Author: Synced

Machine Intelligence | Technology & Industry | Information & Analysis
AI Computer Vision & Graphics Machine Learning & Data Science Research

Meta AI’s OMNIVORE: A Modality-Agnostic Single Vision Model With Cross-Modal Generalization

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.

AI Machine Learning & Data Science Research

Meet Hyper-Tune: New SOTA Efficient Distributed Automatic Hyperparameter Tuning at Scale

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.

AI Machine Learning & Data Science Research

Less is More: Understanding Neural Network Decisions via Simplified Yet Informative Inputs

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.

AI Computer Vision & Graphics Machine Learning & Data Science Popular Research

Pushing the Limits of Self-Supervised ResNets: DeepMind’s ReLICv2 Beats Strong Supervised Baselines on ImageNet

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).

AI Machine Learning & Data Science Research

Predicting Downstream Model Performance at Early Training Stages: A New Perspective on Neural Network Selection via Edge Dynamics

A research team from Rensselaer Polytechnic Institute, Thomas J. Watson Research Center and the University of California, Los Angeles proposes a novel framework for effective pretrained neural network model selection for downstream tasks that forecasts the predictive ability of a model with its cumulative information in the early phase of neural network training.

AI Machine Learning & Data Science Research

Turning a Raspberry Pi Into a Brain-Computer Interface? Researchers Open-Source the Low-Cost, High-Precision PIEEG

PhD electronic researcher Ildar Rakhmatulin and brain-computer interface developer Sebastian Völkl open-source an inexpensive, high-precision, easy-to-maintain PIEEG board that can convert a Raspberry Pi into a brain-computer interface for measuring and processing eight real-time EEG (Electroencephalography) signals.

AI Machine Learning & Data Science Research

Counterfactual Memorization in Language Models: Distinguishing Rare from Common Memorization

A team from Google Research, University of Pennsylvania and Cornell University proposes a principled perspective to filter out common memorization for LMs, introducing “counterfactual memorization” to measure the expected change in a model’s prediction and distinguish “rare” (episodic) memorization from “common” (semantic) memorization in neural LMs.

AI Machine Learning & Data Science Research

Baidu’s 10-Billion Scale ERNIE-ViLG Unified Generative Pretraining Framework Achieves SOTA Performance on Bidirectional Vision-Language Generation Tasks

Baidu researchers propose ERNIE-ViLG, a 10-billion parameter scale pretraining framework for bidirectional text-image generation. Pretrained on 145 million (Chinese) image-text pairs, ERNIE-ViLG achieves state-of-the-art performance on both text-to-image and image-to-text generation tasks.

AI Machine Learning & Data Science Popular Research

A Neural Network Solves, Grades & Generates University-Level Mathematics Problems by Program Synthesis

In the new paper A Neural Network Solves and Generates Mathematics Problems by Program Synthesis: Calculus, Differential Equations, Linear Algebra, and More, a research team from MIT, Columbia University, Harvard University and University of Waterloo proposes a neural network that can solve university-level mathematics problems via program synthesis.

AI Computer Vision & Graphics Machine Learning & Data Science Research

Facebook AI & JHU’s MaskFeat Method Surpasses Kaiming He’s MAE, Sets New SOTA in Video Action Recognition

In the new paper Masked Feature Prediction for Self-Supervised Visual Pre-Training, a Facebook AI Research and Johns Hopkins University team presents a novel Masked Feature Prediction (MaskFeat) approach for the self-supervised pretraining of video models that achieves SOTA results on video benchmarks.

AI Machine Learning & Data Science Research

Google Proposes a ‘Simple Trick’ for Dramatically Reducing Transformers’ (Self-)Attention Memory Requirements

In the new paper Self-attention Does Not Need O(n2) Memory, a Google Research team presents novel and simple algorithms for attention and self-attention that require only constant memory and logarithmic memory and reduce the self-attention memory overhead by 59x for inference and by 32x for differentiation at a sequence length of 16384.

AI Machine Learning & Data Science Research

DeepMind’s RETRO Retrieval-Enhanced Transformer Retrieves from Trillions of Tokens, Achieving Performance Comparable to GPT-3 With 25× Fewer Parameters

A DeepMind research team proposes RETRO (Retrieval-Enhanced Transformer), an enhanced auto-regressive language model that conditions on document chunks retrieved from a large corpus and achieves performance comparable to GPT-3 and Jurassic-1 on the Pile dataset while using 25× fewer parameters.

AI Machine Learning & Data Science Nature Language Tech Research

Peng Cheng Laboratory & Baidu Release PCL-BAIDU Wenxin: The World’s First Knowledge-Enhanced 100-Billion-Scale Pretrained Language Model

Peng Cheng Laboratory (PCL) and Baidu release PCL-BAIDU Wenxin, the world’s first knowledge-enhanced 100-billion-scale pretrained language model and the largest Chinese-language monolithic model with 260 billion parameters. PCL-BAIDU Wenxin achieves state-of-the-art results on more than 60 tasks and significantly advances more than 30 benchmarks for zero-shot and few-shot learning.

AI Machine Learning & Data Science Research

UC Berkeley’s Sergey Levine Says Combining Self-Supervised and Offline RL Could Enable Algorithms That Understand the World Through Actions

In the new paper Understanding the World Through Action, UC Berkeley assistant professor in the department of electrical engineering and computer sciences Sergey Levine argues that a general, principled, and powerful framework for utilizing unlabelled data can be derived from reinforcement learning to enable machine learning systems leveraging large datasets to understand the real world.

AI Machine Learning & Data Science Popular Research

Integrating Self-Attention and Convolution: Tsinghua, Huawei & BAAI’s ACmix Achieves SOTA Performance on CV Tasks With Minimum Cost

In the new paper On the Integration of Self-Attention and Convolution, a research team from Tsinghua University, Huawei Technologies Ltd. and the Beijing Academy of Artificial Intelligence proposes ACmix, a mixed model that leverages the benefits of both self-attention and convolution for computer vision representation tasks while achieving minimum computational overhead compared to its pure convolution or self-attention counterparts.

AI Machine Learning & Data Science Research

Warsaw U, Google & OpenAI’s Terraformer Achieves a 37x Speedup Over Dense Baselines on 17B Transformer Decoding

In the new paper Sparse is Enough in Scaling Transformers, a research team from the University of Warsaw, Google Research and OpenAI proposes Scaling Transformers, a family of novel transformers that leverage sparse layers to scale efficiently and perform unbatched decoding much faster than original transformers, enabling fast inference on long sequences even with limited memory.

AI Others Research

Time-Crystalline Study Published in Nature Journal Observes a New Phase of Matter in a Quantum Processor

A team from Google Research, Stanford University, University of Massachusetts, University of California, Columbia University, Princeton University, Max Planck Institute for the Physics of Complex Systems and University of Oxford uses a quantum processor to observe a time crystal, a new phase of matter which could be one of the most significant physical discoveries in decades.

AI Machine Learning & Data Science Popular Research

Google, Cambridge U & Alan Turing Institute Propose PolyViT: A Universal Transformer for Image, Video, and Audio Classification

A research team from Google Research, University of Cambridge and Alan Turing Institute proposes PolyViT, a single transformer model capable of processing multiple modalities and datasets. PolyViT is parameter-efficient and learns representations that generalize across multiple domains.

AI Computer Vision & Graphics Machine Learning & Data Science Research

Microsoft’s ‘Florence’ General-Purpose Foundation Model Achieves SOTA Results on Dozens of CV Benchmarks

In the paper A New Foundation Model for Computer Vision, a Microsoft research team proposes Florence, a novel foundation model for computer vision that significantly outperforms previous large-scale pretraining approaches and achieves new SOTA results across a wide range of visual and visual-linguistic benchmarks.

AI Machine Learning & Data Science Research

Kwai, Kuaishou & ETH Zürich Propose PERSIA, a Distributed Training System That Supports Deep Learning-Based Recommenders of up to 100 Trillion Parameters

A research team from Kwai Inc., Kuaishou Technology and ETH Zürich builds PERSIA, an efficient distributed training system that leverages a novel hybrid training algorithm to ensure both training efficiency and accuracy for extremely large deep learning recommender systems of up to 100 trillion parameters.