符号音乐分割是将符号旋律分为较小有意义的群体（例如旋律短语）的过程。我们提出了一种无监督的方法来分割符号音乐。提出的模型基于时间预测误差模型的合奏。在训练过程中，每个模型都预测了下一个令牌，以识别音乐短语变化。在测试时，我们执行峰值检测算法以选择候选段。最后，我们汇总了参与合奏的每个模型以预测最终分割的预测。结果表明，在考虑F-SCORE和R-VALUE时，建议的方法在无监督的设置下达到了Essen Folksong数据集的最先进性能。我们还提供消融研究，以更好地评估每个模型组件对最终结果的贡献。正如预期的那样，提出的方法不如监督环境，这为未来的研究提供了改善的空间，考虑到无监督和监督方法之间的差距。

多智能体增强学习（MARL）的最新进展提供了各种工具，支持代理能力适应其环境中的意外变化，并鉴于环境的动态性质（可能会通过其他情况加剧代理商）。在这项工作中，我们强调了集团有效合作的能力与集团的弹性之间的关系，我们衡量了该集团适应环境扰动的能力。为了促进恢复力，我们建议通过新的基于混乱的通信协议进行协作，这是根据其以前经验中未对准的观察结果。我们允许有关代理人自主学习的信息的宽度和频率的决定，这被激活以减少混淆。我们在各种MARL设置中展示了我们的方法的实证评估。

The task of reconstructing 3D human motion has wideranging applications. The gold standard Motion capture (MoCap) systems are accurate but inaccessible to the general public due to their cost, hardware and space constraints. In contrast, monocular human mesh recovery (HMR) methods are much more accessible than MoCap as they take single-view videos as inputs. Replacing the multi-view Mo- Cap systems with a monocular HMR method would break the current barriers to collecting accurate 3D motion thus making exciting applications like motion analysis and motiondriven animation accessible to the general public. However, performance of existing HMR methods degrade when the video contains challenging and dynamic motion that is not in existing MoCap datasets used for training. This reduces its appeal as dynamic motion is frequently the target in 3D motion recovery in the aforementioned applications. Our study aims to bridge the gap between monocular HMR and multi-view MoCap systems by leveraging information shared across multiple video instances of the same action. We introduce the Neural Motion (NeMo) field. It is optimized to represent the underlying 3D motions across a set of videos of the same action. Empirically, we show that NeMo can recover 3D motion in sports using videos from the Penn Action dataset, where NeMo outperforms existing HMR methods in terms of 2D keypoint detection. To further validate NeMo using 3D metrics, we collected a small MoCap dataset mimicking actions in Penn Action,and show that NeMo achieves better 3D reconstruction compared to various baselines.

We propose AnyTOD, an end-to-end task-oriented dialog (TOD) system with zero-shot capability for unseen tasks. We view TOD as a program executed by a language model (LM), where program logic and ontology is provided by a designer in the form of a schema. To enable generalization onto unseen schemas and programs without prior training, AnyTOD adopts a neuro-symbolic approach. A neural LM keeps track of events that occur during a conversation, and a symbolic program implementing the dialog policy is executed to recommend next actions AnyTOD should take. This approach drastically reduces data annotation and model training requirements, addressing a long-standing challenge in TOD research: rapidly adapting a TOD system to unseen tasks and domains. We demonstrate state-of-the-art results on the STAR and ABCD benchmarks, as well as AnyTOD's strong zero-shot transfer capability in low-resource settings. In addition, we release STARv2, an updated version of the STAR dataset with richer data annotations, for benchmarking zero-shot end-to-end TOD models.

A long-standing goal of machine-learning-based protein engineering is to accelerate the discovery of novel mutations that improve the function of a known protein. We introduce a sampling framework for evolving proteins in silico that supports mixing and matching a variety of unsupervised models, such as protein language models, and supervised models that predict protein function from sequence. By composing these models, we aim to improve our ability to evaluate unseen mutations and constrain search to regions of sequence space likely to contain functional proteins. Our framework achieves this without any model fine-tuning or re-training by constructing a product of experts distribution directly in discrete protein space. Instead of resorting to brute force search or random sampling, which is typical of classic directed evolution, we introduce a fast MCMC sampler that uses gradients to propose promising mutations. We conduct in silico directed evolution experiments on wide fitness landscapes and across a range of different pre-trained unsupervised models, including a 650M parameter protein language model. Our results demonstrate an ability to efficiently discover variants with high evolutionary likelihood as well as estimated activity multiple mutations away from a wild type protein, suggesting our sampler provides a practical and effective new paradigm for machine-learning-based protein engineering.

Most research on task oriented dialog modeling is based on written text input. However, users interact with practical dialog systems often using speech as input. Typically, systems convert speech into text using an Automatic Speech Recognition (ASR) system, introducing errors. Furthermore, these systems do not address the differences in written and spoken language. The research on this topic is stymied by the lack of a public corpus. Motivated by these considerations, our goal in hosting the speech-aware dialog state tracking challenge was to create a public corpus or task which can be used to investigate the performance gap between the written and spoken forms of input, develop models that could alleviate this gap, and establish whether Text-to-Speech-based (TTS) systems is a reasonable surrogate to the more-labor intensive human data collection. We created three spoken versions of the popular written-domain MultiWoz task -- (a) TTS-Verbatim: written user inputs were converted into speech waveforms using a TTS system, (b) Human-Verbatim: humans spoke the user inputs verbatim, and (c) Human-paraphrased: humans paraphrased the user inputs. Additionally, we provided different forms of ASR output to encourage wider participation from teams that may not have access to state-of-the-art ASR systems. These included ASR transcripts, word time stamps, and latent representations of the audio (audio encoder outputs). In this paper, we describe the corpus, report results from participating teams, provide preliminary analyses of their results, and summarize the current state-of-the-art in this domain.

As AI systems become more capable, we would like to enlist their help to supervise other AIs. We experiment with methods for training a harmless AI assistant through self-improvement, without any human labels identifying harmful outputs. The only human oversight is provided through a list of rules or principles, and so we refer to the method as 'Constitutional AI'. The process involves both a supervised learning and a reinforcement learning phase. In the supervised phase we sample from an initial model, then generate self-critiques and revisions, and then finetune the original model on revised responses. In the RL phase, we sample from the finetuned model, use a model to evaluate which of the two samples is better, and then train a preference model from this dataset of AI preferences. We then train with RL using the preference model as the reward signal, i.e. we use 'RL from AI Feedback' (RLAIF). As a result we are able to train a harmless but non-evasive AI assistant that engages with harmful queries by explaining its objections to them. Both the SL and RL methods can leverage chain-of-thought style reasoning to improve the human-judged performance and transparency of AI decision making. These methods make it possible to control AI behavior more precisely and with far fewer human labels.

Detection Transformer (DETR) directly transforms queries to unique objects by using one-to-one bipartite matching during training and enables end-to-end object detection. Recently, these models have surpassed traditional detectors on COCO with undeniable elegance. However, they differ from traditional detectors in multiple designs, including model architecture and training schedules, and thus the effectiveness of one-to-one matching is not fully understood. In this work, we conduct a strict comparison between the one-to-one Hungarian matching in DETRs and the one-to-many label assignments in traditional detectors with non-maximum supervision (NMS). Surprisingly, we observe one-to-many assignments with NMS consistently outperform standard one-to-one matching under the same setting, with a significant gain of up to 2.5 mAP. Our detector that trains Deformable-DETR with traditional IoU-based label assignment achieved 50.2 COCO mAP within 12 epochs (1x schedule) with ResNet50 backbone, outperforming all existing traditional or transformer-based detectors in this setting. On multiple datasets, schedules, and architectures, we consistently show bipartite matching is unnecessary for performant detection transformers. Furthermore, we attribute the success of detection transformers to their expressive transformer architecture. Code is available at https://github.com/jozhang97/DETA.

Noninvasive X-ray imaging of nanoscale three-dimensional objects, e.g. integrated circuits (ICs), generally requires two types of scanning: ptychographic, which is translational and returns estimates of complex electromagnetic field through ICs; and tomographic scanning, which collects complex field projections from multiple angles. Here, we present Attentional Ptycho-Tomography (APT), an approach trained to provide accurate reconstructions of ICs despite incomplete measurements, using a dramatically reduced amount of angular scanning. Training process includes regularizing priors based on typical IC patterns and the physics of X-ray propagation. We demonstrate that APT with 12-time reduced angles achieves fidelity comparable to the gold standard with the original set of angles. With the same set of reduced angles, APT also outperforms baseline reconstruction methods. In our experiments, APT achieves 108-time aggregate reduction in data acquisition and computation without compromising quality. We expect our physics-assisted machine learning framework could also be applied to other branches of nanoscale imaging.

Oxidation states are the charges of atoms after their ionic approximation of their bonds, which have been widely used in charge-neutrality verification, crystal structure determination, and reaction estimation. Currently only heuristic rules exist for guessing the oxidation states of a given compound with many exceptions. Recent work has developed machine learning models based on heuristic structural features for predicting the oxidation states of metal ions. However, composition based oxidation state prediction still remains elusive so far, which is more important in new material discovery for which the structures are not even available. This work proposes a novel deep learning based BERT transformer language model BERTOS for predicting the oxidation states of all elements of inorganic compounds given only their chemical composition. Our model achieves 96.82\% accuracy for all-element oxidation states prediction benchmarked on the cleaned ICSD dataset and achieves 97.61\% accuracy for oxide materials. We also demonstrate how it can be used to conduct large-scale screening of hypothetical material compositions for materials discovery.