The architecture of Vision Transformers (ViTs), particularly the Multi-head Attention (MHA) mechanism, imposes substantial hardware demands. Deploying ViTs on devices with varying constraints, such as mobile phones, requires multiple models of different sizes. However, this approach has limitations, such as training and storing each required model separately. This paper introduces HydraViT, a novel approach that addresses these limitations by stacking attention heads to achieve a scalable ViT. By repeatedly changing the size of the embedded dimensions throughout each layer and their corresponding number of attention heads in MHA during training, HydraViT induces multiple subnetworks. Thereby, HydraViT achieves adaptability across a wide spectrum of hardware environments while maintaining performance. Our experimental results demonstrate the efficacy of HydraViT in achieving a scalable ViT with up to 10 subnetworks, covering a wide range of resource constraints. HydraViT achieves up to 5 p.p. more accuracy with the same GMACs and up to 7 p.p. more accuracy with the same throughput on ImageNet-1K compared to the baselines, making it an effective solution for scenarios where hardware availability is diverse or varies over time.

While training with static demonstrations has shown some promise, we show that such methods fall short for controlling real GUIs due to their failure to deal with real world stochasticity and non-stationarity not captured in static observational data. This paper introduces a novel autonomous RL approach, called DigiRL, for training in-the-wild device control agents through fine-tuning a pre-trained VLM in two stages: offline RL to initialize the model, followed by offline-to-online RL. To do this, we build a scalable and parallelizable Android learning environment equipped with a VLM-based evaluator and develop a simple yet effective RL approach for learning in this domain. Our approach runs advantage-weighted RL with advantage estimators enhanced to account for stochasticity along with an automatic curriculum for deriving maximal learning signal. We demonstrate the effectiveness of DigiRL using the Android-in-the-Wild (AitW) dataset, where our 1.3B VLM trained with RL achieves a 49.5% absolute improvement - from 17.7 to 67.2% success rate - over supervised fine-tuning with static human demonstration data. These results significantly surpass not only the prior best agents, including AppAgent with GPT-4V (8.3% success rate) and the 17B CogAgent trained with AitW data (38.5%),

I've been trying to disentangle my online life from Google for a while. And as someone who wrote about Android professionally for years, it hasn't been easy. I've ditched Chrome, but I still use a Samsung Galaxy phone and Google Pixel Watch, for example. But when I finally got off the big daddy, Google Search, and switched to DuckDuckGo, it had a surprising effect: Google got better. That's a broad statement, so let me be more particular right away.

Mobile device operation tasks are increasingly becoming a popular multi-modal AI application scenario. Current Multi-modal Large Language Models (MLLMs), constrained by their training data, lack the capability to function effectively as operation assistants. Instead, MLLM-based agents, which enhance capabilities through tool invocation, are gradually being applied to this scenario. However, the two major navigation challenges in mobile device operation tasks -- task progress navigation and focus content navigation -- are difficult to effectively solve under the single-agent architecture of existing work. This is due to the overly long token sequences and the interleaved text-image data format, which limit performance.

This week in tech: Apple struggles on multiple fronts, OpenAI grows increasingly ambitious, and Trump helps some of his fans lose money on cryptocurrency. Long dominant and unassailable, Apple is showing signs of weakness. The CEO, Tim Cook, can't tame Donald Trump's threats of tariffs that would spike the price of an iPhone; Apple's AI offerings pale against its competitors; and the company can't win a Fortnite match – or a single battle in its legal war with Epic Games – to save its life. On Friday, the president threatened to levy a 25% tariff on any iPhone not made in the US. Trump said in the post: "I have long ago informed Tim Cook of Apple that I expect their iPhones that will be sold in the United States of America will be manufactured and built in the United States, not India, or anyplace else. If that is not the case, a Tariff of at least 25% must be paid by Apple to the US."

Breakthroughs, discoveries, and DIY tips sent every weekday. Amidst the flurry of AI announcements and product reveals from Google in recent months, you might have missed one of the most useful AI-powered apps in the whole collection: NotebookLM (that LM stands for Language Model). Perhaps NotebookLM has gone largely under the radar because it was originally launched as more of an academic research tool when it first appeared back in 2023. Its user interface lacks some of the slickness and accessibility of Google Gemini, and it's not quite as obvious how you're supposed to use it, or what it can do. However, NotebookLM is gradually becoming better known amongst consumers, with official apps for Android and iOS now available, alongside the web app.

A.1 Creation of the Multimodal Web Document Dataset A.1.1 Collecting of a Large Number of HTML Files Our data collection process begins by considering the 25 most recent Common Crawl It contains webpages spanning from February 2020 to January/February 2023. This process yields a total of 41.2 billion documents. Selection of English content To identify non-English content, we apply the FastText classifier (Joulin et al., 2017) to the extracted text, e ectively filtering out 63.6% of the documents. Early text deduplication Often, a set of URLs is crawled repeatedly across di erent Common Crawl snapshots. However, the content of these websites may vary as web administrators make changes over time. Hence, at this stage, we refrain from deduplicating documents based on their URLs. Instead, we perform MinHash (Broder, 1997) deduplication with 16 hashes calculated over 5-grams. To further refine the data, we eliminate documents containing substantial proportions of repeated paragraphs and n-grams, employing the methodology described in MassiveText (Rae et al., 2022).

Camera-based physiological measurement is a fast growing field of computer vision. Remote photoplethysmography (rPPG) utilizes imaging devices (e.g., cameras) to measure the peripheral blood volume pulse (BVP), and enables cardiac measurement via webcams and smartphones. However, the task is non-trivial with important pre-processing, modeling, and post-processing steps required to obtain state-of-the-art results. Replication of results and benchmarking of new models is critical for scientific progress; however, as with many other applications of deep learning, reliable codebases are not easy to find or use.

In the current landscape of pervasive smartphones and tablets, apps frequently exist across both platforms. Although apps share most graphic user interfaces (GUIs) and functionalities across phones and tablets, developers often rebuild from scratch for tablet versions, escalating costs and squandering existing design resources. Researchers are attempting to collect data and employ deep learning in automated GUIs development to enhance developers' productivity. There are currently several publicly accessible GUI page datasets for phones, but none for pairwise GUIs between phones and tablets. This poses a significant barrier to the employment of deep learning in automated GUI development. In this paper, we introduce the Papt dataset, a pioneering pairwise GUI dataset tailored for Android phones and tablets, encompassing 10,035 phone-tablet GUI page pairs sourced from 5,593 unique app pairs. We propose novel pairwise GUI collection approaches for constructing this dataset and delineate its advantages over currently prevailing datasets in the field. Through preliminary experiments on this dataset, we analyze the present challenges of utilizing deep learning in automated GUI development.