Record 27112025 · captured 2026-08-25
The world looked up Google Chrome. 30 tracked subjects, 25 discussions, 25 papers. This record is frozen and will not change.
Complete record JSON
What the most people looked up, ranked by Wikipedia pageviews for that day.
Google Chrome is a cross-platform web browser developed by Google. It was launched in September 2008 for Microsoft Windows and was built with free software components from Apple WebKit and Mozilla Firefox. Versions for Linux, macOS, iOS, iPadOS, and Android we
Dancing with the Stars (American TV series) season 34
Season thirty-four of Dancing with the Stars premiered on ABC and Disney+ on September 16, 2025, and concluded on December 2, 2025. This season, marking the twentieth anniversary of the series, was the third to air live on both networks simultaneously and the
1989 Tiananmen Square protests and massacre
Protests led by students and workers, known in China as the June Fourth Incident, were held in Tiananmen Square in Beijing, China, from 15 April to 4 June 1989. After weeks of unsuccessful attempts between the demonstrators and the Chinese government to find a
Sir Richard Charles Nicholas Branson is an English business magnate who co-founded the Virgin Group in 1970, and, as of 2016, controlled five companies.
The fifth and final season of the American science fiction horror drama television series Stranger Things, marketed as Stranger Things 5, was released on the streaming service Netflix in two volumes and the finale. The first set of four episodes was released o
Sawyer Storm Sweeten was an American child actor. He was best known for his role as Geoffrey Barone on the sitcom Everybody Loves Raymond.
Katherine Elaine Hendrix is an American actress. She gained recognition for appearing in a range of television films in the 1990s before her breakthrough role as Meredith Blake in the romantic comedy film The Parent Trap (1998). On television, Hendrix appeared
Dharmendra was an Indian actor, producer and politician, primarily known for his work in Hindi films. He is regarded as one of the greatest and most commercially successful actors in the history of Indian cinema. Known as the "He-man", he was popular for his h
Robert Clarence Irwin is an Australian conservationist, zookeeper, wildlife photographer, and television presenter. The son of conservationists Steve and Terri Irwin, he is regarded as an influential figure in Australian popular culture. Time magazine named hi
This is a list of lists of deaths of significant people, organized by year. New deaths articles are added to their respective month and then linked below.
Stranger Things is an American television series created by the Duffer Brothers for Netflix. Produced by Monkey Massacre Productions and 21 Laps Entertainment, the first season was released on Netflix on July 15, 2016. The second and third seasons followed in
Bruce Lee was a Hong Kong and American martial artist, actor, and filmmaker. He was the founder of Jeet Kune Do, a hybrid martial arts philosophy, which was formed from his experiences in unarmed fighting and self-defense—as well as eclectic, Zen Buddhist, and
Witney Capri Carson McAllister is an American professional Latin and ballroom dancer and choreographer. She first gained recognition as a contestant on the ninth season of the reality competition series So You Think You Can Dance.
Zootopia 2 is a 2025 American animated buddy cop comedy film produced by Walt Disney Animation Studios, the second film in the series and a sequel to Zootopia (2016). Directed by Jared Bush and Byron Howard and written by Bush, the film stars Ginnifer Goodwin,
Wicked: For Good is a 2025 musical fantasy film directed by Jon M. Chu and written by Winnie Holzman and Dana Fox. The sequel to Wicked (2024), it adapts the second act of the 2003 stage musical by Stephen Schwartz and Holzman, which was loosely based on Grego
Pluribus is an American post-apocalyptic science fiction television series created by Vince Gilligan for Apple TV. Set and filmed primarily in Albuquerque, New Mexico, the series follows novelist Carol Sturka, who finds herself isolated after an alien virus tr
Alix Ashley Earle is an American social media personality who rose to popularity posting "Get Ready With Me" videos on TikTok in which she shares details of her personal life. She is known by online communities for promoting products in a way that rapidly incr
Dancing with the Stars (American TV series)
Dancing with the Stars is an American reality dance competition television series that premiered on ABC on June 1, 2005. It is the American version of the British contest program Strictly Come Dancing and is part of its international franchise. The series pair
Bindi Sue Irwin is an Australian conservationist, zookeeper, actress, and television personality. The daughter of conservationists Steve and Terri Irwin, she is regarded as an influential figure in Australian popular culture. Time magazine named her and her yo
Mark Edward Kelly is an American politician and a retired astronaut and naval officer. He is the senior United States senator from Arizona, a seat he has held since 2020. He is a member of the Democratic Party.
Millie Bonnie Bongiovi, known professionally as Millie Bobby Brown, is a British actress and film producer. She gained international recognition for playing Eleven in the Netflix science fiction series Stranger Things (2016–2025), for which she received nomina
This is a list of Hindi cinema films released in 2025.
Nicholas Dylan Harrison Efron is an American television personality and production coordinator. He is the younger brother of actor Zac Efron.
6-7 was an Internet meme, slang term, and gesture that became popular in 2025 on TikTok and Instagram Reels. It has no fixed meaning.
The Constitution Day, also known as National Law Day, is celebrated in India on 26 November every year to commemorate the adoption of the Constitution of India. On 26 November 1949, the Constituent Assembly of India adopted the Constitution of India, and it ca
Stephen Robert Irwin was an Australian conservationist, environmentalist, zookeeper, television personality, and wildlife educator. Nicknamed the "Crocodile Hunter", he is regarded as an influential figure in Australian popular culture, and as one of the great
Thanksgiving or Thanksgiving Day is a national holiday celebrated on various dates in October and November in the United States, Canada, Saint Lucia, and Liberia. It is also observed in the Australian territory of Norfolk Island. It began as a day of giving th
Imran Ahmed Khan Niazi is a Pakistani former cricketer, philanthropist, and politician who served as the 19th prime minister of Pakistan from August 2018 until April 2022. As a cricketer, he captained the Pakistan national cricket team to victory in the 1992 C
The Family Man (Indian TV series)
The Family Man is an Indian Hindi-language spy thriller streaming television series created by Raj & DK for Amazon Prime Video. It features Manoj Bajpayee as Srikant Tiwari, a middle-class man secretly working as an intelligence officer for the Threat Analysis
Cynthia Erivo is a British actress and singer. Known for her work on both stage and screen, she is the recipient of several accolades and one of few individuals nominated for an Emmy, a Grammy, an Oscar, and a Tony Award (EGOT), winning all but the Oscar. Eriv
What the people building things argued about, from Hacker News.
Papers submitted to arXiv cs.AI that day.
LTD: Low Temperature Distillation for Gradient Masking-free Adversarial Training
Adversarial training is a widely adopted strategy to bolster the robustness of neural network models against adversarial attacks. This paper revisits the fundamental assumptions underlying image classification and suggests that representing data as one-hot labels is a key factor that leads to vulnerabilities. However, in real-world datasets, data ambiguity often arises, with samples exhibiting characteristics of mult
Prototypical part network (ProtoPNet) has drawn wide attention and boosted many follow-up studies due to its self-explanatory property for explainable artificial intelligence (XAI). However, when directly applying ProtoPNet on vision transformer (ViT) backbones, learned prototypes have a "distraction" problem: they have a relatively high probability of being activated by the background and pay less attention
In recent years, deep neural networks have defined the state-of-the-art in semantic segmentation where their predictions are constrained to a predefined set of semantic classes. They are to be deployed in applications such as automated driving, although their categorically confined expressive power runs contrary to such open world scenarios. Thus, the detection and segmentation of objects from outside their predefine
Uncertainty-based Detection of Adversarial Attacks in Semantic Segmentation
State-of-the-art deep neural networks have proven to be highly powerful in a broad range of tasks, including semantic image segmentation. However, these networks are vulnerable against adversarial attacks, i.e., non-perceptible perturbations added to the input image causing incorrect predictions, which is hazardous in safety-critical applications like automated driving. Adversarial examples and defense strategies are
Machine Reading Comprehension using Case-based Reasoning
We present an accurate and interpretable method for answer extraction in machine reading comprehension that is reminiscent of case-based reasoning (CBR) from classical AI. Our method (CBR-MRC) builds upon the hypothesis that contextualized answers to similar questions share semantic similarities with each other. Given a test question, CBR-MRC first retrieves a set of similar cases from a nonparametric memory and then
Semi-supervised Multimodal Representation Learning through a Global Workspace
Recent deep learning models can efficiently combine inputs from different modalities (e.g., images and text) and learn to align their latent representations, or to translate signals from one domain to another (as in image captioning, or text-to-image generation). However, current approaches mainly rely on brute-force supervised training over large multimodal datasets. In contrast, humans (and other animals) can learn
Evaluating Large Language Models for Radiology Natural Language Processing
The rise of large language models (LLMs) has marked a pivotal shift in the field of natural language processing (NLP). LLMs have revolutionized a multitude of domains, and they have made a significant impact in the medical field. Large language models are now more abundant than ever, and many of these models exhibit bilingual capabilities, proficient in both English and Chinese. However, a comprehensive evaluation of
Dual-Balancing for Multi-Task Learning
Multi-task learning aims to learn multiple related tasks simultaneously and has achieved great success in various fields. However, the disparity in loss and gradient scales among tasks often leads to performance compromises, and the balancing of tasks remains a significant challenge. In this paper, we propose Dual-Balancing Multi-Task Learning (DB-MTL) to achieve task balancing from both the loss and gradient perspec
AMLP: Adjustable Masking Lesion Patches for Self-Supervised Medical Image Segmentation
Self-supervised masked image modeling (MIM) methods have shown promising performances on analyzing natural images. However, directly applying such methods to medical image segmentation tasks still cannot achieve satisfactory results. The challenges arise from the facts that (i) medical images are inherently more complex compared to natural images, and the subjects in medical images often exhibit more distinct contour
While federated learning (FL) and differential privacy (DP) have been extensively studied, their application to automatic speech recognition (ASR) remains largely unexplored due to the challenges in training large transformer models. Specifically, large models further exacerbate issues in FL as they are particularly susceptible to gradient heterogeneity across layers, unlike the relatively uniform gradient behavior o
TinyFormer: Efficient Transformer Design and Deployment on Tiny Devices
Developing deep learning models on tiny devices (e.g. Microcontroller units, MCUs) has attracted much attention in various embedded IoT applications. However, it is challenging to efficiently design and deploy recent advanced models (e.g. transformers) on tiny devices due to their severe hardware resource constraints. In this work, we propose TinyFormer, a framework specifically designed to develop and deploy resourc
Bring Your Own KG: Self-Supervised Program Synthesis for Zero-Shot KGQA
We present BYOKG, a universal question-answering (QA) system that can operate on any knowledge graph (KG), requires no human-annotated training data, and can be ready to use within a day -- attributes that are out-of-scope for current KGQA systems. BYOKG draws inspiration from the remarkable ability of humans to comprehend information present in an unseen KG through exploration -- starting at random nodes, inspecting
Factor-Assisted Federated Learning for Personalized Optimization with Heterogeneous Data
Federated learning is an emerging distributed machine learning framework aiming at protecting data privacy. Data heterogeneity is one of the core challenges in federated learning, which could severely degrade the convergence rate and prediction performance of deep neural networks. To address this issue, we develop a novel personalized federated learning framework for heterogeneous data, which we refer to as FedSplit.
Natural Strategic Ability in Stochastic Multi-Agent Systems
Strategies synthesized using formal methods can be complex and often require infinite memory, which does not correspond to the expected behavior when trying to model Multi-Agent Systems (MAS). To capture such behaviors, natural strategies are a recently proposed framework striking a balance between the ability of agents to strategize with memory and the model-checking complexity, but until now has been restricted to
Decentralized Bilevel Optimization: A Perspective from Transient Iteration Complexity
Stochastic bilevel optimization (SBO) is becoming increasingly essential in machine learning due to its versatility in handling nested structures. To address large-scale SBO, decentralized approaches have emerged as effective paradigms in which nodes communicate with immediate neighbors without a central server, thereby improving communication efficiency and enhancing algorithmic robustness. However, most decentraliz
Single- vs. Dual-Policy Reinforcement Learning for Dynamic Bike Rebalancing
Bike-sharing systems (BSS) provide a sustainable urban mobility solution, but ensuring their reliability requires effective rebalancing strategies to address stochastic demand and prevent station imbalances. This paper proposes reinforcement learning (RL) algorithms for dynamic rebalancing problem with multiple vehicles, introducing and comparing two RL approaches: Single-policy RL and Dual-policy RL. We formulate th
Federated Learning: A Stochastic Approximation Approach
This paper considers the Federated learning (FL) in a stochastic approximation (SA) framework. Here, each client $i$ trains a local model using its dataset $\mathcal{D}^{(i)}$ and periodically transmits the model parameters $w^{(i)}_n$ to a central server, where they are aggregated into a global model parameter $\bar{w}_n$ and sent back. The clients continue their training by re-initializing their local models with t
A Simple Framework Towards Vision-based Traffic Signal Control with Microscopic Simulation
Traffic signal control (TSC) is crucial for reducing traffic congestion leading to smoother traffic flow, reduced idle time, and mitigated CO2 emissions. In this paper, we explore the computer vision approach for TSC that modulates on-road traffic flows through visual observation. Unlike traditional feature-based approaches, vision-based methods depend much less on heuristics and predefined features, bringing promisi
Activator: GLU Activation Function as the Core Component of a Vision Transformer
The transformer architecture has driven many successes in a variety of tasks within the field of deep learning, in particular the recent advances in natural language processing (NLP) culminating with large language models (LLM). Adding to that success, transformer architecture has found widespread interest from computer vision (CV) researchers and practitioners, allowing for many advancements in vision-related tasks
Data Valuation by Fusing Global and Local Statistical Information
Data valuation has garnered increasing attention in recent years, given the critical role of high-quality data in various applications. Among diverse data valuation approaches, Shapley value-based methods are predominant due to their strong theoretical grounding. However, the exact computation of Shapley values is often computationally prohibitive, prompting the development of numerous approximation techniques. Despi
Safety Control of Service Robots with LLMs and Embodied Knowledge Graphs
Safety limitations in service robotics across various industries have raised significant concerns about the need for robust mechanisms ensuring that robots adhere to safe practices, thereby preventing actions that might harm humans or cause property damage. Despite advances, including the integration of Knowledge Graphs (KGs) with Large Language Models (LLMs), challenges in ensuring consistent safety in autonomous ro
CTSyn: A Foundation Model for Cross Tabular Data Generation
Generative Foundation Models (GFMs) have achieved remarkable success in producing high-quality synthetic data for images and text. However, their application to tabular data presents significant challenges due to the heterogeneous nature of table features. Current cross-table learning frameworks struggle because they lack a generative model backbone and an effective mechanism to decode heterogeneous feature values. T
Gram2Vec: An Interpretable Document Vectorizer
We present Gram2Vec, a grammatical style embedding system that embeds documents into a higher dimensional space by extracting the normalized relative frequencies of grammatical features present in the text. Compared to neural approaches, Gram2Vec offers inherent interpretability based on how the feature vectors are generated. In this paper, we use authorship verification and AI detection as two applications to show h
A Catalyst Framework for the Quantum Linear System Problem via the Proximal Point Algorithm
Solving systems of linear equations is a fundamental problem, but it can be computationally intensive for classical algorithms in high dimensions. Existing quantum algorithms can achieve exponential speedups for the quantum linear system problem (QLSP) in terms of the problem dimension, but the advantage is bottlenecked by condition number of the coefficient matrix. In this work, we propose a new quantum algorithm fo
Data-Driven Lipschitz Continuity: A Cost-Effective Approach to Improve Adversarial Robustness
As deep neural networks (DNNs) are increasingly deployed in sensitive applications, ensuring their security and robustness has become critical. A major threat to DNNs arises from adversarial attacks, where small input perturbations can lead to incorrect predictions. Recent advances in adversarial training improve robustness by incorporating additional examples from external datasets or generative models. However, the
Notable events recorded on this day and month across all years.