Record 25122025 · captured 2026-08-25
The world looked up Dhurandhar. 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 is a 2025 Indian Hindi-language spy action thriller film written and directed by Aditya Dhar. It is produced by Aditya Dhar, Lokesh Dhar and Jyoti Deshpande under Jio Studios and B62 Studios. The film features an ensemble cast consisting of Ranveer
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
Avatar: Fire and Ash is a 2025 American epic science fiction film directed by James Cameron from a screenplay he co-wrote with Rick Jaffa and Amanda Silver. Produced by Lightstorm Entertainment, it is the third installment in the Avatar film series and the seq
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
Tylor Chase is an American former actor and YouTuber, best known for his role as Martin Qwerly in the Nickelodeon series Ned's Declassified School Survival Guide (2004–2007).
Jeffrey Edward Epstein was an American financier and child sex offender. He began his career as a math teacher at the Dalton School in New York City, before entering the banking and finance sector. Over several decades, he made much of his fortune providing ta
Vincent Walter Zampella II was an American video game designer. He was best known for being a co-founder and the former studio head of Infinity Ward, the head of Respawn Entertainment, and the former CEO of Ripple Effect Studios.
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
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.
The Epstein files are a partially released collection of millions of documents, images, videos, and emails related to the activities of American financier and convicted child sex offender Jeffrey Epstein, including his social circle of public figures, politici
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
Benjamin Eric Sasse is an American politician and academic administrator. He represented Nebraska in the United States Senate from 2015 to 2023, resigning to become the president of the University of Florida. He is a member of the Republican Party. A critic of
Macaulay Macaulay Culkin Culkin is an American actor and musician. Considered one of the most successful child actors of the 1990s, Culkin has received several accolades including a Golden Globe Award nomination. In 2005, he was ranked second on VH1's list of
James Finley Ransone III was an American actor. Known for his roles in horror and drama, he played Ziggy Sobotka in the second season of the drama series The Wire, Cpl. Josh Ray Person in the war drama miniseries Generation Kill (2008), Deputy "So-and-So" in t
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
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
Marty Supreme is a 2025 American sports comedy-drama film directed by Josh Safdie, who co-wrote it with Ronald Bronstein. Set in the 1950s, it stars Timothée Chalamet as table tennis player Marty Mauser and follows his quest to become world champion. Gwyneth P
Christopher Anton Rea was an English-Irish rock and blues singer-songwriter, guitarist and record producer. He was known for his distinctive gravelly voice, slide guitar playing and music style blending soft rock with blues.
Onika Tanya Maraj-Petty, known professionally as Nicki Minaj, is a Trinidadian rapper, singer, and songwriter. Dubbed the "Queen of Rap" and one of the most influential rappers of all time, she is noted for her dynamic rap flow, witty lyrics, musical versatili
Wake Up Dead Man is a 2025 American mystery film written and directed by Rian Johnson. It is the third film in the Knives Out series. The film stars Daniel Craig, who reprises his role as master detective Benoit Blanc as he investigates the death of a Catholic
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
Heated Rivalry is a Canadian sports romance television series created, written, and directed by Jacob Tierney for Crave. Based on the Game Changers book series by Rachel Reid, the show takes its title from the 2019 second installment. It stars Hudson Williams
Patrick Cassidy Finn was an American film and television actor. Initially performing with the comedy troupe The Second City in Chicago, he first gained attention for his main role as Dan Coleman on the CBS sitcom The George Wendt Show (1995).
6-7 is an Internet meme, slang term, and gesture that became popular in 2025 on TikTok and Instagram Reels. It has no fixed meaning.
One Battle After Another is a 2025 American action thriller film written, directed, and produced by Paul Thomas Anderson. Inspired by the 1990 novel Vineland by Thomas Pynchon, the film's ensemble cast includes Leonardo DiCaprio, Sean Penn, Benicio del Toro, R
Ghislaine Noelle Marion Maxwell is a British convicted child sex trafficker and former socialite. In 2021, she was convicted of child sex trafficking, and in 2022 was sentenced to 20 years in prison.
Avatar is a 2009 epic science fiction film written and directed by James Cameron. It features an ensemble cast including Sam Worthington, Zoe Saldaña, Stephen Lang, Michelle Rodriguez, and Sigourney Weaver. It is the first installment in the Avatar film series
Anthony Oluwafemi Olaseni "AJ" Joshua is a British professional boxer. He held the unified heavyweight championship twice between 2017 and 2021. He also held the International Boxing Organization (IBO) title during his reigns as champion. At regional level, he
Love Actually is a 2003 Christmas romantic comedy film written and directed by Richard Curtis. The film features an ensemble cast, composed predominantly of British actors, many of whom had worked with Curtis in previous projects. An international co-productio
The Great Flood (Korean: 대홍수) is a 2025 South Korean science fiction disaster film co-written and directed by Kim Byung-woo. Starring Kim Da-mi and Park Hae-soo, the film depicts the desperate struggle of those who have pinned their hopes on humanity's last da
What the people building things argued about, from Hacker News.
Papers submitted to arXiv cs.AI that day.
Improving Neural Question Generation using World Knowledge
In this paper, we propose a method for incorporating world knowledge (linked entities and fine-grained entity types) into a neural question generation model. This world knowledge helps to encode additional information related to the entities present in the passage required to generate human-like questions. We evaluate our models on both SQuAD and MS MARCO to demonstrate the usefulness of the world knowledge features.
Explicit Group Sparse Projection with Applications to Deep Learning and NMF
We design a new sparse projection method for a set of vectors that guarantees a desired average sparsity level measured leveraging the popular Hoyer measure (an affine function of the ratio of the $\ell_1$ and $\ell_2$ norms). Existing approaches either project each vector individually or require the use of a regularization parameter which implicitly maps to the average $\ell_0$-measure of sparsity. Instead, in our a
The remarkable empirical performance of distributional reinforcement learning (RL) has garnered increasing attention to understanding its theoretical advantages over classical RL. By decomposing the categorical distributional loss commonly employed in distributional RL, we find that the potential superiority of distributional RL can be attributed to a derived distribution-matching entropy regularization. This less-st
We propose Deep Kronecker Network (DKN), a novel framework designed for analyzing medical imaging data, such as MRI, fMRI, CT, etc. Medical imaging data is different from general images in at least two aspects: i) sample size is usually much more limited, ii) model interpretation is more of a concern compared to outcome prediction. Due to its unique nature, general methods, such as convolutional neural network (CNN),
Eliciting Risk Aversion with Inverse Reinforcement Learning via Interactive Questioning
We investigate a framework for robo-advisors to estimate non-expert clients' risk aversion using adaptive binary-choice questionnaires. We model risk aversion using cost functions and spectral risk measures in a static setting. We prove the finite-sample identifiability and, for properly designed questions, obtain a convergence rate of $\sqrt{N}$ up to a logarithmic factor, where $N$ is the number of questions. W
Imperative Learning: A Self-supervised Neuro-Symbolic Learning Framework for Robot Autonomy
Data-driven methods such as reinforcement and imitation learning have achieved remarkable success in robot autonomy. However, their data-centric nature still hinders them from generalizing well to ever-changing environments. Moreover, labeling data for robotic tasks is often impractical and expensive. To overcome these challenges, we introduce a new self-supervised neuro-symbolic (NeSy) computational framework, imper
TimeBridge: Better Diffusion Prior Design with Bridge Models for Time Series Generation
Time series generation is widely used in real-world applications such as simulation, data augmentation, and hypothesis testing. Recently, diffusion models have emerged as the de facto approach to time series generation, enabling diverse synthesis scenarios. However, the fixed standard-Gaussian diffusion prior may be ill-suited for time series data, which exhibit properties such as temporal order and fixed time points
DATTA: Domain Diversity Aware Test-Time Adaptation for Dynamic Domain Shift Data Streams
Test-Time Adaptation (TTA) addresses domain shifts between training and testing. However, existing methods assume a homogeneous target domain (e.g., single domain) at any given time. They fail to handle the dynamic nature of real-world data, where single-domain and multiple-domain distributions change over time. We identify that performance drops in multiple-domain scenarios are caused by batch normalization errors a
BoostTrack++: using tracklet information to detect more objects in multiple object tracking
Multiple object tracking (MOT) depends heavily on selection of true positive detected bounding boxes. However, this aspect of the problem is mostly overlooked or mitigated by employing two-stage association and utilizing low confidence detections in the second stage. Recently proposed BoostTrack attempts to avoid the drawbacks of multiple stage association approach and use low-confidence detections by applying detect
Sequence to Sequence Reward Modeling: Improving RLHF by Language Feedback
Aligning the behavior of Large language models (LLMs) with human intentions and values remains a critical challenge. Reinforcement learning from human feedback (RLHF) aligns LLMs by training a reward model (RM) on human preferences and fine-tuning the LLMs to maximize RM feedback. Despite its effectiveness and popularity, RLHF is prone to biased local optimization. It means RM fails to provide feedback that accuratel
Characterizing a quantum system by learning its state or evolution is a fundamental problem in quantum physics and learning theory with a myriad of applications. Recently, as a new approach to this problem, the task of agnostic state tomography was defined, in which one aims to approximate an arbitrary quantum state by a simpler one in a given class. Generalizing this notion to quantum processes, we initiate the stud
Unbiased Region-Language Alignment for Open-Vocabulary Dense Prediction
Pre-trained vision-language models (VLMs), such as CLIP, have demonstrated impressive zero-shot recognition capability, but still underperform in dense prediction tasks. Self-distillation recently is emerging as a promising approach for fine-tuning VLMs to better adapt to local regions without requiring extensive annotations. However, previous state-of-the-art approaches often suffer from significant `foreground bias
A Review on the Applications of Transformer-based language models for Nucleotide Sequence Analysis
In recent times, Transformer-based language models are making quite an impact in the field of natural language processing. As relevant parallels can be drawn between biological sequences and natural languages, the models used in NLP can be easily extended and adapted for various applications in bioinformatics. In this regard, this paper introduces the major developments of Transformer-based models in the recent past
Towards Hierarchical Multi-Agent Decision-Making for Uncertainty-Aware EV Charging
Recent advances in bidirectional EV charging and discharging systems have spurred interest in workplace applications. However, real-world deployments face various dynamic factors, such as fluctuating electricity prices and uncertain EV departure times, that hinder effective energy management. To address these issues and minimize building electricity costs while meeting EV charging requirements, we design a hierarchic
Pointmap-Conditioned Diffusion for Consistent Novel View Synthesis
Synthesizing extrapolated views remains a difficult task, especially in urban driving scenes, where the only reliable sources of data are limited RGB captures and sparse LiDAR points. To address this problem, we present PointmapDiff, a framework for novel view synthesis that utilizes pre-trained 2D diffusion models. Our method leverages point maps (i.e., rasterized 3D scene coordinates) as a conditioning signal, capt
Full-scale Representation Guided Network for Retinal Vessel Segmentation
The U-Net architecture and its variants have remained state-of-the-art (SOTA) for retinal vessel segmentation over the past decade. In this study, we introduce a Full-Scale Guided Network (FSG-Net), where a novel feature representation module using modernized convolution blocks effectively captures full-scale structural information, while a guided convolution block subsequently refines this information. Specifically,
This study attempts to advancing content analysis methodology from consensus-oriented to coordination-oriented practices, thereby embracing diverse coding outputs and exploring the dynamics among differential perspectives. As an exploratory investigation of this approach, we evaluate six GPT-4o configurations to analyze sentiment in Fox News and MSNBC transcripts on Biden and Trump during the 2020 U.S. presidential c
This paper addresses the problem of weakly supervised cross-view localization, where the goal is to estimate the pose of a ground camera relative to a satellite image with noisy ground truth annotations. A common approach to bridge the cross-view domain gap for pose estimation is Bird's-Eye View (BEV) synthesis. However, existing methods struggle with height ambiguity due to the lack of depth information in groun
SPOC: Spatially-Progressing Object State Change Segmentation in Video
Object state changes in video reveal critical cues about human and agent activity. However, existing methods are limited to temporal localization of when the object is in its initial state (e.g., cheese block) versus when it has completed a state change (e.g., grated cheese), offering no insight into where the change is unfolding. We propose to deepen the problem by introducing the spatially-progressing object state
CAKE: Cascading and Adaptive KV Cache Eviction with Layer Preferences
Large language models (LLMs) excel at processing long sequences, boosting demand for key-value (KV) caching. While recent efforts to evict KV cache have alleviated the inference burden, they often fail to allocate resources rationally across layers with different attention patterns. In this paper, we introduce Cascading and Adaptive KV cache Eviction (CAKE), a novel approach that frames KV cache eviction as a "ca
Evolving Security in LLMs: A Study of Jailbreak Attacks and Defenses
Large Language Models (LLMs) are increasingly popular, powering a wide range of applications. Their widespread use has sparked concerns, especially through jailbreak attacks that bypass safety measures to produce harmful content. In this paper, we present a comprehensive security analysis of large language models (LLMs), addressing critical research questions on the evolution and determinants of model safety. Specifi
Ensuring Safety in an Uncertain Environment: Constrained MDPs via Stochastic Thresholds
This paper studies constrained Markov decision processes (CMDPs) with constraints against stochastic thresholds, aiming at safety of reinforcement learning in unknown and uncertain environments. We leverage a Growing-Window estimator sampling from interactions with the uncertain environment to estimate the thresholds, based on which we design Stochastic Pessimistic-Optimistic Thresholding (SPOT), a novel model-based
A Multicore and Edge TPU-Accelerated Multimodal TinyML System for Livestock Behavior Recognition
The advancement of technology has revolutionized the agricultural industry, transitioning it from labor-intensive farming practices to automated, AI-powered management systems. In recent years, more intelligent livestock monitoring solutions have been proposed to enhance farming efficiency and productivity. This work presents a novel approach to animal activity recognition and movement tracking, leveraging tiny machi
Physics-Informed Inference Time Scaling for Solving High-Dimensional PDE via Defect Correction
Solving high-dimensional partial differential equations (PDEs) is a critical challenge where modern data-driven solvers often lack reliability and rigorous error guarantees. We introduce Simulation-Calibrated Scientific Machine Learning (SCaSML), a framework that systematically improves pre-trained PDE solvers at inference time without any retraining. Our core idea is to use defect correction method that derive a new
Learning Enhanced Ensemble Filters
The filtering distribution in hidden Markov models evolves according to the law of a mean-field model in state-observation space. The ensemble Kalman filter (EnKF) approximates this mean-field model with an ensemble of interacting particles, employing a Gaussian ansatz for the joint distribution of the state and observation at each observation time. These methods are robust, but the Gaussian ansatz limits accuracy. H
Notable events recorded on this day and month across all years.