Record 01062026 · captured 2026-08-25
The world looked up Victor Wembanyama. 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.
Victor Wembanyama, nicknamed "Wemby" and "the Alien", is a French professional basketball player for the San Antonio Spurs of the National Basketball Association (NBA). He was selected first overall by the Spurs in the 2023 NBA draft and is considered one of t
Backrooms is a 2026 American science fiction psychological horror film directed and co-scored by Kane Parsons, and written by Will Soodik. It is based on Parsons's web series which was inspired by the "Backrooms" creepypasta. In the film, Clark, a furniture st
Clash in Italy was a 2026 professional wrestling pay-per-view (PPV) and livestreaming event produced by the American company WWE. The event took place on Sunday, May 31, 2026, at the Inalpi Arena in Turin, Italy, and was held for wrestlers from the promotion's
Obsession is a 2025 American supernatural horror film written, directed, and edited by Curry Barker. The film follows Bear, a music store employee who buys a supernatural toy that grants his wish for his friend Nikki to fall in love with him, which makes her b
Mitchell Chase Johnson is an American professional basketball coach and former player who is the head coach for the San Antonio Spurs of the National Basketball Association (NBA). He replaced Gregg Popovich, who stepped down after 29 seasons. He previously ser
Callum Robilliard Turner is a British actor. After working as a fashion model, he began working in film and television. He had lead roles in the drama film Queen and Country (2014) and the mystery drama series Glue (2014), and played Theseus, the brother of Ne
Kelly Lee Curtis was an American actress. She was known for her roles in Magic Sticks (1987) and The Devil's Daughter (1991).
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
Spider-Noir is an American superhero series developed by Oren Uziel for MGM+ and Prime Video. Based on Marvel Comics featuring the character Spider-Man Noir, the series follows an aging private investigator and superhero in 1930s New York City who grapples wit
Blast is a 2026 Indian Tamil-language action thriller film directed by Subash K. Raj in his debut and produced by AGS Entertainment. The film stars Arjun Sarja, Abhirami and Preity Mukhundhan, with John Kokken, Vivek Prasanna, Arjun Chidambaram, Dileepan and P
Dua Lipa is an English singer and songwriter. Her accolades include seven Brit Awards and three Grammy Awards.
The following notable deaths occurred in 2026. Names are reported under the date of death, in alphabetical order. A typical entry reports information in the following sequence:Name, age, country of citizenship at birth, subsequent nationality, what subject was
The Backrooms is a fictional location invented in a 2019 thread on the imageboard website 4chan. The Backrooms are usually portrayed as an impossibly large extradimensional complex of empty rooms, accessed by exiting reality. They are one of the best-known exa
Dylan Robert Harper is an American professional basketball player for the San Antonio Spurs of the National Basketball Association (NBA). He played college basketball for the Rutgers Scarlet Knights, and was drafted second overall in the 2025 NBA draft by the
Luis Enrique Martínez García is a Spanish football manager and former player who is currently the head coach of Ligue 1 club Paris Saint-Germain.
List of European Cup and UEFA Champions League finals
The UEFA Champions League is a seasonal football competition established in 1955. Prior to the 1992–93 season, the tournament was named the European Cup. The UEFA Champions League is open to the league champions of all UEFA member associations, as well as to t
Vaibhav Sooryavanshi, also spelled Vaibhav Suryavanshi, is an Indian cricketer. He is a left-handed top order batter and an occasional slow left-arm orthodox bowler. He made his international debut for the Indian cricket team in the T20I series against England
Beaufort or Belfort Castle, known locally as Qal'at al-Shaqif or Shaqif Arnun, is a Crusader fortress in Nabatieh Governorate, Southern Lebanon, about 1 kilometre (0.62 mi) to the south-south-east of the village of Arnoun. There was a fortification on the site
List of Indian Premier League seasons and results
The Indian Premier League (IPL) is a domestic, annual Twenty20 cricket tournament played in India since 2008. It is organized by the IPL Governing Council, under the aegis of the Board of Control for Cricket in India (BCCI). It is the most watched Twenty20 tou
Rajat Manohar Patidar is an Indian international cricketer. He is a right-handed top order batter and an off-spin bowler. He made his international debut against South Africa in December 2023. Patidar plays for Madhya Pradesh in domestic cricket and captains t
Andrea Schöpp is a German curler from Garmisch-Partenkirchen. She lectures part-time in statistics at LMU Munich.
The UEFA Champions League, commonly known as the Champions League, is an annual club association football competition organised by the Union of European Football Associations (UEFA) that is contested by top-division European clubs. The competition begins with
The San Antonio Spurs are an American professional basketball team based in San Antonio. The Spurs compete in the National Basketball Association (NBA) as a member of the Southwest Division of the Western Conference. The team plays its home games at Frost Bank
Paris Saint-Germain Football Club, commonly referred to as Paris Saint-Germain, PSG, Paris, or Paris SG, is a French professional football club based in Paris. Founded in 1970 through the merger of Paris FC and Stade Saint-Germain, the club competes in Ligue 1
Julian Kymani Champagnie is an American professional basketball player for the San Antonio Spurs of the National Basketball Association (NBA). He played college basketball for the St. John's Red Storm, where he was a two-time first-team All-Big East selection
Star Wars: The Mandalorian and Grogu is a 2026 American science fiction film directed by Jon Favreau, who co-wrote the film with Dave Filoni and Noah Kloor. Produced by Lucasfilm and Fairview Entertainment, and distributed by Walt Disney Studios Motion Picture
Andoni Iraola Sagarna is a Spanish professional football manager and former player who is the head coach of Premier League club Liverpool.
Michael Joseph Jackson was an American singer, songwriter, dancer, and philanthropist. Dubbed the "King of Pop", he is widely regarded as one of the most culturally significant figures of the 20th century. His musical achievements broke American racial barrier
Shaivonte Aician Gilgeous-Alexander, also known by his initials SGA, is a Canadian professional basketball player for the Oklahoma City Thunder of the National Basketball Association (NBA). He is a four-time NBA All-Star, a four-time All-NBA First Team member,
Jean Obeid was a Lebanese lawyer, journalist and politician, who served in different cabinet posts, the last of which was foreign minister of Lebanon from 2003 to 2004.
What the people building things argued about, from Hacker News.
Papers submitted to arXiv cs.AI that day.
On the regularization of Wasserstein GANs
Since their invention, generative adversarial networks (GANs) have become a popular approach for learning to model a distribution of real (unlabeled) data. Convergence problems during training are overcome by Wasserstein GANs which minimize the distance between the model and the empirical distribution in terms of a different metric, but thereby introduce a Lipschitz constraint into the optimization problem. A simple
Advances and Challenges in Meta-Learning: A Technical Review
Meta-learning empowers learning systems with the ability to acquire knowledge from multiple tasks, enabling faster adaptation and generalization to new tasks. This review provides a comprehensive technical overview of meta-learning, emphasizing its importance in real-world applications where data may be scarce or expensive to obtain. The paper covers the state-of-the-art meta-learning approaches and explores the rela
SDF2Net: Shallow to Deep Feature Fusion Network for PolSAR Image Classification
Polarimetric synthetic aperture radar (PolSAR) images encompass valuable information that can facilitate extensive land cover interpretation and generate diverse output products. Extracting meaningful features from PolSAR data poses challenges distinct from those encountered in optical imagery. Deep learning (DL) methods offer effective solutions for overcoming these challenges in PolSAR feature extraction. Convoluti
Graph Machine Learning in the Era of Large Language Models (LLMs)
Graphs play an important role in representing complex relationships in various domains like social networks, knowledge graphs, and molecular discovery. With the advent of deep learning, Graph Neural Networks (GNNs) have emerged as a cornerstone in Graph Machine Learning (Graph ML), facilitating the representation and processing of graphs. Recently, LLMs have demonstrated unprecedented capabilities in language tasks a
We introduce Hyper-Trees as a novel framework for modeling time series data using gradient boosted trees. Unlike conventional tree-based approaches that forecast time series directly, Hyper-Trees learn the parameters of a target time series model, such as ARIMA or Exponential Smoothing, as functions of features. These parameters are then used by the target model to generate the final forecasts. Our framework combines
Goldfish: Monolingual Language Models for 350 Languages
For many low-resource languages, the only available language models are large multilingual models trained on many languages simultaneously. Despite state-of-the-art performance on reasoning tasks, we find that these models still struggle with basic grammatical text generation in many languages. First, large multilingual models perform worse than bigrams for many languages (e.g. 24% of languages in XGLM 4.5B; 43% in B
LLM Bias Evaluation: Gender, Racial, and Age Disparities in Occupational and Crime Scenarios
LLM bias evaluation is critical as large language models (LLMs) increasingly influence high-stakes decisions. This paper provides a comprehensive assessment of gender, racial, and age disparities in leading LLMs, revealing that debiasing efforts often create new fairness trade-offs. Recent advancements in LLMs have been notable, yet widespread enterprise adoption remains limited due to various constraints. This paper
Scalable Mechanistic Neural Networks for Differential Equations and Machine Learning
We propose Scalable Mechanistic Neural Network (S-MNN), an enhanced neural network framework designed for scientific machine learning applications involving long temporal sequences. By reformulating the original Mechanistic Neural Network (MNN) (Pervez et al., 2024), we reduce the computational time and space complexities from cubic and quadratic with respect to the sequence length, respectively, to linear. This sign
Multimodal Fusion via Self-Consistent Task-Gradient Fields
Multimodal learning aims to preserve as much task-related information as possible from different inputs. However, current fusion designs often distort the feedback loop to feature extractors. Aggressively merging modalities entangles their representations, making the feature extractors fragile to incomplete inputs. Meanwhile, attempting to separate features via auxiliary losses frequently introduces optimization conf
Learning Coupled Subspaces for Multi-Condition Spike Data
In neuroscience, numerous studies conduct sensory or behavioral experiments under multiple conditions to acquire neural responses in the form of high-dimensional spike train datasets. Analyzing high-dimensional spike data is a challenging statistical problem. To this end, Gaussian process factor analysis (GPFA), a popular class of latent variable models, has been proposed for data collected under a single experimenta
Minibatch Optimal Transport and Perplexity Bound Estimation in Discrete Flow Matching
Discrete flow matching, a recent framework for modeling categorical data, has shown competitive performance with autoregressive models. However, unlike continuous flow matching, the rectification strategy cannot be applied due to the stochasticity of discrete paths, necessitating alternative methods to minimize state transitions. We propose a dynamic-optimal-transport-like minimization objective and derive its Kantor
Modern recommender systems often create information cocoons, restricting users' exposure to diverse content. The central challenge is to balance content exploration and exploitation while allowing users to adjust their recommendation preferences. Ideally, this balance can be captured with a hierarchical representation, where depth search facilitates exploitation and breadth search enables exploration. However, ex
Understanding the Fundamental Design Decisions of Retrieval-Augmented Generation Systems
Retrieval-Augmented Generation (RAG) has emerged as a critical technique for enhancing large language model (LLM) capabilities. However, practitioners face significant challenges when making RAG deployment decisions. While existing research prioritizes algorithmic innovations, a systematic gap persists in understanding fundamental engineering trade-offs that determine RAG success. We present the first comprehensive s
Safeguarding Text-to-Image Generation via Inference-Time Prompt-Noise Optimization
Text-to-Image (T2I) diffusion models are widely recognized for their ability to generate high-quality and diverse images based on text prompts. However, despite recent advances, these models are still prone to generating unsafe images containing sensitive or inappropriate content, which can be harmful to users. Current efforts to prevent inappropriate image generation for diffusion models are easy to bypass and vulne
Cross-Modal Attention Calibration for LVLM Hallucination Mitigation
Large vision-language models (LVLMs) have shown remarkable capabilities in visual-language understanding. Despite their success, LVLMs still suffer from generating hallucinations in complex generation tasks, leading to inconsistencies between visual inputs and generated content. To address this issue, some approaches have introduced inference-time interventions, such as contrastive decoding, to reduce overreliance on
The web-scale of pretraining data has created an important evaluation challenge: to disentangle linguistic competence on cases well-represented in pretraining data from generalization to out-of-domain language, specifically the dynamic, real-world instances less common in pretraining data. To this end, we construct a diagnostic evaluation to systematically assess natural language understanding in LLMs by leveraging C
Face recognition systems (FRS) exhibit significant accuracy differences based on the user's gender. Since such a gender gap reduces the trustworthiness of FRS, more recent efforts have tried to find the causes. However, these studies make use of manually selected, correlated, and small-sized sets of facial features to support their claims. In this work, we analyze gender bias in face recognition by successfully e
Learning General Causal Structures with Hidden Dynamic Process for Climate Analysis
Understanding climate dynamics requires going beyond correlations in observational data to uncover the underlying causal process. Latent drivers such as atmospheric processes play a central role in temporal dynamics, while direct causal influences also exist among geographically proximate observed variables. Traditional Causal Representation Learning (CRL) typically focuses on latent factors but overlooks such observ
Unifying and Optimizing Data Values for Selection via Sequential Decision-Making
Data selection has emerged as a crucial downstream application of data valuation, yet the theoretical foundations for using data values in selection remain underexplored. We reformulate data selection as a sequential decision-making problem where the optimal selection sequence arises from dynamic programming, and data values can be understood as encodings of this optimal sequence. This framework unifies and reinterpr
ProofWala: A Framework for Multilingual Proof Data Synthesis and Theorem-Proving
Neural approaches to theorem proving require robust infrastructure for interfacing with interactive theorem provers (ITPs), extracting structured proof data, and executing proof search at scale. However, existing tooling is often assistant-specific and oriented toward file-level execution, making repository-scale analysis and parallel experimentation challenging. We present ProofWala, a multilingual proof engineering
PRISM: Self-Pruning Intrinsic Selection Method for Training-Free Multimodal Data Selection
Visual instruction tuning adapts pre-trained Multimodal Large Language Models (MLLMs) to follow human instructions for real-world applications. However, the rapid growth of these datasets introduces significant redundancy, leading to increased computational costs. Existing methods for selecting instruction data aim to prune this redundancy, but predominantly rely on computationally demanding techniques such as proxy-
MeMo: Towards Language Models with Associative Memory Mechanisms
Memorization is a fundamental ability of Transformer-based Large Language Models, achieved through learning. In this paper, we propose a paradigm shift by designing an architecture to memorize text directly, bearing in mind the principle that memorization precedes learning. We introduce MeMo, a novel architecture for language modeling that explicitly memorizes sequences of tokens in layered associative memories. By d
Auto-Discovery-Bench: Diagnosing Structured State Tracking in Oracle-Guided Discovery
Interactive discovery requires agents to maintain and update structured beliefs over many rounds of feedback. Before evaluating agents in noisy, open-ended scientific environments, it is useful to isolate this prerequisite capability under controlled conditions. We introduce Auto-Discovery-Bench, a deterministic oracle-guided diagnostic benchmark in which agents recover hidden structures through repeated hypothesis--
Large Language Models (LLMs) have achieved impressive progress across a wide range of tasks, yet their heavy reliance on English-centric training data leads to significant performance degradation in non-English languages. While existing multilingual prompting methods emphasize reformulating queries into English or enhancing reasoning capabilities, they often fail to incorporate the language- and culture-specific grou
How does Bayesian Sampling help Membership Inference Attacks?
Membership Inference Attacks (MIAs) aim to estimate whether a specific data point was used in the training of a given model. Existing state-of-the-art attacks typically rely on training multiple reference models to approximate the conditional score distribution for individual data points, which leads to significant computational overhead and limits their practical applicability. In this work, we propose a novel appro
Notable events recorded on this day and month across all years.