AI Technology & Industry Review
A research team from the National University of Singapore, HPC-AI Technology Inc., Helixon and Shanghai Jiao Tong University proposes FastFold, a highly efficient protein structure prediction model for training and inference that reduces AlphaFold 2’s training time from 11 days to 67 hours.
An Idiap Research Institute team proposes a novel multi-layer perceptron (MLP) model, HyperMixer, as a Green AI alternative to transformers. HyperMixer achieves comparable performance with substantially lower costs in terms of processing time, training data and hyperparameter tuning.
A research team from DeepMind, Ca’ Foscari University of Venice, University of Oxford and Athens University of Economics and Business introduces Ithaca, a deep neural network (DNN) designed for textual restoration and geographical and chronological attribution of ancient Greek inscriptions.
In the new paper Tensor Programs V: Tuning Large Neural Networks via Zero-Shot Hyperparameter Transfer, Microsoft and OpenAI researchers propose µTransfer, a method that leverages Maximal Update Parametrization (µP) to zero-shot transfer hyperparameters from small models and obtain near-optimal parameters on large models without directly tuning them.
In the new paper AutoDIME: Automatic Design of Interesting Multi-Agent Environments, an OpenAI research team explores automatic environment design for multi-agent environments using an RL-trained teacher that samples environments to maximize student learning. The work demonstrates that intrinsic teacher rewards are a promising approach for automating both single and multi-agent environment design.
In the new paper Learning Robust Real-Time Cultural Transmission Without Human Data, a DeepMind research team proposes a procedure for training artificially intelligent agents capable of flexible, high-recall, robust real-time cultural transmission from human co-players in a rich 3D physical simulation without using human data in the training pipeline.
A research team from the University of Washington, UC San Diego and Microsoft prototypes Tensor Query Processor (TQP), a query processor that runs atop tensor computation runtimes (TCRs) such as PyTorch, TVM, and ONNX Runtime, improving query execution time by up to 20x over CPU-only systems and up to 5x over specialized GPU solutions.
A Microsoft research team proposes DeepNorm, a novel normalization function that improves the stability of transformers to enable scaling that is an order of magnitude deeper (more than 1,000 layers) than previous deep transformers.
A Google research team publishes guidelines for designing more practical and reliable sparse expert models. Their pretrained 269B sparse model achieves state-of-the-art results across many natural language processing (NLP) benchmarks.
A research team from Cornell University and Google Brain introduces FLASH, a model family that achieves quality on par with fully augmented transformers while maintaining linear scalability over the context size on modern accelerators.
In the new paper DataMUX: Data Multiplexing for Neural Networks, a Princeton University research team proposes Data Multiplexing (DataMUX). The novel technique enables neural networks to process multiple inputs simultaneously and generate accurate predictions, increasing model throughput with minimal additional memory requirements.
A research team from Imperial College London and Microsoft Research introduces a cheap and accessible way to upgrade a popular off-the-shelf 3-axis 3D printer to 5 axes, enabling low-cost multi-axis and conformal 3D printing.
DeepMind researchers propose Hierarchical Perceiver (HiP), a model that retains the original Perceiver’s ability to process arbitrary modalities but is faster, can scale up to even more inputs/outputs, reduces the need for input engineering, and improves both efficiency and accuracy on classical computer vision benchmarks.
In the new paper Visual Attention Network, a research team from Tsinghua University and Nankai University introduces a novel large kernel attention (LKA) mechanism for an extremely simple and efficient Visual Attention Network (VAN) that significantly outperforms state-of-the-art vision transformers and convolutional neural networks on various computer vision tasks.
DeepMind trains agents to use keyboard and mouse commands with pixel and Document Object Model (DOM) observations to control computers, achieving state-of-the-art and human-level mean performance across all tasks on the MiniWob++ benchmark.
A research team from the University of Hong Kong, Shanghai AI Lab, Huawei Noah’s Ark Lab and the University of Washington takes dataset generation methods via large-scale pretrained language models (PLMs) to the extreme with ZEROGEN, a flexible and efficient zero-shot learning framework via dataset generation.
A research team from DeepMind and University College London proposes Neural Population Learning (NeuPL), an efficient and general framework that learns and represents diverse policies in symmetric zero-sum games within a single conditional network.
A team from Facebook AI Research, UC Berkeley and UCLA proposes Online Decision Transformers (ODT), an RL algorithm based on sequence modelling that incorporates offline pretraining and online finetuning in a unified framework and achieves performance competitive with the state-of-the-art models on the D4RL benchmark.
In the new paper Block-NeRF: Scalable Large Scene Neural View Synthesis, a team from UC Berkeley, Waymo and Google Research proposes Block-NeRF, a neural radiance fields variant capable of representing city-scale environments.
A Google Research team proposes Masked Generative Image Transformer (MaskGIT), a novel image synthesis paradigm that uses a bidirectional transformer decoder. MaskGIT significantly outperforms state-of-the-art transformer models on the ImageNet dataset and accelerates autoregressive decoding by up to 64x.
A Google Brain research team introduces EvoJAX, a JAX-based, scalable, general-purpose, hardware-accelerated neuroevolution toolkit that enables neuroevolution algorithms to work with neural networks running in parallel across multiple TPU/GPUs and achieves significant training speedups.
A team from Google Research and J.P. Morgan AI Research proposes an algorithm for scalable learning on multiplex networks with a large number of layers, improving efficiency over recent popular approaches.
A research team from Alibaba Group’s DAMO Academy proposes OFA (One For All), a pretrained model that unifies modalities and tasks to a simple Seq2Seq learning framework and achieves SOTA results on a series of multimodal tasks.
A research team from UC Berkeley, Amazon Web Services, Google, Shanghai Jiao Tong University and Duke University proposes Alpa, a compiler system for distributed deep learning on GPU clusters that automatically generates parallelization plans that match or outperform hand-tuned model-parallel training systems even on the models they were designed for.
An OpenAI research team presents an expert iteration-based neural theorem prover capable of solving a curriculum of increasingly difficult mathematical problems (such as high-school olympiad-level problems) from a set of formal statements of sufficiently varied difficulty and without the need for associated ground-truth proofs.
A DeepMind research team presents AlphaCode, an automated code-generation system that can create novel solutions for programming problems that require deep reasoning and achieves a top 54.3% ranking in programming competitions.
A research team from Microsoft and NVIDIA leverages the NVIDIA Megatron-LM and Microsoft’s DeepSpeed to create an efficient and scalable 3D parallel system that combines data, pipeline, and tensor-slicing based parallelism, achieving superior zero-, one-, and few-shot learning accuracies and new state-of-the-art results on NLP benchmarks.
A research team from the University of Oxford proposes COIN++, a neural compression framework that addresses the existing issues of COIN while maintaining its generality and can seamlessly handle a wide range of data modalities.
A research team from Mila, Québec Artificial Intelligence Institute, Université de Montréal, CIFAR and IVADO Labs challenges the assumption that task diversity will improve model performance in meta-learning, finding instead that repeating the same tasks over the training phase can achieve performance similar to models trained on uniform sampling.
A research team from Sapienza University and OpenAI introduces an explanatory learning procedure that enables machines to understand existing explanations from symbolic sequences and create new explanations for unexplained phenomena, and further proposes Critical Rationalist Network (CRN) models for discovering explanations for novel phenomena.
An OpenAI research team leverages reinforcement learning from human feedback (RLHF) to make significant progress on aligning language models with the users’ intentions. The proposed InstructGPT models are better at following instructions than GPT-3 while also more truthful and less toxic.
A team from UC Berkeley and Facebook AI Research proposes a Neural Manifold Clustering and Embedding (NMCE) method for general-purpose manifold clustering that significantly outperforms autoencoder-based deep subspace clustering approaches.
University of Illinois Urbana-Champaign and Google researchers introduce AutoDistill, an end-to-end fully automated model distillation framework that integrates model architecture exploration and multi-objective optimization for building hardware-efficient pretrained natural language processing models.
In the new paper Laplace Redux — Effortless Bayesian Deep Learning, a research team from the University of Cambridge, University of Tübingen, ETH Zurich and DeepMind conducts extensive experiments demonstrating that the Laplace approximation (LA) is a simple and cost-efficient yet competitive approximation method for inference in Bayesian deep learning.
A Meta AI research team presents OMNIVORE, a single vision model for various visual modalities that can perform cross-modal generalization and achieves performance at par or better than traditional modality-specific models of the same size.
A research team from the University of California Irvine and DeepMind proposes Anytime Optimal PSRO, a new PSRO variant for two-player zero-sum games that is guaranteed to converge to a Nash equilibrium while decreasing exploitability from iteration to iteration.
A research team from Peking University, ETH Zürich and Kuaishou Technology proposes Hyper-Tune, an efficient and robust distributed hyperparameter-tuning framework that features system optimizations such as automatic resource allocation, asynchronous scheduling and a multi-fidelity optimizer, and achieves state-of-the-art performance on multiple tuning tasks.
A research team from University Medical Center Freiburg, ML Collective, and Google Brain introduces SimpleBits — an information-reduction method that learns to synthesize simplified inputs that contain less information yet remain informative for the task, providing a new approach for exploring the basis of network decisions.
A Microsoft research team proposes DeepSpeed-MoE, comprising a novel MoE architecture design and model compression technique that reduces MoE model size by up to 3.7x and a highly optimized inference system that provides 7.3x better latency and cost compared to existing MoE inference solutions.
A DeepMind research team proposes ReLICv2, which demonstrates for the first time that representations learned without labels can consistently outperform a strong, supervised baseline on ImageNet and even achieve comparable results to state-of-the-art self-supervised vision transformers (ViTs).