Record 06042026 · captured 2026-08-25
The world looked up Dhurandhar: The Revenge. 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.
Dhurandhar: The Revenge is a 2026 Indian Hindi-language spy action-thriller film written and directed by Aditya Dhar. It is produced by Dhar, Lokesh Dhar, and Jyoti Deshpande under Jio Studios and B62 Studios. It is a sequel to the 2025 film Dhurandhar and the
Artemis II was a crewed flyby of the Moon. It is currently the only crewed flight beyond low Earth orbit since Apollo 17 in 1972. It was the first crewed flight of the NASA-led Artemis program, the first crewed flight of the Space Launch System (SLS), and the
The Drama is a 2026 American dark romantic comedy film written and directed by Kristoffer Borgli. It stars Zendaya and Robert Pattinson as a happily engaged couple whose relationship is tested by an unexpected revelation the week before their wedding.
Lauren Marie Betts is an American professional basketball player for the Washington Mystics of the Women's National Basketball Association (WNBA). She played for Grandview High School in Aurora, Colorado, where she was ranked as the number one recruit in her c
List of highest-grossing Indian films
This ranking lists the highest-grossing Indian films produced by Indian cinema, based on conservative global box office estimates as reported by organisations classified as green by Wikipedia. The figures are not adjusted for inflation. However, there is no of
Easter, also called Pasch or Pascha or Resurrection Sunday, is a Christian festival and cultural holiday commemorating the resurrection of Jesus from the dead, described in the Bible's New Testament as having occurred on the third day of his burial following h
Since 28 February 2026, the United States and Israel have been at war with Iran and its regional allies. Hostilities broke out after US–Israeli airstrikes killed several Iranian officials, including Supreme Leader Ali Khamenei. The strikes were launched amid o
Project Hail Mary is a 2026 American science fiction film produced and directed by Phil Lord and Christopher Miller and written by Drew Goddard, based on the 2021 novel of the same name by Andy Weir. It stars Ryan Gosling, who also produced the film, as Ryland
The Super Mario Galaxy Movie is a 2026 American animated adventure comedy film based on Nintendo's Mario video game franchise. Directed by Aaron Horvath and Michael Jelenic and written by Matthew Fogel, it is the sequel to The Super Mario Bros. Movie (2023). C
Donald John Trump is an American politician, media personality, and businessman who is the 47th president of the United States. A member of the Republican Party, he served as the 45th president from 2017 to 2021.
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
Daniel S. Hurley is an American men's college basketball coach who is the head coach of the UConn Huskies. In 2023 and 2024, Hurley led UConn to back-to-back NCAA Division I national championships, and led the Huskies to another title game appearance in 2026.
Lamar Joseph Odom is an American former professional basketball player who played for four teams during his 14-year career in the National Basketball Association (NBA), and won back-to-back championships in 2009 and 2010 with the Los Angeles Lakers. He was als
Cori Rashel Close is an American basketball coach who is the head coach for the UCLA Bruins women's team. She played college basketball as a guard for the UC Santa Barbara Gauchos from 1989 to 1993, serving as a team captain during her final two seasons and he
World League for Freedom and Democracy
The World League for Freedom and Democracy (WLFD) is an international non-governmental organization of anti-communist politicians and groups. It was founded in 1954 as the Asian Peoples' Anti-Communist League (APACL) under the initiative of Chiang Kai-shek, le
Dusty Allan May is an American professional basketball coach who is the head coach of the Dallas Mavericks of the National Basketball Association (NBA). He was previously the head coach for Florida Atlantic University from 2018 to 2024 and the University of Mi
On May 11, 2022, Anna Moriah "Mo" Wilson, a 25‑year‑old professional cyclist, was fatally shot at a friend's residence in Austin, Texas. Investigators identified Kaitlin Marie Armstrong as the suspect after surveillance footage placed her near the scene and ev
Dawn Michelle Staley is an American basketball coach and former player who is the head coach for the South Carolina Gamecocks women's basketball team. A point guard, she played college basketball for the Virginia Cavaliers and spent eight seasons in the Women'
The Ten Commandments (1956 film)
The Ten Commandments is a 1956 American epic biblical adventure drama film produced, directed, and narrated by Cecil B. DeMille, shot in VistaVision, and released by Paramount Pictures. Based on the Bible's Book of Exodus and other sources, it dramatizes the s
Saints Row 2 is a 2008 action-adventure game developed by Volition and published by THQ. It is the sequel to 2006's Saints Row and the second installment in the Saints Row series. The game was released in October 2008 for the PlayStation 3 and Xbox 360, Januar
John Anthony White is an American musician who was the guitarist and lead vocalist of the rock duo the White Stripes. He was a key artist of the 2000s indie and garage rock movements, noted for his distinctive musical techniques, eccentricity, and utilization
The Chainsmokers are an American electronic DJ and production duo consisting of Alex Pall and Drew Taggart. They started out by releasing remixes of songs by indie artists. The EDM-pop duo achieved a breakthrough with their 2014 song "#Selfie", which became a
George Nicholson (rugby union)
George Nicholson was a New Zealand rugby union footballer who played for New Zealand – the All Blacks – between 1903 and 1907. He played club rugby in Auckland for the City club, before making his provincial debut for Auckland in 1901. After playing for the No
Project Hail Mary is a 2021 hard science fiction novel by American writer Andy Weir. It centers on science teacher and former biologist Ryland Grace, who wakes up aboard a spacecraft, afflicted with amnesia.
Yaxel Okari Lendeborg is an American-Dominican basketball player for the Golden State Warriors of the National Basketball Association (NBA). He was drafted 11th overall in the 2026 NBA draft by the Warriors. Lendeborg played college basketball for the Arizona
Something Very Bad Is Going to Happen
Something Very Bad Is Going to Happen is an American horror television miniseries created by Haley Z. Boston for Netflix. Boston serves as the series showrunner and is also an executive producer along with the Duffer Brothers. Camila Morrone and Adam DiMarco s
This is a list of dates for Easter. The Easter dates also affect when Ash Wednesday, Holy Thursday, Good Friday, Holy Saturday, the Feast of the Ascension and Pentecost occur in a given year. Easter may occur on different dates in the Gregorian Calendar (Weste
Aday Mara Gómez is a Spanish basketball player for the Oklahoma City Thunder of the National Basketball Association (NBA). He played college basketball for the UCLA Bruins and Michigan Wolverines. Mara was an NCAA national champion and the Big Ten Defensive Pl
The 2026 NXT Stand & Deliver, also promoted as NXT Stand & Deliver: St. Louis, was a professional wrestling livestreaming event produced by WWE for its developmental brand NXT. It was the sixth annual Stand & Deliver and took place on Saturday, April 4, 2026,
Christina Hammock Koch is an American engineer and NASA astronaut. On her mission to the International Space Station in 2019–20 she was part of the first all‑female spacewalk and set the record for the longest spaceflight by a woman. On the Artemis II lunar fl
What the people building things argued about, from Hacker News.
Papers submitted to arXiv cs.AI that day.
Linguistic Frameworks Go Toe-to-Toe at Neuro-Symbolic Language Modeling
We examine the extent to which, in principle, linguistic graph representations can complement and improve neural language modeling. With an ensemble setup consisting of a pretrained Transformer and ground-truth graphs from one of 7 different formalisms, we find that, overall, semantic constituency structures are most useful to language modeling performance -- outpacing syntactic constituency structures as well as syn
Reanalyzing L2 Preposition Learning with Bayesian Mixed Effects and a Pretrained Language Model
We use both Bayesian and neural models to dissect a data set of Chinese learners' pre- and post-interventional responses to two tests measuring their understanding of English prepositions. The results mostly replicate previous findings from frequentist analyses and newly reveal crucial interactions between student ability, task type, and stimulus sentence. Given the sparsity of the data as well as high diversity
In this work we build upon negative results from an attempt at language modeling with predicted semantic structure, in order to establish empirical lower bounds on what could have made the attempt successful. More specifically, we design a concise binary vector representation of semantic structure at the lexical level and evaluate in-depth how good an incremental tagger needs to be in order to achieve better-than-bas
Distributed Quantum Neural Networks via Partitioned Features Encoding
Quantum neural networks are expected to be a promising application in near-term quantum computing, but face challenges such as vanishing gradients during optimization and limited expressibility by a limited number of qubits and shallow circuits. To mitigate these challenges, an approach using distributed quantum neural networks has been proposed to make a prediction by approximating outputs of a large circuit using m
Efficient Causal Graph Discovery Using Large Language Models
We propose a novel framework that leverages LLMs for full causal graph discovery. While previous LLM-based methods have used a pairwise query approach, this requires a quadratic number of queries which quickly becomes impractical for larger causal graphs. In contrast, the proposed framework uses a breadth-first search (BFS) approach which allows it to use only a linear number of queries. We also show that the propose
Prompting ChatGPT for Translation: A Comparative Analysis of Translation Brief and Persona Prompts
Prompt engineering has shown potential for improving translation quality in LLMs. However, the possibility of using translation concepts in prompt design remains largely underexplored. Against this backdrop, the current paper discusses the effectiveness of incorporating the conceptual tool of translation brief and the personas of translator and author into prompt design for translation tasks in ChatGPT. Findings sugg
One of the current principal defenses against weaponized synthetic media continues to be the ability of the targeted individual to visually or auditorily recognize AI-generated content when they encounter it. However, as the realism of synthetic media continues to rapidly improve, it is vital to have an accurate understanding of just how susceptible people currently are to potentially being misled by convincing but f
Output-Constrained Decision Trees
Incorporating domain-specific constraints into machine learning models is essential for generating predictions that are both accurate and feasible in real-world applications. This paper introduces new methods for training Output-Constrained Regression Trees (OCRT), addressing the limitations of traditional decision trees in constrained multi-target regression tasks. We propose three approaches: M-OCRT, which uses spl
Swish-T : Enhancing Swish Activation with Tanh Bias for Improved Neural Network Performance
We propose the Swish-T family, an enhancement of the existing non-monotonic activation function Swish. Swish-T is defined by adding a Tanh bias to the original Swish function. This modification creates a family of Swish-T variants, each designed to excel in different tasks, showcasing specific advantages depending on the application context. The Tanh bias allows for broader acceptance of negative values during initia
Motion Capture from Inertial and Vision Sensors
Human motion capture is the foundation for many computer vision and graphics tasks. While industrial motion capture systems with complex camera arrays or expensive wearable sensors have been widely adopted in movie and game production, consumer-affordable and easy-to-use solutions for personal applications are still far from mature. To utilize a mixture of a monocular camera and very few inertial measurement units (I
Generalized SAM: Efficient Fine-Tuning of SAM for Variable Input Image Sizes
There has been a lot of recent research on improving the efficiency of fine-tuning foundation models. In this paper, we propose a novel efficient fine-tuning method that allows the input image size of Segment Anything Model (SAM) to be variable. SAM is a powerful foundational model for image segmentation trained on huge datasets, but it requires fine-tuning to recognize arbitrary classes. The input image size of SAM
Expressive Prompting: Improving Emotion Intensity and Speaker Consistency in Zero-Shot TTS
Recent advancements in speech synthesis have enabled large language model (LLM)-based systems to perform zero-shot generation with controllable content, timbre, speaker identity, and emotion through input prompts. As a result, these models heavily rely on prompt design to guide the generation process. However, existing prompt selection methods often fail to ensure that prompts contain sufficiently stable speaker iden
Amortized Inference of Causal Models via Conditional Fixed-Point Iterations
Structural Causal Models (SCMs) offer a principled framework to reason about interventions and support out-of-distribution generalization, which are key goals in scientific discovery. However, the task of learning SCMs from observed data poses formidable challenges, and often requires training a separate model for each dataset. In this work, we propose an amortized inference framework that trains a single model to pr
Transferable Targeted Attacks (TTAs) face significant challenges due to severe overfitting to surrogate models. Recent breakthroughs heavily rely on large-scale training data of victim models, while data-free solutions, \textit{i.e.}, image transformation-involved gradient optimization, often depend on black-box feedback for method design and tuning. These dependencies violate black-box transfer settings and compromi
Fast and Efficient Transformer-based Method for Bird's Eye View Instance Prediction
Accurate object detection and prediction are critical to ensure the safety and efficiency of self-driving architectures. Predicting object trajectories and occupancy enables autonomous vehicles to anticipate movements and make decisions with future information, increasing their adaptability and reducing the risk of accidents. Current State-Of-The-Art (SOTA) approaches often isolate the detection, tracking, and predic
Precision medicine in musculoskeletal imaging requires scalable measurement infrastructure. We developed a modular system that converts routine MRI into standardized quantitative biomarkers suitable for clinical decision support. Promptable foundation segmenters (SAM, SAM2, MedSAM) were fine-tuned across heterogeneous musculoskeletal datasets and coupled to automated detection for fully automatic prompting. Fine-tune
How has the public responded to the increasing prevalence of artificial intelligence (AI)-based technologies? We investigate public perceptions of AI by collecting over 12,000 responses over 12 months from a nationally representative U.S. sample. Participants provided open-ended metaphors reflecting their mental models of AI, a methodology that overcomes the limitations of traditional self-reported measures by captur
Distributional Statistics Restore Training Data Auditability in One-step Distilled Diffusion Models
The proliferation of diffusion models trained on web-scale, provenance-uncertain image collections has made it essential, yet technically unresolved, to determine whether a model has learned from specific copyrighted data without authorization. Current methods primarily rely on the memorization effect, whereby models reconstruct their training images better than unseen ones, to detect unauthorized training data on a
Zero-shot Concept Bottleneck Models
Concept bottleneck models (CBMs) are inherently interpretable and intervenable neural network models, which explain their final label prediction by the intermediate prediction of high-level semantic concepts. However, they require target task training to learn input-to-concept and concept-to-label mappings, incurring target dataset collections and training resources. In this paper, we present zero-shot concept bottle
Learn then Decide: A Learning Approach for Designing Data Marketplaces
As data marketplaces become increasingly central to the digital economy, it is crucial to design efficient pricing mechanisms that optimize revenue while ensuring fair and adaptive pricing. We introduce the Maximum Auction-to-Posted Price (MAPP) mechanism, a novel two-stage approach that first estimates the bidders' value distribution through auctions and then determines the optimal posted price based on the lear
A Unified Approach to Analysis and Design of Denoising Markov Models
Probabilistic generative models based on measure transport, such as diffusion and flow-based models, are often formulated in the language of Markovian stochastic dynamics, where the choice of the underlying process impacts both algorithmic design choices and theoretical analysis. In this paper, we aim to establish a rigorous mathematical foundation for denoising Markov models, a broad class of generative models that
We'll Fix it in Post: Improving Text-to-Video Generation with Neuro-Symbolic Feedback
Current text-to-video (T2V) generation models are increasingly popular due to their ability to produce coherent videos from textual prompts. However, these models often struggle to generate semantically and temporally consistent videos when dealing with longer, more complex prompts involving multiple objects or sequential events. Additionally, the high computational costs associated with training or fine-tuning make
ELEPHANT: Measuring and understanding social sycophancy in LLMs
LLMs are known to exhibit sycophancy: agreeing with and flattering users, even at the cost of correctness. Prior work measures sycophancy only as direct agreement with users' explicitly stated beliefs that can be compared to a ground truth. This fails to capture broader forms of sycophancy such as affirming a user's self-image or other implicit beliefs. To address this gap, we introduce social sycophancy, cha
gen2seg: Generative Models Enable Generalizable Instance Segmentation
By pretraining to synthesize coherent images from perturbed inputs, generative models inherently learn to understand object boundaries and scene compositions. How can we repurpose these generative representations for general-purpose perceptual organization? We finetune Stable Diffusion and MAE (encoder+decoder) for category-agnostic instance segmentation using our instance coloring loss exclusively on a narrow set of
Improving LLM First-Token Predictions in Multiple-Choice Question Answering via Output Prefilling
Large Language Models (LLMs) are increasingly evaluated on multiple-choice question answering (MCQA) tasks using *first-token probability* (FTP), which selects the answer option whose initial token has the highest likelihood. While efficient, FTP can be fragile: models may assign high probability to unrelated tokens (*misalignment*) or use a valid token merely as part of a generic preamble rather than as a clear answ
Notable events recorded on this day and month across all years.