

Error correction in automatic speech recognition (ASR) aims to correct those incorrect words in sentences generated by ASR models. Since recent ASR models usually have low word error rate (WER), to avoid affecting originally correct tokens, error correction models should only modify incorrect words, and therefore detecting incorrect words is important for error correction. Previous works on error correction either implicitly detect error words through target-source attention or CTC (connectionist temporal classification) loss, or explicitly locate specific deletion/substitution/insertion errors. However, implicit error detection does not provide clear signal about which tokens are incorrect and explicit error detection suffers from low detection accuracy. In this paper, we propose SoftCorrect with a soft error detection mechanism to avoid the limitations of both explicit and implicit error detection. Specifically, we first detect whether a token is correct or not through a probability produced by a dedicatedly designed language model, and then design a constrained CTC loss that only duplicates the detected incorrect tokens to let the decoder focus on the correction of error tokens. Compared with implicit error detection with CTC loss, SoftCorrect provides explicit signal about which words are incorrect and thus does not need to duplicate every token but only incorrect tokens; compared with explicit error detection, SoftCorrect does not detect specific deletion/substitution/insertion errors but just leaves it to CTC loss. Experiments on AISHELL-1 and Aidatatang datasets show that SoftCorrect achieves 26.1% and 9.4% CER reduction respectively, outperforming previous works by a large margin, while still enjoying fast speed of parallel generation.

Indoor scenes typically exhibit complex, spatially-varying appearance from global illumination, making inverse rendering a challenging ill-posed problem. This work presents an end-to-end, learning-based inverse rendering framework incorporating differentiable Monte Carlo raytracing with importance sampling. The framework takes a single image as input to jointly recover the underlying geometry, spatially-varying lighting, and photorealistic materials. Specifically, we introduce a physically-based differentiable rendering layer with screen-space ray tracing, resulting in more realistic specular reflections that match the input photo. In addition, we create a large-scale, photorealistic indoor scene dataset with significantly richer details like complex furniture and dedicated decorations. Further, we design a novel out-of-view lighting network with uncertainty-aware refinement leveraging hypernetwork-based neural radiance fields to predict lighting outside the view of the input photo. Through extensive evaluations on common benchmark datasets, we demonstrate superior inverse rendering quality of our method compared to state-of-the-art baselines, enabling various applications such as complex object insertion and material editing with high fidelity. Code and data will be made available at \url{https://jingsenzhu.github.io/invrend}.

如今，基础模型已成为人工智能中的基本基础设施之一，铺平了通往通用情报的方式。但是，现实提出了两个紧急挑战：现有的基础模型由英语社区主导；用户通常会获得有限的资源，因此不能总是使用基础模型。为了支持中文社区的发展，我们介绍了一个名为Fengshenbang的开源项目，该项目由认知计算与自然语言研究中心（CCNL）领导。我们的项目具有全面的功能，包括大型预培训模型，用户友好的API，基准，数据集等。我们将所有这些都包装在三个子项目中：风水次模型，风水框架和狂热基准。 Fengshenbang的开源路线图旨在重新评估中国预培训的大型大型模型的开源社区，促使整个中国大型模型社区的发展。我们还希望构建一个以用户为中心的开源生态系统，以允许个人访问所需的模型以匹配其计算资源。此外，我们邀请公司，大学和研究机构与我们合作建立大型开源模型的生态系统。我们希望这个项目将成为中国认知情报的基础。

我们介绍了一项对自然语言（NL）推理的人类通知，开放域和逻辑上复杂且多样的数据集，配备了一阶逻辑（fol）注释。对开本由1,435个示例（独特的结论）组成，每个示例与487组前提之一搭配，这些场所作为规则，可用于演绎理由，以理解每个结论的有效性。前提和结论的逻辑正确性是通过其平行注释来确保的，这些注释会自动由我们的FOL推理引擎验证。除了主要的NL推理任务外，对开本中的NL-FOL对自动构成了使用FOL作为逻辑形式的新的NL-FOL翻译数据集。我们对广泛的实验系统地评估了对中型语言模型（BERT，ROBERTA）进行微调的FOL推理能力，并且在大型语言模型（GPT-NEOX，OPT，OPT，GPT-3，Codex）上促成了很少的射击。对于NL-FOL翻译，我们尝试使用GPT-3和Codex。我们的结果表明，公开可用的最强大的大语言模型之一（LLM），GPT-3 Davinci，仅比随机结果略好，而在一部分集的一部分中，该模型尤其不好，并且在预测该模型方面尤其不好。纠正虚假和未知结论的真实价值。我们的数据集和代码可在https://github.com/yale-lily/folio上找到。

在本文中，我们提出了一种新颖的学习方案，用于自我监督的视频表示学习。受到人类如何理解视频的激励，我们建议先学习一般视觉概念，然后参加歧视性的局部区域以进行视频理解。具体而言，我们利用静态框架和框架差异来帮助解开静态和动态概念，并分别使潜在空间中的概念分布对齐。我们增加了多样性和忠诚的正常化，以确保我们学习一套紧凑的有意义的概念。然后，我们采用跨注意机制来汇总不同概念的详细局部特征，并滤除具有低激活的冗余概念以执行局部概念对比。广泛的实验表明，我们的方法提炼有意义的静态和动态概念来指导视频理解，并在UCF-101，HMDB-51和潜水-48上获得最新的结果。

在本报告中，我们建议针对四个EGO4D挑战任务，包括自然语言查询（NLQ），MOMMER QUERY（MQ），对象状态变更分类（OSCC），以及PNR定位（PNR）。尤其是，我们将最近发布的EGO4D数据集\ cite {grauman2021ego4d}从预处理数据集，预处理目标和开发集中从egecentric vlp中提升。基于上述三个设计，我们开发了一个验证的视频语言模型，该模型能够将其以自我为中心的视频文本表示或仅视频表示形式转移到几个视频下游任务中。我们的Egentric VLP在NLQ上实现10.46r@1&iou @0.3，MQ上的10.33地图，OSCC上的74％ACC，PNR上的0.67秒错误。该代码可在https://github.com/showlab/egovlp上找到。

在本报告中，我们为Epic-kitchens-100多实体检索（miR）挑战提出了一个基于视频的预处理（VLP）解决方案\ cite {kevin202222222egovlp}。尤其是，我们将最近发布的EGO4D数据集\ cite {grauman2021ego4d}从预处理数据集，预处理目标和开发集中从egecentric vlp中提升。基于上述三个设计，我们开发了一个预验证的视频语言模型，该模型能够将其自我为中心的视频文本表示为mir基准。此外，我们设计了一种自适应多构度最大损失，以有效地微调模型并为可靠的推理配备双重效果技术。我们最好的单个模型在挑战测试集上获得了强劲的性能，其中47.39％的地图和61.44％的NDCG。该代码可在https://github.com/showlab/egovlp上找到。