使用Denoisis扩散概率模型（DDPM）的神经声码器已通过适应给定的声学特征的扩散噪声分布来改善。在这项研究中，我们提出了适应扩散噪声的素描，以使其随时间变化的光谱包络变得接近条件对数 - 摩尔光谱图。随着时变的过滤这种适应可改善声音质量，尤其是在高频带中。它是在时频域中处理的，以使计算成本几乎与常规DDPM基于DDPM的神经声码器相同。实验结果表明，在分析合成和语音增强方案中，Specgrad比常规DDPM的神经声码器产生比常规DDPM的更高的语音波形。音频演示可在wavegrad.github.io/specgrad/上获得。

Extracting complex structures from grid-based data is a common key step in automated medical image analysis. The conventional solution to recovering tree-structured geometries typically involves computing the minimal cost path through intermediate representations derived from segmentation masks. However, this methodology has significant limitations in the context of projective imaging of tree-structured 3D anatomical data such as coronary arteries, since there are often overlapping branches in the 2D projection. In this work, we propose a novel approach to predicting tree connectivity structure which reformulates the task as an optimization problem over individual steps of a recursive process. We design and train a two-stage model which leverages the UNet and Transformer architectures and introduces an image-based prompting technique. Our proposed method achieves compelling results on a pair of synthetic datasets, and outperforms a shortest-path baseline.

Coronary Computed Tomography Angiography (CCTA) provides information on the presence, extent, and severity of obstructive coronary artery disease. Large-scale clinical studies analyzing CCTA-derived metrics typically require ground-truth validation in the form of high-fidelity 3D intravascular imaging. However, manual rigid alignment of intravascular images to corresponding CCTA images is both time consuming and user-dependent. Moreover, intravascular modalities suffer from several non-rigid motion-induced distortions arising from distortions in the imaging catheter path. To address these issues, we here present a semi-automatic segmentation-based framework for both rigid and non-rigid matching of intravascular images to CCTA images. We formulate the problem in terms of finding the optimal \emph{virtual catheter path} that samples the CCTA data to recapitulate the coronary artery morphology found in the intravascular image. We validate our co-registration framework on a cohort of $n=40$ patients using bifurcation landmarks as ground truth for longitudinal and rotational registration. Our results indicate that our non-rigid registration significantly outperforms other co-registration approaches for luminal bifurcation alignment in both longitudinal (mean mismatch: 3.3 frames) and rotational directions (mean mismatch: 28.6 degrees). By providing a differentiable framework for automatic multi-modal intravascular data fusion, our developed co-registration modules significantly reduces the manual effort required to conduct large-scale multi-modal clinical studies while also providing a solid foundation for the development of machine learning-based co-registration approaches.

Fusion-in-Decoder (FiD) is a powerful retrieval-augmented language model that sets the state-of-the-art on many knowledge-intensive NLP tasks. However, FiD suffers from very expensive inference. We show that the majority of inference time results from memory bandwidth constraints in the decoder, and propose two simple changes to the FiD architecture to speed up inference by 7x. The faster decoder inference then allows for a much larger decoder. We denote FiD with the above modifications as FiDO, and show that it strongly improves performance over existing FiD models for a wide range of inference budgets. For example, FiDO-Large-XXL performs faster inference than FiD-Base and achieves better performance than FiD-Large.

Recent work in large language modeling (LLMs) has used fine-tuning to align outputs with the preferences of a prototypical user. This work assumes that human preferences are static and homogeneous across individuals, so that aligning to a a single "generic" user will confer more general alignment. Here, we embrace the heterogeneity of human preferences to consider a different challenge: how might a machine help people with diverse views find agreement? We fine-tune a 70 billion parameter LLM to generate statements that maximize the expected approval for a group of people with potentially diverse opinions. Human participants provide written opinions on thousands of questions touching on moral and political issues (e.g., "should we raise taxes on the rich?"), and rate the LLM's generated candidate consensus statements for agreement and quality. A reward model is then trained to predict individual preferences, enabling it to quantify and rank consensus statements in terms of their appeal to the overall group, defined according to different aggregation (social welfare) functions. The model produces consensus statements that are preferred by human users over those from prompted LLMs (>70%) and significantly outperforms a tight fine-tuned baseline that lacks the final ranking step. Further, our best model's consensus statements are preferred over the best human-generated opinions (>65%). We find that when we silently constructed consensus statements from only a subset of group members, those who were excluded were more likely to dissent, revealing the sensitivity of the consensus to individual contributions. These results highlight the potential to use LLMs to help groups of humans align their values with one another.

Large language models (LLMs) have been shown to be able to perform new tasks based on a few demonstrations or natural language instructions. While these capabilities have led to widespread adoption, most LLMs are developed by resource-rich organizations and are frequently kept from the public. As a step towards democratizing this powerful technology, we present BLOOM, a 176B-parameter open-access language model designed and built thanks to a collaboration of hundreds of researchers. BLOOM is a decoder-only Transformer language model that was trained on the ROOTS corpus, a dataset comprising hundreds of sources in 46 natural and 13 programming languages (59 in total). We find that BLOOM achieves competitive performance on a wide variety of benchmarks, with stronger results after undergoing multitask prompted finetuning. To facilitate future research and applications using LLMs, we publicly release our models and code under the Responsible AI License.

Policies produced by deep reinforcement learning are typically characterised by their learning curves, but they remain poorly understood in many other respects. ReLU-based policies result in a partitioning of the input space into piecewise linear regions. We seek to understand how observed region counts and their densities evolve during deep reinforcement learning using empirical results that span a range of continuous control tasks and policy network dimensions. Intuitively, we may expect that during training, the region density increases in the areas that are frequently visited by the policy, thereby affording fine-grained control. We use recent theoretical and empirical results for the linear regions induced by neural networks in supervised learning settings for grounding and comparison of our results. Empirically, we find that the region density increases only moderately throughout training, as measured along fixed trajectories coming from the final policy. However, the trajectories themselves also increase in length during training, and thus the region densities decrease as seen from the perspective of the current trajectory. Our findings suggest that the complexity of deep reinforcement learning policies does not principally emerge from a significant growth in the complexity of functions observed on-and-around trajectories of the policy.

Reinforcement Learning (RL) has seen many recent successes for quadruped robot control. The imitation of reference motions provides a simple and powerful prior for guiding solutions towards desired solutions without the need for meticulous reward design. While much work uses motion capture data or hand-crafted trajectories as the reference motion, relatively little work has explored the use of reference motions coming from model-based trajectory optimization. In this work, we investigate several design considerations that arise with such a framework, as demonstrated through four dynamic behaviours: trot, front hop, 180 backflip, and biped stepping. These are trained in simulation and transferred to a physical Solo 8 quadruped robot without further adaptation. In particular, we explore the space of feed-forward designs afforded by the trajectory optimizer to understand its impact on RL learning efficiency and sim-to-real transfer. These findings contribute to the long standing goal of producing robot controllers that combine the interpretability and precision of model-based optimization with the robustness that model-free RL-based controllers offer.

本文描述了我们对第9届论证挖掘研讨会共同任务的贡献（2022）。我们的方法使用大型语言模型来进行论证质量预测的任务。我们使用GPT-3进行及时的工程，并研究培训范式多任务学习，对比度学习和中任务培训。我们发现混合预测设置优于单个模型。提示GPT-3最适合预测论点有效性，而论证新颖性最好通过使用所有三个训练范式训练的模型来估算。

在典型的自主驾驶堆栈中，计划和控制系统代表了两个最关键的组件，其中传感器检索并通过感知算法处理的数据用于实施安全舒适的自动驾驶行为。特别是，计划模块可以预测自动驾驶汽车应遵循正确的高级操作的路径，而控制系统则执行一系列低级动作，控制转向角度，油门和制动器。在这项工作中，我们提出了一个无模型的深钢筋学习计划者培训一个可以预测加速度和转向角度的神经网络，从而获得了一个单个模块，可以使用自我自我的本地化和感知算法处理的数据来驱动车辆-驾车。特别是，在模拟中进行了全面训练的系统能够在模拟和帕尔马市现实世界中的无障碍环境中平稳驱动，证明该系统具有良好的概括能力，也可以驱动驱动在培训方案之外的那些部分。此外，为了将系统部署在真正的自动驾驶汽车上，并减少模拟和现实世界中的差距，我们还开发了一个由微小的神经网络表示的模块，能够在期间重现真正的车辆动态行为模拟的培训。