Google & TUAT’s WaveFit Neural Vocoder Achieves Inference Speeds 240x Faster Than WaveRNN
A neural vocoder is a neural network designed to generate speech waveforms given acoustic features — often used as aContinue Reading
Tag: Machine Learning
UNC Chapel Hill’s Textless Vision-Language Transformer: Comparable Performance to Text-Based Approaches but 28x Faster
In the new paper TVLT: Textless Vision-Language Transformer, researchers from UNC Chapel Hill present the Textless Vision-Language Transformer (TVLT) for vision-and-language representation learning. TVLT uses only raw visual and audio inputs and performs comparably to its text-based counterparts but requires only 1/3 the parameters and achieves 28x faster inference speeds.
Google & DeepMind Propose Geometric Complexity for DNN Analysis and Evaluation
In the new paper Why Neural Networks Find Simple Solutions: The Many Regularizers of Geometric Complexity, a research team from Google and DeepMind proposes Geometric Complexity (GC), a measure of deep neural network model complexity that serves as a useful tool for understanding the underlying mechanisms of complexity control.
Microsoft & Xiamen U’s Progressive Distillation Method Sets New SOTA for Dense Retrieval
In the new paper Progressive Distillation for Dense Retrieval, a research team from Xiamen U and Microsoft Research presents PROD, a progressive distillation method for dense retrieval that achieves state-of-the-art performance on five widely used benchmarks.
DeepMind, Oxford U, IDSIA, Mila & Purdue U’s General Neural Algorithmic Learner Matches Task-Specific Expert Performance
In the new paper A Generalist Neural Algorithmic Learner, a research team from DeepMind, University of Oxford, IDSIA, Mila, and Purdue University presents a novel generalist neural algorithmic learner — a single graph neural network (GNN) capable of solving various classical algorithms at single-task expert level.
Google’s Promptagator Creates Task-Specific Neural Retrievers From Only 8 Examples
In the new paper Promptagator: Few-shot Dense Retrieval From 8 Examples, a Google Research team proposes Prompt-based Query Generation for Retriever (Promptagator), a novel and simple approach for few-shot retrieval that leverages large language model (LLM) prompting to generate synthetic task-specific training data.
Columbia U’s Infinitely Deep Probabilistic Model Adapts Its Complexity to the Data at Hand
While today’s deep neural networks (DNNs) are driving AI’s deep-learning revolution, determining a DNN’s appropriate complexity remains challenging. If aContinue Reading
Transformers on Edge Devices? Monash U’s Energy-Saving Attention With Linear Complexity Reduces Compute Cost by 73%
In the new paper EcoFormer: Energy-Saving Attention with Linear Complexity, a Monash University research team presents EcoFormer, an attention mechanism with linear complexity that replaces expensive multiply-accumulate operations with simple accumulations and achieves a 73 percent energy footprint reduction on ImageNet.
DeepMind’s MEME Agent Achieves Human-level Atari Game Performance 200x Faster Than Agent57
In the new paper Human-level Atari 200x Faster, a DeepMind research team applies a set of diverse strategies to Agent57, with their resulting MEME (Efficient Memory-based Exploration) agent surpassing the human baseline on all 57 Atari games in just 390 million frames — two orders of magnitude faster than Agent57.
Google Brain’s Vec2Text Models for Sentence Generation Excel in Universality, Diversity, Fluency & Semantic Structure
In the new paper Vec2text With Round-Trip Translations, Google Brain researchers explore large language models’ capabilities for generating arbitrary natural language text from inputs of fixed-size vectors — a vec2text setting — and propose a simple data augmentation approach based on round-trip translations to improve vec2text model performance.
DeepMind’s ‘Expert-Aware’ Data Augmentation Technique Enables Data-Efficient Learning from Parametric Experts
The new DeepMind paper Data Augmentation for Efficient Learning from Parametric Experts proposes Augmented Policy Cloning (APC), a simple yet effective data-augmentation approach designed to support data-efficient learning from parametric experts. The method significantly improves data efficiency across various control and reinforcement learning settings.
Peking U & Microsoft’s Knowledge Attribution Method Enables Editing Factual Knowledge in Pretrained Transformers Without Fine-Tuning
In the new paper Knowledge Neurons in Pretrained Transformers, a research team from Peking University and Microsoft Research introduces a knowledge attribution method that identifies the neurons that store factual knowledge in pretrained transformers and leverages these neurons to edit factual knowledge in transformers without any fine-tuning.
DeepMind’s Model-Based Offline Options Framework Supports Automatic Skill & Behaviour Discovery, Boosts Transfer Capabilities
In the new paper MO2: Model-Based Offline Options, a DeepMind research team introduces Model-Based Offline Options (MO2), an offline hindsight bottleneck options framework that supports sample-efficient option discovery over continuous state-action spaces for efficient skill transfer to new tasks.
CMU’s ASR2K Pipeline Recognizes Speech in 1909 Languages Without Audio
In the new paper ASR2K: Speech Recognition for Around 2000 Languages Without Audio, a Carnegie Mellon University research team introduces a speech recognition pipeline that can recognize almost 2000 languages without audio requirements.
Toward a Turing Machine? Microsoft & Harvard Propose Neural Networks That Discover Learning Algorithms Themselves
A research team from Microsoft and Harvard University demonstrates that neural networks can discover succinct learning algorithms on their own in polynomial time and presents an architecture that combines recurrent weight-sharing between layers and convolutional weight-sharing to reduce parameter size from even trillions of nodes down to a constant.
Using State-Of-The-Art AI Models for Free: Try OPT-175B on Your Cellphone and Laptop
Colossal-AI, a unified deep learning system for the big model era, can efficiently and rapidly deploy large AI model training and inference with just a few lines of code, and promote the low-cost application and implementation of big models.
Meta AI & Inria Saclay Advance BCIs to Enable Natural Speech Decoding From Non-Invasive Brain Recordings
In the new paper Decoding Speech From Non-Invasive Brain Recordings, a research team from Meta AI and the Inria Saclay Centre presents a single end-to-end architecture for decoding natural speech processing from non-invasive magnetoencephalography (MEG) or electroencephalography (EEG) brain recordings that can detect macroscopic brain signals in real-time.
DeepMind’s Selection-Inference Language Model System Generates Humanly Interpretable Reasoning Traces
In the new paper Faithful Reasoning Using Large Language Models, a DeepMind research team proposes a forward-chaining selection-inference model that performs faithful reasoning and provides a valid reasoning trace to improve reasoning quality and help users validate the model’s final answers.
Plan, Edit, Explain and Repeat: The PEER Collaborative Language Model Brings a Humanlike Process to Text Generation
In the new paper PEER: A Collaborative Language Model, a research team from Meta AI, Carnegie Mellon University, PSL University, and University College London presents PEER, a collaborative language model that performs a humanlike writing process — composing drafts, adding suggestions, proposing edits and providing explanations for its actions.
Princeton U & Adobe’s 3D-FM GAN Enables Precise 3D-Controllable Face Manipulation
In the new paper 3D-FM GAN: Towards 3D-Controllable Face Manipulation, a team from Princeton University and Adobe Research presents 3D-FM GAN, a novel conditional GAN framework that enables precise 3D-controllable face manipulation with high photorealism and strong identity preservation without requiring any manual tuning or optimizations.
Microsoft’s BEiT-3 Foundation Model: A ‘Big Convergence of Language, Vision, and Multimodal Pretraining’ That Achieves SOTA Results on Popular Benchmarks
In the new paper Image as a Foreign Language: BEiT Pretraining for All Vision and Vision-Language Tasks, a Microsoft research team presents BEiT-3, a general-purpose state-of-the-art multimodal foundation model for both vision and vision-language tasks that advances the big convergence of backbone architectures, pretraining tasks, and model scaling.
CMU Details 6 Years of Contributions to the National Science Foundation- Funded DialPort Project for Dialog Research
Carnegie Mellon University researchers provide background information and details on contributions to the DialPort project over the last six years in their new paper The DialPort Tools. These tools — such as the DialPort Portal and DialCrowd — will be demoed at the SIGDIAL 2022 conference next month in Edinburgh.
Microsoft’s Parameter-Efficient Z-Code++ Language Model Beats the 200x Larger GPT3-175B on Abstractive Text Summarization
In the new paper Z-Code++: A Pre-trained Language Model Optimized for Abstractive Summarization, a research team from Microsoft Azure AI and Microsoft Research presents Z-Code++, a novel encoder-decoder pretrained language model optimized for abstractive summarization that significantly improves performance on low-resource summarization tasks.
Adobe and ANU’s Paint2Pix: Intent-Accurate Image Synthesis from Simple Brushstroke Inputs
In the new paper Paint2Pix: Interactive Painting based Progressive Image Synthesis and Editing, a research team from Adobe Research and Australian National University presents paint2pix, a novel model that learns to predict users’ intentions and produce photorealistic images from primitive and coarse human brushstroke inputs.
Accelerating Structure Prediction of Protein Monomers and Multimer by 11 Times! An Open Source Solution from Colossal-AI and BioMap
Colossal-AI team and BioMap open-source their latest solution – xTrimo Multimer for protein monomer and multimer structure prediction. This new solution can predict both monomer and multimer structure simultaneously accelerating the process by up to 11 times!
Google & CMU Open-Source a Library for Graph Representation of Python Programs for Machine Learning Research
Google Research and Carnegie Mellon University have open-sourced a library for constructing Python program graph representations used in machine learning for code research. Details are presented in the report A Library for Representing Python Programs as Graphs for Machine Learning.
Microsoft, Penn U & UC San Diego’s TiCoder Framework Generates Code With 90.4% Consistency to User Intent
In the new paper Interactive Code Generation via Test-Driven User-Intent Formalization, a team from Microsoft Research, the University of Pennsylvania, and the University of California, San Diego proposes a workflow for test-driven user-intent formalization that leverages user feedback to generate code that is 90.40 percent consistent with user intent.
‘A Promising Direction for Semi-Supervised Learning’ – AWS Lab’s Semi-ViT Beats CNNs While Maintaining Scalability
In the new paper Semi-supervised Vision Transformers at Scale, a research team from AWS AI Labs proposes a semi-supervised learning pipeline for vision transformers that is stable, reduces hyperparameter tuning sensitivity, and outperforms conventional convolutional neural networks.
Georgia Tech & Google Propose a Novel Discrete Variational Autoencoder for Automatically Improving Code Efficiency
In the new paper Learning to Improve Code Efficiency, a research team from the Georgia Institute of Technology and Google Research presents a novel discrete generative latent-variable model designed to help programmers identify more computationally efficient code variants, taking a step toward automating the process of code performance optimization.
Meet Atlas: A Pretrained Retrieval Augmented Language Model That Outperforms a 540B Parameter Model But Requires 50x Fewer Parameters
In the new paper Few-shot Learning With Retrieval Augmented Language Models, a research team from Meta AI, PSL University, Inria, and University College London presents Atlas, a pretrained retrieval augmented language model that effectively learns new knowledge-intensive tasks under few-shot settings. Atlas outperforms the 540B parameter PaLM model on QA tasks while using 50x fewer parameters.
Meta AI & Mila Publicly Release BlenderBot 3: A 175B SOTA Chatbot That Continually Improves via Human Interactions
In the new paper BlenderBot 3: A Deployed Conversational Agent That Continually Learns to Responsibly Engage, researchers from Meta AI and Mila/McGill University release BlenderBot 3, a 175B parameter state-of-the-art open-domain dialogue model deployed on a public website. BlenderBot 3 is designed for continual learning via its user interactions.
Tencent’s Effidit Significantly Expands the Capabilities of AI Writing Assistants
A Tencent AI Lab research team introduces Efficient and Intelligent Editing (Effidit), a digital writing assistant that leverages large-scale neural language models to provide high-quality assistance in text completion, error checking, text polishing, keywords to sentences (K2S) and cloud input methods (cloud IME).
NVIDIA’s Minimal Video Instance Segmentation Framework Achieves SOTA Performance Without Video-Based Training
In the new paper MinVIS: A Minimal Video Instance Segmentation Framework Without Video-based Training, an NVIDIA research team presents MinVIS, a minimal video instance segmentation framework that outperforms state-of-the-art VIS approaches without requiring video-based training.
Microsoft & Arizona U’s TextWorldExpress Simulates Text Games at 1M SPS, a Speedup of 3 Orders of Magnitude
In the new paper TextWorldExpress: Simulating Text Games at One Million Steps Per Second, a research team from the University of Arizona and Microsoft Research Montréal presents TextWorldExpress, a high-performance text-game simulator that boosts throughput by approximately three orders of magnitude, reaching one million steps per second.
OpenAI Presents a Simple and Efficient Training Strategy to Boost Language Models’ Text-Infilling Capabilities
In the new paper Efficient Training of Language Models to Fill in the Middle, an OpenAI research team shows that causal decoder-based autoregressive (AR) language models can learn to infill texts via a very simple and straightforward transformation to the training data and without any architectural modifications.
IITM & UT Austin’s Generalizable NeRF Transformer Demonstrates Transformers’ Capabilities for Graphical Rendering
In the new paper Is Attention All NeRF Needs?, a research team from the Indian Institute of Technology Madras and the University of Texas at Austin proposes Generalizable NeRF Transformer (GNT), a pure and universal transformer-based architecture for efficient on-the-fly reconstruction of NeRFs. The work demonstrates that a pure attention mechanism suffices for learning a physically-grounded rendering process.
Google Introduces the First Effective Face-Motion Deblurring System for Mobile Phones
In the new paper Face Deblurring Using Dual Camera Fusion on Mobile Phones, a Google team proposes a novel dual camera fusion technique that achieves robust face deblurring in diverse motion and lighting conditions.
Fancy a Friendly Chat? Stanford NLP’s Chirpy Cardinal Enables Open-Domain and Humanlike Conversations
In the new paper Neural Generation Meets Real People: Building a Social, Informative Open-Domain Dialogue Agent, a Stanford NLP research team presents Chirpy Cardinal, an open-domain conversational social chatbot with emotional and social intelligence that enables authentic and engaging interactions with real people.
Google & DeepMind Study the Interactions Between Scaling Laws and Neural Network Architectures
In the new paper Scaling Laws vs Model Architectures: How does Inductive Bias Influence Scaling?, a research team from Google and DeepMind posits that understanding the connections between neural network architectures and scaling laws is essential for designing and evaluating new models. The team pretrains and finetunes over 100 models to reveal useful insights on the scaling behaviours of ten diverse model architectures.
Microsoft, DP Technology & Tsinghua U Enable Efficient Low-Precision Training of Gradient Boosting Decision Trees
In the new paper Quantized Training of Gradient Boosting Decision Trees, a team from Microsoft Research, DP Technology and Tsinghua University proposes a method for the low-precision training of gradient boosting decision trees via gradient quantization.