Record 21072026 · captured 2026-08-25
The world looked up Lamine Yamal. 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.
Lamine Yamal Nasraoui Ebana, commonly known as Lamine Yamal, is a Spanish professional footballer who plays as a right winger for the La Liga club Barcelona and the Spain national team. He is widely regarded as one of the best players in the world.
The Odyssey is a 2026 epic action fantasy film written and directed by Christopher Nolan, who produced it with his wife Emma Thomas. An adaptation of Homer's ancient Greek epic poem the Odyssey, it stars an ensemble cast including Matt Damon, Tom Holland, Anne
Andrew Murray Burnham is a British politician who has served as Prime Minister of the United Kingdom and Leader of the Labour Party since July 2026. He has been Member of Parliament (MP) for Makerfield in Greater Manchester since June 2026, and was Mayor of Gr
The 2026 FIFA World Cup was the 23rd FIFA World Cup, the quadrennial international men's soccer championship contested by the national teams of the member associations of FIFA. The tournament began on June 11, 2026, and concluded on July 19 with Spain winning
Joseph Kevin Keegan was an English football player and manager who played as an attacking midfielder or forward. Nicknamed "King Kev" or "Mighty Mouse", Keegan was recognised for his dribbling ability, finishing and presence in the air, as much as he was for h
Lionel Andrés "Leo" Messi is an Argentine professional footballer who plays as a forward for and captains both Major League Soccer (MLS) club Inter Miami and the Argentina national team. Widely regarded as one of the greatest players in history, Messi has set
Leandro Daniel Paredes is an Argentine professional footballer who plays as a defensive midfielder for Argentine Primera División club Boca Juniors and the Argentina national team. He previously played for Roma, Zenit Saint Petersburg and Paris Saint-Germain,
Ferran Torres García is a Spanish professional footballer who plays as a forward or winger for Ligue 1 club Paris Saint-Germain and the Spain national team.
Rodrigo Hernández Cascante, known simply as Rodri or Rodrigo, is a Spanish professional footballer who plays as a defensive midfielder for La Liga club Barcelona and captains the Spain national team. Widely regarded as one of the best midfielders in the world,
The FIFA World Cup is an international association football competition among the senior men's national teams of the members of the Fédération Internationale de Football Association (FIFA), the sport's global governing body. The tournament has been held every
Shakira Isabel Mebarak Ripoll, known mononymously as Shakira, is a Colombian singer-songwriter, dancer, and record producer. Referred to as the "Queen of Latin Music", she has had a significant impact on the musical landscape of Latin America and has been cred
The FIFA World Cup is an international association football competition contested by the senior men's national teams of the Fédération Internationale de Football Association (FIFA), the sport's global governing body. The championship has been awarded every fou
The Spain national football team have represented Spain in men's international football competition since 1920, and are governed by the Royal Spanish Football Federation. They are the reigning World and European champions, having won the most recent FIFA World
Marie-France van Heel is a marketing executive. She is married to Andy Burnham, the prime minister of the United Kingdom and the leader of the Labour Party.
The Odyssey is one of two major epics of ancient Greek literature attributed to Homer. It is one of the oldest surviving works of literature and remains popular with modern audiences. Like the Iliad, the Odyssey is divided into 24 books. It follows the heroic
The 2030 FIFA World Cup is scheduled to be the 24th FIFA World Cup, the quadrennial international football tournament that is contested by the men's national teams of the member associations of FIFA. The tournament is planned to be jointly hosted by Morocco, P
John Healey is a British politician who has served as Chancellor of the Exchequer under Andy Burnham since 20 July 2026. He previously served as Secretary of State for Defence under Keir Starmer from 2024 to 2026. A member of the Labour Party, he has been the
Pau Cubarsí Paredes is a Spanish professional footballer who plays as a centre-back for La Liga club Barcelona and the Spain national team. He is considered one of the best young defenders in the world.
Nicholas Williams Arthuer is a Spanish professional footballer who plays as a winger for La Liga club Athletic Bilbao and the Spain national team. He is recognised for his speed and dribbling skills.
Enzo Jeremías Fernández is an Argentine professional footballer who plays as a midfielder for Premier League club Chelsea and the Argentina national team.
Gerard Piqué Bernabeu is a Spanish former professional footballer who played as a centre-back. He is considered to be one of the greatest defenders of his generation and is one of the most decorated players with 37 trophies. In 2022, he founded the Kings Leagu
Marc Cucurella Saseta is a Spanish professional footballer who plays as a left-back or left wing-back for La Liga club Real Madrid and the Spain national team. He is considered to be one of the best left-backs in the world.
The final match of the 2026 FIFA World Cup—the 23rd edition of the FIFA competition for men's national soccer teams—was played at MetLife Stadium in East Rutherford, New Jersey, part of the New York metropolitan area, on July 19, 2026. It was contested by Spai
In mathematics, the Jacobian conjecture is a conjecture concerning polynomials in several variables that states that if a polynomial function from an -dimensional space to itself has a Jacobian determinant that is a non-zero constant, then the function has a p
Avengers: Doomsday is an upcoming American superhero film based on the Marvel Comics superhero team the Avengers. Produced by Marvel Studios and distributed by Walt Disney Studios Motion Pictures, it is intended to be the sequel to Avengers: Endgame (2019) and
Luis de la Fuente (footballer, born 1961)
Luis de la Fuente Castillo is a Spanish professional football manager and former player who played as a left-back. He is the manager of the Spain national team.
Cristiano Ronaldo dos Santos Aveiro is a Portuguese professional footballer who plays as a forward for and captains the Saudi Pro League club Al-Nassr and the Portugal national team. Nicknamed CR7, he is widely regarded as one of the greatest players in histor
Kylian Mbappé Lottin is a French professional footballer who plays as a forward for La Liga club Real Madrid and captains the France national team. Widely regarded as one of the best players in the world and one of the greatest French players of all time, he i
Sir Christopher Edward Nolan is a British and American filmmaker. Known for his Hollywood blockbusters with complex storytelling, Nolan is considered a leading filmmaker of the 21st century. His films have earned over $7.7 billion worldwide, making him the thi
At the end of each FIFA World Cup final tournament, several awards are presented to the players and teams who have distinguished themselves in various aspects of the game.
What the people building things argued about, from Hacker News.
Papers submitted to arXiv cs.AI that day.
Ghosts in Neural Networks: Existence, Structure and Role of Infinite-Dimensional Null Space
We study parameter nonuniqueness in continuous-width depth-two fully connected neural networks. Our main contribution is a direct method for solving the neural-network equation $S[γ]=f$. Starting from the Fourier expression of the synthesis operator, separation of variables produces a ridgelet particular solution and identifies every homogeneous direction. To isolate the argument, we first prove an abstract reconstru
Automated Reinforcement Learning: An Overview
Reinforcement Learning and, recently, Deep Reinforcement Learning are popular methods for solving sequential decision-making problems modeled as Markov Decision Processes. RL modeling of a problem and selecting algorithms and hyper-parameters require careful consideration, as different configurations may entail completely different performances. These considerations are mainly the task of RL experts; however, RL is p
We study a general matrix optimization problem with a fixed-rank positive semidefinite (PSD) constraint. We perform the Burer-Monteiro factorization and consider a particular Riemannian quotient geometry in a search space that has a total space equipped with the Euclidean metric. When the original objective f satisfies standard restricted strong convexity and smoothness properties, we characterize the global landscap
Fourier-Mixed Window Attention: Accelerating Informer for Long Sequence Time-Series Forecasting
We study a fast local-global window-based attention method to accelerate Informer for long sequence time-series forecasting. While window attention being local is a considerable computational saving, it lacks the ability to capture global token information which is compensated by a subsequent Fourier transform block. Our method, named FWin, does not rely on query sparsity hypothesis and an empirical approximation und
Gradient-Free Privacy Leakage in Federated Language Models through Selective Weight Tampering
Federated learning (FL) has become a key component in various language modeling applications such as machine translation, next-word prediction, and medical record analysis. These applications are trained on datasets from many FL participants that often include privacy-sensitive data, such as healthcare records, phone/credit card numbers, login credentials, etc. Although FL enables computation without necessitating cl
We introduce a new approach using computer vision to predict the land surface displacement from subsurface geometry images for Carbon Capture and Sequestration (CCS). CCS has been proved to be a key component for a carbon neutral society. However, scientists see there are challenges along the way including the high computational cost due to the large model scale and limitations to generalize a pre-trained model with
Prompt-Guided Foundation Model Tuning for Pathology Image Classification
Foundation models have become pivotal in advancing computational pathology, particularly for whole slide image (WSI) classification. However, prevailing methodologies often rely on frozen, pre-trained models for feature extraction, overlooking the pronounced domain shift and task discrepancy between the pre-training and downstream tasks. To address this challenge, we propose PAMT, a novel Prompt-guided Adaptive Model
Octopus: On-device language model for function calling of software APIs
In the rapidly evolving domain of artificial intelligence, Large Language Models (LLMs) play a crucial role due to their advanced text processing and generation abilities. This study introduces a new strategy aimed at harnessing on-device LLMs in invoking software APIs. We meticulously compile a dataset derived from software API documentation and apply fine-tuning to LLMs with capacities of 2B, 3B and 7B parameters,
Octopus v2: On-device language model for super agent
Language models have shown effectiveness in a variety of software applications, particularly in tasks related to automatic workflow. These models possess the crucial ability to call functions, which is essential in creating AI agents. Despite the high performance of large-scale language models in cloud environments, they are often associated with concerns over privacy and cost. Current on-device models for function c
Octopus v3: Technical Report for On-device Sub-billion Multimodal AI Agent
A multimodal AI agent is characterized by its ability to process and learn from various types of data, including natural language, visual, and audio inputs, to inform its actions. Despite advancements in large language models that incorporate visual data, such as GPT-4V, effectively translating image-based data into actionable outcomes for AI agents continues to be challenging. In this paper, we introduce a multimoda
Octopus v4: Graph of language models
Language models have been effective in a wide range of applications, yet the most sophisticated models are often proprietary. For example, GPT-4 by OpenAI and various models by Anthropic are expensive and consume substantial energy. In contrast, the open-source community has produced competitive models, like Llama3. Furthermore, niche-specific smaller language models, such as those tailored for legal, medical or fina
Unsupervised Multimodal Clustering for Semantics Discovery in Multimodal Utterances
Discovering the semantics of multimodal utterances is essential for understanding human language and enhancing human-machine interactions. Existing methods manifest limitations in leveraging nonverbal information for discerning complex semantics in unsupervised scenarios. This paper introduces a novel unsupervised multimodal clustering method (UMC), making a pioneering contribution to this field. UMC introduces a uni
Posts of Peril: Detecting Information About Hazards in Text
Socio-linguistic indicators of affectively-relevant phenomena, such as emotion or sentiment, are often extracted from text to better understand features of human-computer interactions, including on social media. However, an indicator that is often overlooked is the presence or absence of information concerning harms or hazards. Detecting such indicators in text is important because substantial research demonstrates t
Octo-planner: On-device Language Model for Planner-Action Agents
AI agents have become increasingly significant in various domains, enabling autonomous decision-making and problem-solving. To function effectively, these agents require a planning process that determines the best course of action and then executes the planned actions. In this paper, we present an efficient on-device Planner-Action framework that separates planning and action execution into two distinct components: a
Numerous existing studies have examined the performance of Sample Average Approximation (SAA) in the fundamental newsvendor problem. Despite these advances, critical gaps remain in two aspects. First, existing works focus on the linear-cost newsvendor problem and heavily rely on the quantile expression of the optimal solution. As a result, their analytical methods limit generalizability to more general inventory prob
Fairness-Aware Multi-Group Target Detection in Online Discussion
Target-group detection is the task of detecting which group(s) a piece of content is ``directed at or about''. Applications include targeted marketing, content recommendation, and group-specific content assessment. Key challenges include: 1) that a single post may target multiple groups; and 2) ensuring consistent detection accuracy across groups for fairness. In this work, we investigate fairness implication
PriPHiT: Privacy-Preserving Hierarchical Training of Deep Neural Networks
The training phase of deep neural networks requires substantial resources and as such is often performed on cloud servers. However, this raises privacy concerns when the training dataset contains sensitive content, e.g., facial or medical images. In this work, we propose a method to perform the training phase of a deep learning model on both an edge device and a cloud server that prevents sensitive content being tran
Heterogeneous system configurations of distributed clients connected to the central server (CS) via a time-varying wireless network pose significant challenges for popular distributed machine learning (ML) algorithms such as federated learning (FL). Although the limited (radio and computational) resources are widely acknowledged, two critical yet often ignored aspects are (a) client devices can only dedicate a small
PMSN: A Parallel Multi-compartment Spiking Neuron for Multi-scale Temporal Processing
Spiking Neural Networks (SNNs) hold great potential to realize brain-inspired, energy-efficient computational systems. However, current SNNs still fall short in terms of multiscale temporal processing compared to their biological counterparts. This limitation has resulted in poor performance in many pattern recognition tasks with information that varies across different timescales. To address this issue, we put forwa
Squid: Long Context as a New Modality for Energy-Efficient On-Device Language Models
This paper presents Dolphin, a novel decoder-decoder architecture for energy-efficient processing of long contexts in language models. Our approach addresses the significant energy consumption and latency challenges inherent in on-device models. Dolphin employs a compact 0.5B parameter decoder to distill extensive contextual information into a memory embedding, substantially reducing the input length for the primary
Bundle Adjustment in the Eager Mode
Bundle adjustment (BA) is a critical technique in various robotic applications such as simultaneous localization and mapping (SLAM), augmented reality (AR), and photogrammetry. BA optimizes parameters such as camera poses and 3D landmarks to align them with observations. With the growing importance of deep learning in perception systems, there is an increasing need to integrate BA with deep learning frameworks for en
Gradient Span Algorithms Make Predictable Progress in High Dimension
We prove that all 'gradient span algorithms' have asymptotically deterministic behavior on scaled Gaussian random functions as the dimension tends to infinity. This is a functional generalization of similar results for random quadratic functions and spin glasses. They explain the counterintuitive phenomenon that different training runs of many large machine learning models result in approximately equal cost c
This research presents an online path planner for Unmanned Aerial Vehicles (UAVs) that can handle dynamic obstacles and UAV motion constraints, including maximum curvature and desired orientations. Our proposed planner uses a NURBS path representation and a Differential Evolution algorithm, incorporating concepts from the Velocity Obstacle approach in a constraint function. Initial results show that our approach is f
Accurate forecasts of distributed solar generation are necessary to maintain grid stability amid the increased uptake of distributed solar photovoltaic (PV) systems. However, the high variability of solar generation over short time intervals (seconds to minutes) caused by cloud movement makes this forecasting task difficult. To address this, using cloud images, which capture the second-to-second changes in cloud cove
A Benchmark of Generative Methods for Zero-Shot Environmental Sound Classification
Zero-shot learning enables models to generalise to unseen classes using semantic information, bridging the gap between training classes and previously unseen test classes. While widely studied in computer vision, its application to environmental audio remains underexplored, and generative approaches have received little attention. This work presents the first benchmark of generative methods for zero-shot environmenta
Notable events recorded on this day and month across all years.