Record 09062026 · captured 2026-08-25
The world looked up Obsession (2025 film). 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.
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
2026 Peruvian general election
General elections were held in Peru from 12 to 13 April 2026 to elect the president, vice presidents, and the Congress of the Republic of Peru. As no presidential candidate achieved a majority of votes in the first round, a runoff election was held on 7 June.
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
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
Alexander "Sascha" Zverev is a German professional tennis player. He has a career-high singles ranking of world No. 2 by the ATP achieved in June 2022. Zverev has won 25 ATP Tour singles titles, including the 2026 French Open, a gold medal at the 2020 Tokyo Ol
Masters of the Universe (2026 film)
Masters of the Universe is a 2026 American sword-and-sorcery film based on the media franchise by Mattel. It is the second live-action film adaptation, the 1987 film was the first. It was directed by Travis Knight and written by Chris Butler, Aaron Nee, Adam N
Christian Dannemann Eriksen is a Danish professional footballer who plays as a midfielder for 2. Bundesliga club VfL Wolfsburg and the Denmark national team.
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
Peddi is a 2026 Indian Telugu-language sports action drama film written and directed by Buchi Babu Sana. Produced by Venkata Satish Kilaru under Vriddhi Cinemas and co-produced by Ishan Saksena under IVY Entertainment and presented by Mythri Movie Makers and S
The 79th Tony Awards were held on June 7, 2026, to recognize excellence in Broadway productions during the 2025–26 season. The ceremony took place at Radio City Music Hall in New York City, and was broadcast on CBS and streamed on Paramount+.
Rachel Jane Nickell was a British woman who was stabbed to death on Wimbledon Common in southwest London on 15 July 1992. The initial police investigation of the crime resulted in the arrest in controversial circumstances of an innocent man, who was acquitted.
Spencer William Pratt is an American reality television personality. In 2007, he began dating Heidi Montag, a primary cast member of the reality television series The Hills and came to prominence after being cast in the series. A feud between them and Montag's
Scary Movie is a 2026 American parody film directed by Michael Tiddes and written by Marlon Wayans, Shawn Wayans, Keenen Ivory Wayans, Craig Wayans, and Rick Alvarez. It is the sixth installment in the Scary Movie film series and has been referred to as the sp
Ronald Stacey King was an American professional basketball player and sports announcer. He played as a center in the National Basketball Association (NBA) and won three consecutive championships with the Chicago Bulls in 1991, 1992, and 1993. He played college
Danielle Fabiola "Inde" Navarrette is an American actress and former online streamer. She began her acting career as a teenager with roles in short films, before landing roles in the Netflix drama series 13 Reasons Why (2020) and The CW's superhero drama serie
The Ford Creek Patrol Cabin in Glacier National Park was built in 1928. The National Park Service Rustic log structure was a significant resource both architecturally and historically as a network of shelters, approx. one day's travel apart, for patrolling bac
Nelly Korda is an American professional golfer who plays on the LPGA Tour. She is a four-time major winner, claiming victories at the 2021 Women's PGA Championship, the 2024 and 2026 Chevron Championships and the 2026 U.S. Women's Open. In total, she has won 2
Nithya V. Raman is an American urban planner, activist, and politician serving as the Los Angeles city councilmember for the 4th district since 2020. Raman, a member of the Democratic Party and the Democratic Socialists of America, defeated incumbent councilme
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
2026 Armenian parliamentary election
Parliamentary elections were held in Armenia on 7 June 2026 to elect members of the 9th convocation of the National Assembly. According to exit polls, incumbent Prime Minister Nikol Pashinyan's party Civil Contract won with 56.7% of the vote, followed by the p
Jalen Marquis Brunson, nicknamed "Captain Clutch", and the "King of New York" is an American professional basketball player for the New York Knicks of the National Basketball Association (NBA). The son of former NBA guard Rick Brunson, he played college basket
Béla Pap de Szill was a Hungarian military officer and politician, who served as Minister of Defence from March to April 1906, during the Hungarian Constitutional Crisis of 1905.
Robert Clive Napper is an English serial killer and rapist. He has been convicted of two murders, one manslaughter, two rapes and two attempted rapes. He was sentenced to indefinite detention at Broadmoor Hospital on 18 December 2008 for the manslaughter of Ra
Manav Jagdusakumar Suthar is an Indian cricketer who plays for the Indian national team. He is a bowling all-rounder, who bats left-handed and bowls slow left-arm orthodox spin. He represents Rajasthan in domestic cricket and Gujarat Titans in the Indian Premi
Teach You a Lesson (Korean: 참교육) is a 2026 South Korean action school drama television series written by Lee Nam-kyu, Kim Da-hee, and Moon Jong-ho, directed by Hong Jong-chan, and starring Kim Mu-yeol, Lee Sung-min, Jin Ki-joo, and Pyo Ji-hoon. Based on the Na
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
Sir Lewis Carl Davidson Hamilton is a British racing driver who competes in Formula One for Ferrari. Hamilton has won a joint-record seven Formula One World Drivers' Championship titles—tied with Michael Schumacher—and holds the records for most wins (106), po
2026 Gilgit Baltistan Assembly election
Elections to appoint the 24 members of the 4th Gilgit-Baltistan Assembly, the highest body of the Government of Gilgit-Baltistan, were held on 7 June 2026.
Neatsville is an unincorporated community in Adair County, in the U.S. state of Kentucky. It is located at the junction of Kentucky Route 206 and Kentucky Route 76. Its elevation is 705 feet (215 m). For unknown reasons, the town's name was spelled as Neetsvil
Anthony Stewart Head was an English actor and singer. Primarily a performer in musical theatre, he rose to fame in the United Kingdom in the 1980s following his role in the Gold Blend couple television advertisements for Nescafé, which led to major roles in se
What the people building things argued about, from Hacker News.
Papers submitted to arXiv cs.AI that day.
There is a small number of case studies of automatic land cover classification on the coastal area. Here, I test extraction of seagrass beds, sandy area, oyster farming rafts at Mangoku-ura Lagoon, Miyagi, Japan by comparing manual tracing, simple image segmentation, and image transformation using deep learning. The result was used to extract the changes before and after the earthquake and tsunami. The output resolut
Non-Stationary Bandit Learning via Predictive Sampling
Thompson sampling has proven effective across a wide range of stationary bandit environments. However, as we demonstrate in this paper, it can perform poorly when applied to non-stationary environments. We show that such failures are attributed to the fact that, when exploring, the algorithm does not differentiate actions based on how quickly the information acquired loses its usefulness due to nonstationarity. Build
TAMUNA: Doubly Accelerated Distributed Optimization under Partial Participation
In distributed optimization and federated learning, slow and costly communication between parallel devices and the central server constitutes the primary bottleneck. To alleviate this burden, two strategies have emerged: 1) local training (LT), which reduces communication frequency by performing multiple local computations between rounds, and 2) compression (CC), which consists of transmitting lower-dimensional, comp
Geometric structure of shallow neural networks and constructive ${\mathcal L}^2$ cost minimization
In this paper, we approach the problem of cost (loss) minimization in underparametrized shallow ReLU networks through the explicit construction of upper bounds which appeal to the structure of classification data, without use of gradient descent. A key focus is on elucidating the geometric structure of approximate and precise minimizers. We consider an $L^2$ cost function, input space $\mathbb{R}^M$, output space ${\
Large Models for Time Series and Spatio-Temporal Data: A Survey and Outlook
Temporal data, including time series and spatio-temporal data, are pervasive in real-world applications. Generated in massive volumes by physical and virtual sensors, they record dynamic system behaviors and enable a wide range of downstream tasks. Effectively analyzing such data is crucial to unlocking their rich information content. Recent advances in large language models and other foundation models have accelerat
Bayesian Multistate Bennett Acceptance Ratio Methods
The multistate Bennett acceptance ratio (MBAR) method is a prevalent approach for computing free energies of thermodynamic states. In this work, we introduce BayesMBAR, a Bayesian generalization of the MBAR method. By integrating configurations sampled from thermodynamic states with a prior distribution, BayesMBAR computes a posterior distribution of free energies. Using the posterior distribution, we derive free ene
Persistent Homology for High-dimensional Data Based on Spectral Methods
Persistent homology is a popular computational tool for analyzing the topology of point clouds, such as the presence of loops or voids. However, many real-world datasets with low intrinsic dimensionality reside in an ambient space of much higher dimensionality. We show that in this case traditional persistent homology becomes very sensitive to noise and fails to detect the correct topology. The same holds true for ex
Consensus-based adaptive sampling and approximation for high-dimensional energy landscapes
We present a consensus-based framework that unifies phase space exploration with posterior-residual-based adaptive sampling for surrogate construction in high-dimensional energy landscapes. Unlike standard approximation tasks where sampling points can be freely queried, physical systems with complex energy landscapes such as molecular dynamics (MD) do not have direct access to arbitrary sampling regions due to the ph
We analyze geometric aspects of the gradient descent algorithm in Deep Learning (DL), and give a detailed discussion of the circumstance that in underparametrized DL networks, zero loss minimization can generically not be attained. As a consequence, we conclude that the distribution of training inputs must necessarily be non-generic in order to produce zero loss minimizers, both for the method constructed in [Chen-Mu
Node Classification in Random Trees
We propose a method for the classification of objects that are structured as random trees. Our aim is to model a distribution over the node label assignments in settings where the tree data structure is associated with node attributes (typically high dimensional embeddings). The tree topology is not predetermined and none of the label assignments are present during inference. Other methods that produce a distribution
The Mirrored Influence Hypothesis: Efficient Data Influence Estimation by Harnessing Forward Passes
Large-scale black-box models have become ubiquitous across numerous applications. Understanding the influence of individual training data sources on predictions made by these models is crucial for improving their trustworthiness. Current influence estimation techniques involve computing gradients for every training point or repeated training on different subsets. These approaches face obvious computational challenges
A Survey on Large Language Model-Based Game Agents
Game environments provide rich, controllable settings that stimulate many aspects of real-world complexity. As such, game agents offer a valuable testbed for exploring capabilities relevant to Artificial General Intelligence. Recently, the emergence of Large Language Models (LLMs) provides new opportunities to endow these agents with generalizable reasoning, memory, and adaptability in complex game environments. This
Interpretable global minima of deep ReLU neural networks on sequentially separable data
We explicitly construct zero loss neural network classifiers. We write the weight matrices and bias vectors in terms of cumulative parameters, which determine truncation maps acting recursively on input space. The configurations for the training data considered are (i) sufficiently small, well separated clusters corresponding to each class, and (ii) equivalence classes which are sequentially linearly separable. In th
Smoke and Mirrors in Causal Downstream Tasks
Machine Learning and AI have the potential to transform data-driven scientific discovery, enabling accurate predictions for several scientific phenomena. As many scientific questions are inherently causal, this paper looks at the causal inference task of treatment effect estimation, where the outcome of interest is recorded in high-dimensional observations in a Randomized Controlled Trial (RCT). Despite being the sim
Phase transition in large language models and the criticality of natural languages
Generation of text and speech in natural languages can be modeled as a stochastic process. This idea dates back to the seminal work of Markov and, later, to that of Shannon and also underlies the recent development of large language models (LLMs). The stochastic processes corresponding to natural languages should be distinct from those that generate nonlinguistic sequences. One of the features that discriminate lingu
OATH-Frames: Characterizing Online Attitudes Towards Homelessness with LLM Assistants
Warning: Contents of this paper may be upsetting. Public attitudes towards key societal issues, expressed on online media, are of immense value in policy and reform efforts, yet challenging to understand at scale. We study one such social issue: homelessness in the U.S., by leveraging the remarkable capabilities of large language models to assist social work experts in analyzing millions of posts from Twitter. We int
Embedding high-dimensional data into a low-dimensional space is an indispensable component of data analysis. In numerous applications, it is necessary to align and jointly embed multiple datasets from different studies or experimental conditions. Such datasets may share underlying structures of interest but exhibit individual distortions, resulting in misaligned embeddings using traditional techniques. In this work,
Mean Teacher based SSL Framework for Indoor Localization Using Wi-Fi RSSI Fingerprinting
Conventional large-scale indoor localization based on Wi-Fi RSSI fingerprinting faces issues of time-consuming and labor-intensive labeled data collection, limited generalization of a model trained under a supervised learning (SL) framework due to its inability to leverage unlabeled data, and model performance degradation in dynamic scenarios with environmental variations. To address those challenging issues, we prop
Most federated learning (FL) approaches assume a fixed device set. However, real-world scenarios often involve devices dynamically joining or leaving the system, driven by, e.g., user mobility patterns or handovers across cell boundaries. This dynamic setting introduces unique challenges: (1) the optimization objective evolves with the active device set, unlike traditional FL's static objective; and (2) the curre
On the Convergence and Straightness of Rectified Flow
Flow Matching has become a cornerstone of modern generative models like Stable Diffusion 3, largely due to the efficiency of its Rectified Flow (RF) variant. The success of RF hinges on iteratively learning straight trajectories, pushing generation towards fewer sampling steps. However, the theoretical link between path geometry and sampling efficiency has been underexplored. This paper fills this gap by introducing
ChronoFact: Timeline-based Temporal Fact Verification
Temporal claims, often riddled with inaccuracies, are a significant challenge in the digital misinformation landscape. Fact-checking systems that can accurately verify such claims are crucial for combating misinformation. Current systems struggle with the complexities of evaluating the accuracy of these claims, especially when they include multiple, overlapping, or recurring events. We introduce a novel timeline-base
MotionGPT-2: A General-Purpose Motion-Language Model for Motion Generation and Understanding
Generating lifelike human motions from descriptive texts has experienced remarkable research focus in the recent years, propelled by the emerging requirements of digital humans.Despite impressive advances, existing approaches are often constrained by limited control modalities, task specificity, and focus solely on body motion representations.In this paper, we present MotionGPT-2, a unified Large Motion-Language Mode
Discovering Data Structures: Nearest Neighbor Search and Beyond
We propose a general framework for end-to-end learning of data structures. Our framework adapts to the underlying data distribution and provides fine-grained control over query and space complexity. Crucially, the data structure is learned from scratch, and does not require careful initialization or seeding with candidate data structures/algorithms. We first apply this framework to the problem of nearest neighbor sea
Learning to transform conditional probability densities over time is a fundamental challenge spanning probabilistic modeling and the natural sciences. This task is paramount when forecasting the evolution of stochastic nonlinear dynamical systems in biological and physical domains. While flow-based models can predict the temporal evolution of probability distributions, existing approaches often assume discrete condit
Learning Fine-grained Parameter Sharing via Sparse Tensor Decomposition
Large neural networks achieve state-of-the-art performance on many tasks, yet their sheer size hinders deployment on resource-constrained devices. Among existing compression approaches, cross-layer parameter sharing remains relatively unexplored for transformer models. In this paper, we introduce Fine-grained Parameter Sharing (FiPS), a unified framework for compressing transformer Multi-Layer Perceptrons (MLPs) that
Notable events recorded on this day and month across all years.