We study the problem of efficient generative inference for Transformer models, in one of its most challenging settings: large deep models, with tight latency targets and long sequence lengths. Better understanding of the engineering tradeoffs for inference for large Transformer-based models is important as use cases of these models are growing rapidly throughout application areas. We develop a simple analytical model for inference efficiency to select the best multi-dimensional partitioning techniques optimized for TPU v4 slices based on the application requirements. We combine these with a suite of low-level optimizations to achieve a new Pareto frontier on the latency and model FLOPS utilization (MFU) tradeoffs on 500B+ parameter models that outperforms the FasterTransformer suite of benchmarks. We further show that with appropriate partitioning, the lower memory requirements of multiquery attention (i.e. multiple query heads share single key/value head) enables scaling up to 32x larger context lengths. Finally, we achieve a low-batch-size latency of 29ms per token during generation (using int8 weight quantization) and a 76% MFU during large-batch-size processing of input tokens, while supporting a long 2048-token context length on the PaLM 540B parameter model.

Finetuning language models on a collection of datasets phrased as instructions has been shown to improve model performance and generalization to unseen tasks. In this paper we explore instruction finetuning with a particular focus on (1) scaling the number of tasks, (2) scaling the model size, and (3) finetuning on chain-of-thought data. We find that instruction finetuning with the above aspects dramatically improves performance on a variety of model classes (PaLM, T5, U-PaLM), prompting setups (zero-shot, few-shot, CoT), and evaluation benchmarks (MMLU, BBH, TyDiQA, MGSM, open-ended generation). For instance, Flan-PaLM 540B instruction-finetuned on 1.8K tasks outperforms PALM 540B by a large margin (+9.4% on average). Flan-PaLM 540B achieves state-of-the-art performance on several benchmarks, such as 75.2% on five-shot MMLU. We also publicly release Flan-T5 checkpoints, which achieve strong few-shot performance even compared to much larger models, such as PaLM 62B. Overall, instruction finetuning is a general method for improving the performance and usability of pretrained language models.

大型语言模型已被证明可以使用少量学习来实现各种自然语言任务的出色表现，这大大减少了将模型调整到特定应用程序所需的特定任务培训示例的数量。为了进一步了解量表对少量学习的影响，我们培训了一个5400亿个参数，密集激活的变压器语言模型，我们称之为“途径”语言模型棕榈。我们使用Pathways在6144 TPU V4芯片上训练了Palm，这是一种新的ML系统，可在多个TPU POD上进行高效的训练。我们通过在数百种语言理解和产生基准的基准方面实现最先进的学习结果来证明扩展的持续好处。在这些任务中，Palm 540B实现了突破性的表现，在一系列多步推理任务上表现出色，超过了最新的最新表现，并且在最近发布的Big Benchmark上表现优于平均人类表现。大量的大型基础任务显示出与模型量表的不连续改进，这意味着当我们扩展到最大模型时，性能急剧增加。 Palm在多语言任务和源代码生成方面也具有很强的功能，我们在各种基准测试中证明了这一点。我们还提供了有关偏见和毒性的全面分析，并研究了训练数据记忆的程度，相对于模型量表。最后，我们讨论与大语言模型有关的道德考虑，并讨论潜在的缓解策略。

我们提供了一种新的单调改进保证，以优化合作多代理增强学习（MARL）中的分散政策，即使过渡动态是非平稳的。这项新分析提供了对两种最新的MARL参与者批评方法的强劲表现的理论理解，即独立的近端策略优化（IPPO）和多代理PPO（MAPPO）（MAPPO），它们都依赖于独立比率，即计算概率，每个代理商的政策分别比率。我们表明，尽管独立比率引起的非平稳性，但由于对所有分散政策的信任区域约束，仍会产生单调的改进保证。我们还可以根据培训中的代理数量来界定独立比率，从而以原则性的方式有效地执行这种信任区域约束，从而为近端剪辑提供了理论基础。此外，我们表明，当IPPO和Mappo中优化的替代目标在批评者收敛到固定点时实质上是等效的。最后，我们的经验结果支持以下假设：IPPO和MAPPO的强劲表现是通过削减集中式培训来执行这种信任区域约束的直接结果，而该执行的超参数的良好值对此对此具有高度敏感性正如我们的理论分析所预测的那样。

We introduce a new language representation model called BERT, which stands for Bidirectional Encoder Representations from Transformers. Unlike recent language representation models (Peters et al., 2018a;Radford et al., 2018), BERT is designed to pretrain deep bidirectional representations from unlabeled text by jointly conditioning on both left and right context in all layers. As a result, the pre-trained BERT model can be finetuned with just one additional output layer to create state-of-the-art models for a wide range of tasks, such as question answering and language inference, without substantial taskspecific architecture modifications.BERT is conceptually simple and empirically powerful. It obtains new state-of-the-art results on eleven natural language processing tasks, including pushing the GLUE score to 80.5% (7.7% point absolute improvement), MultiNLI accuracy to 86.7% (4.6% absolute improvement), SQuAD v1.1 question answering Test F1 to 93.2 (1.5 point absolute improvement) and SQuAD v2.0 Test F1 to 83.1 (5.1 point absolute improvement).

Biological systems and processes are networks of complex nonlinear regulatory interactions between nucleic acids, proteins, and metabolites. A natural way in which to represent these interaction networks is through the use of a graph. In this formulation, each node represents a nucleic acid, protein, or metabolite and edges represent intermolecular interactions (inhibition, regulation, promotion, coexpression, etc.). In this work, a novel algorithm for the discovery of latent graph structures given experimental data is presented.

The Government of Kerala had increased the frequency of supply of free food kits owing to the pandemic, however, these items were static and not indicative of the personal preferences of the consumers. This paper conducts a comparative analysis of various clustering techniques on a scaled-down version of a real-world dataset obtained through a conjoint analysis-based survey. Clustering carried out by centroid-based methods such as k means is analyzed and the results are plotted along with SVD, and finally, a conclusion is reached as to which among the two is better. Once the clusters have been formulated, commodities are also decided upon for each cluster. Also, clustering is further enhanced by reassignment, based on a specific cluster loss threshold. Thus, the most efficacious clustering technique for designing a food kit tailored to the needs of individuals is finally obtained.

Over the past decade, neural networks have been successful at making predictions from biological sequences, especially in the context of regulatory genomics. As in other fields of deep learning, tools have been devised to extract features such as sequence motifs that can explain the predictions made by a trained network. Here we intend to go beyond explainable machine learning and introduce SEISM, a selective inference procedure to test the association between these extracted features and the predicted phenotype. In particular, we discuss how training a one-layer convolutional network is formally equivalent to selecting motifs maximizing some association score. We adapt existing sampling-based selective inference procedures by quantizing this selection over an infinite set to a large but finite grid. Finally, we show that sampling under a specific choice of parameters is sufficient to characterize the composite null hypothesis typically used for selective inference-a result that goes well beyond our particular framework. We illustrate the behavior of our method in terms of calibration, power and speed and discuss its power/speed trade-off with a simpler data-split strategy. SEISM paves the way to an easier analysis of neural networks used in regulatory genomics, and to more powerful methods for genome wide association studies (GWAS).

Prior works on improving speech quality with visual input typically study each type of auditory distortion separately (e.g., separation, inpainting, video-to-speech) and present tailored algorithms. This paper proposes to unify these subjects and study Generalized Speech Enhancement, where the goal is not to reconstruct the exact reference clean signal, but to focus on improving certain aspects of speech. In particular, this paper concerns intelligibility, quality, and video synchronization. We cast the problem as audio-visual speech resynthesis, which is composed of two steps: pseudo audio-visual speech recognition (P-AVSR) and pseudo text-to-speech synthesis (P-TTS). P-AVSR and P-TTS are connected by discrete units derived from a self-supervised speech model. Moreover, we utilize self-supervised audio-visual speech model to initialize P-AVSR. The proposed model is coined ReVISE. ReVISE is the first high-quality model for in-the-wild video-to-speech synthesis and achieves superior performance on all LRS3 audio-visual enhancement tasks with a single model. To demonstrates its applicability in the real world, ReVISE is also evaluated on EasyCom, an audio-visual benchmark collected under challenging acoustic conditions with only 1.6 hours of training data. Similarly, ReVISE greatly suppresses noise and improves quality. Project page: https://wnhsu.github.io/ReVISE.

Due to the high activation sparsity and use of accumulates (AC) instead of expensive multiply-and-accumulates (MAC), neuromorphic spiking neural networks (SNNs) have emerged as a promising low-power alternative to traditional DNNs for several computer vision (CV) applications. However, most existing SNNs require multiple time steps for acceptable inference accuracy, hindering real-time deployment and increasing spiking activity and, consequently, energy consumption. Recent works proposed direct encoding that directly feeds the analog pixel values in the first layer of the SNN in order to significantly reduce the number of time steps. Although the overhead for the first layer MACs with direct encoding is negligible for deep SNNs and the CV processing is efficient using SNNs, the data transfer between the image sensors and the downstream processing costs significant bandwidth and may dominate the total energy. To mitigate this concern, we propose an in-sensor computing hardware-software co-design framework for SNNs targeting image recognition tasks. Our approach reduces the bandwidth between sensing and processing by 12-96x and the resulting total energy by 2.32x compared to traditional CV processing, with a 3.8% reduction in accuracy on ImageNet.