Record 06032026 · captured 2026-08-25
The world looked up Markwayne Mullin. 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.
Markwayne Mullin is an American politician and businessman who has served since 2026 as the ninth United States secretary of homeland security. A member of the Republican Party, Mullin served from 2023 to 2026 as the junior United States senator from Oklahoma
Kristi Lynn Arnold Noem is an American politician serving as the United States special envoy for the Shield of the Americas since 2026. From 2025 to 2026, she served as the eighth United States secretary of homeland security. A member of the Republican Party,
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
Ali Hosseini Khamenei was an Iranian politician and Shia cleric who served as the second supreme leader of Iran from 1989 until his assassination in 2026. A member of the Khamenei family who held the title Grand Ayatollah, he previously served as the third pre
James Dell Talarico is an American politician and educator who has served since 2018 as a member of the Texas House of Representatives. He is the Democratic nominee in the 2026 U.S. Senate election in Texas.
Louis Leo Holtz was an American college football coach. He served as the head football coach at the College of William & Mary (1969–1971), North Carolina State University (1972–1975), the New York Jets (1976), the University of Arkansas (1977–1983), the Univer
The ICC Men's T20 World Cup, formerly the ICC World Twenty20, is a biennial world cup for cricket in Twenty20 International (T20I) format, organised by the International Cricket Council (ICC). It was held in every odd year from 2007 to 2009, and since 2010 has
Corey Ryan Lewandowski is an American political operative, lobbyist, and pundit politically aligned with Donald Trump. He served as the first campaign manager for Trump's 2016 presidential campaign. He has also worked as a political commentator for CNN, One Am
Iran, officially the Islamic Republic of Iran, and historically known as Persia, is a country in West Asia. It borders Iraq to the west, Turkey, Azerbaijan, and Armenia to the northwest, the Caspian Sea to the north, Turkmenistan to the northeast, Afghanistan
IRIS Dena (75) was a Moudge-class frigate in the Southern Fleet of the Islamic Republic of Iran Navy. She was named after Mount Dena, and was commissioned into the navy in 2021.
Timothy Patrick Sheehy is an American politician serving since 2025 as the junior United States senator from Montana. A member of the Republican Party, he is the youngest Republican U.S. senator and the second-youngest U.S. senator, after Jon Ossoff.
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
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
Peter Brian Hegseth is an American government official, veteran, and former television personality who has served as the 29th United States secretary of defense since 2025.
Jasmine Felicia Crockett is an American politician serving as the U.S. representative for Texas's 30th congressional district since 2023. A member of the Democratic Party, she represented the 100th district in the Texas House of Representatives from 2021 to 20
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 Yakovlev Yak-130 is a subsonic, two-seat, advanced jet trainer and light combat aircraft.
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
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
Ruhollah Mostafavi Khomeini was an Iranian politician and Shia cleric who served as the first supreme leader of Iran from 1979 until his death in 1989. He was the leader of the Iranian Revolution, which overthrew Mohammad Reza Pahlavi, ended the Pahlavi era, a
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.
Mojtaba Hosseini Khamenei is an Iranian Shia cleric and politician who has served as the third supreme leader of Iran since 2026. A member of the Khamenei family and the second son of second supreme leader Ali Khamenei, he previously served as Vakil of the Sup
Anna's Archive is an open source search engine for shadow libraries that was launched by the pseudonymous Anna shortly after law enforcement efforts to shut down Z-Library in 2022. The site aggregates records from Z-Library, Sci-Hub, and Library Genesis (LibGe
Kurds, or the Kurdish people, are an Iranic ethnic group from West Asia. They are indigenous to Kurdistan, which is a geographic region spanning southeastern Turkey, northwestern Iran, northern Iraq, and northeastern Syria. Consisting of 30–45 million people,
Young Sherlock (British TV series)
Young Sherlock is a British mystery television series that is created by Matthew Parkhill and developed by Peter Harness and Guy Ritchie who also directed two episodes. It is inspired by Andrew Lane's Young Sherlock Holmes book series, itself a pastiche of Art
Elizabeth Lyon (fl. c. 1722–1726), nicknamed Edgworth Bess or Edgware Bess, was an English thief, prostitute and the partner of the criminal Jack Sheppard. Little is known about her background or her early life, but it is known that she was working as a prosti
Jeffrey Preston Bezos is an American businessman, and the founder, executive chairman, and former president and CEO of Amazon, the world's largest e-commerce and cloud computing company. According to the Bloomberg Billionaires Index and Forbes, he was the worl
John Fitzgerald Kennedy Jr., also referred to as JFK Jr., was an American businessman, attorney, magazine publisher, and journalist. He was the son of the 35th U.S. president John F. Kennedy, and First Lady Jacqueline Kennedy.
The Bride! is a 2026 American gothic romance film directed and written by Maggie Gyllenhaal and starring Jessie Buckley, Christian Bale, Peter Sarsgaard, Annette Bening, Jake Gyllenhaal, and Penélope Cruz. The film draws inspiration from the 1935 film Bride of
Hero Beauregard Faulkner Fiennes Tiffin is an English actor and film producer. First gaining recognition as the young Tom Riddle in Harry Potter and the Half-Blood Prince (2009), he is most known for his starring roles as Hardin Scott in the After film series
What the people building things argued about, from Hacker News.
Papers submitted to arXiv cs.AI that day.
Motion Illusions Generated Using Predictive Neural Networks Also Fool Humans
Why do we sometimes perceive static images as if they were moving? Visual motion illusions enjoy a sustained popularity, yet there is no definitive answer to the question of why they work. Here we present evidence in favor of the hypothesis that illusory motion is a side effect of the predictive abilities of the brain. We present a generative model, the Evolutionary Illusion GENerator (EIGen), that creates new visual
Linear Multidimensional Regression with Interactive Fixed-Effects
This paper studies a linear model for multidimensional panel data of three or more dimensions with unobserved interactive fixed-effects. The main estimator uses a Neyman-orthogonal approach, and requires two preliminary steps. First, the model is embedded within a two-dimensional panel framework where factor model methods in Bai (2009) lead to consistent, but slowly converging, estimates. The second step develops a w
EHRSQL: A Practical Text-to-SQL Benchmark for Electronic Health Records
We present a new text-to-SQL dataset for electronic health records (EHRs). The utterances were collected from 222 hospital staff members, including physicians, nurses, and insurance review and health records teams. To construct the QA dataset on structured EHR data, we conducted a poll at a university hospital and used the responses to create seed questions. We then manually linked these questions to two open-source
Deep Learning Meets Mechanism Design: Key Results and Some Novel Applications
Mechanism design is essentially reverse engineering of games and involves inducing a game among strategic agents in a way that the induced game satisfies a set of desired properties in an equilibrium of the game. Desirable properties for a mechanism include incentive compatibility, individual rationality, welfare maximisation, revenue maximisation (or cost minimisation), fairness of allocation, etc. It is known from
In this paper, we study zeroth-order algorithms for nonconvex minimax problems with coupled linear constraints under the deterministic and stochastic settings, which have attracted wide attention in machine learning, signal processing and many other fields in recent years, e.g., adversarial attacks in resource allocation problems and network flow problems etc. We propose two single-loop algorithms, namely the zeroth-
Large Language Models are Contrastive Reasoners
Prompting methods play a crucial role in enhancing the capabilities of pre-trained large language models (LLMs). We explore how contrastive prompting (CP) significantly improves the ability of large language models to perform complex reasoning. We demonstrate that LLMs are decent contrastive reasoners by simply adding "Let's give a correct and a wrong answer." before LLMs provide answers. Experiments on v
Localized Distributional Robustness in Submodular Multi-Task Subset Selection
In this work, we treat the problem of multi-task submodular optimization from the perspective of local distributional robustness within the neighborhood of a reference distribution which assigns an importance score to each task. We initially propose to introduce a relative-entropy regularization term to the standard multi-task objective. We then demonstrate through duality that this novel formulation itself is equiva
InstructHumans: Editing Animated 3D Human Textures with Instructions
We present InstructHumans, a novel framework for instruction-driven {animatable} 3D human texture editing. Existing text-based 3D editing methods often directly apply Score Distillation Sampling (SDS). SDS, designed for generation tasks, cannot account for the defining requirement of editing -- maintaining consistency with the source avatar. This work shows that naively using SDS harms editing, as it may destroy cons
INMS: Memory Sharing for Large Language Model based Agents
While Large Language Model (LLM) based agents excel at complex tasks, their performance in open-ended scenarios is often constrained by isolated operation and reliance on static databases, missing the dynamic knowledge exchange of human dialogue. To bridge this gap, we propose the INteractive Memory Sharing (INMS) framework, an asynchronous interaction paradigm for multi-agent systems. By integrating real-time memory
Distilling Privileged Information for Dubins Traveling Salesman Problems with Neighborhoods
This paper presents a novel learning approach for Dubins Traveling Salesman Problems(DTSP) with Neighborhood (DTSPN) to quickly produce a tour of a non-holonomic vehicle passing through neighborhoods of given task points. The method involves two learning phases: initially, a model-free reinforcement learning approach leverages privileged information to distill knowledge from expert trajectories generated by the LinKe
Molecular simulations have assumed a paramount role in the fields of chemistry, biology, and material sciences, being able to capture the intricate dynamic properties of systems. Within this realm, coarse-grained (CG) techniques have emerged as invaluable tools to sample large-scale systems and reach extended timescales by simplifying system representation. However, CG approaches come with a trade-off: they sacrifice
This paper introduces EasyAnimate, an efficient and high quality video generation framework that leverages diffusion transformers to achieve high-quality video production, encompassing data processing, model training, and end-to-end inference. Despite substantial advancements achieved by video diffusion models, existing video generation models still struggles with slow generation speeds and less-than-ideal video qual
Learning to Cover: Online Learning and Optimization with Irreversible Decisions
We define an online learning and optimization problem with discrete and irreversible decisions contributing toward a coverage target. In each period, a decision-maker selects facilities to open, receives information on the success of each one, and updates a classification model to guide future decisions. The goal is to minimize facility openings under a chance constraint reflecting the coverage target, in an asymptot
Parallel Split Learning with Global Sampling
Parallel split learning (PSL) suffers from two intertwined issues: the effective batch size grows with the number of clients, and data that is not identically and independently distributed (non-IID) skews global batches. We present parallel split learning with global sampling (GPSL), a server-driven scheme that fixes the global batch size while computing per-client batch-size schedules using pooled-level proportions.
We tackle the problem of consciousness by taking the naturally selected, embodied organism as our starting point. We provide a formalism describing how biological systems such as human bodies self-organize to hierarchically interpret unlabelled sensory information according to valence. The system is attracted and repelled at different spatial and temporal scales. This is a qualitative interpretation of an unlabelled
Towards a Fairer Non-negative Matrix Factorization
There has been a recent critical need to study fairness and bias in machine learning (ML) algorithms. Since there is clearly no one-size-fits-all solution to fairness, ML methods should be developed alongside bias mitigation strategies that are practical and approachable to the practitioner. Motivated by recent work on ``fair" PCA, here we consider the more challenging method of non-negative matrix factorization
Track Anything Behind Everything: Zero-Shot Amodal Video Object Segmentation
We present Track Anything Behind Everything (TABE), a novel pipeline for zero-shot amodal video object segmentation. Unlike existing methods that require pretrained class labels, our approach uses a single query mask from the first frame where the object is visible, enabling flexible, zero-shot inference. We pose amodal segmentation as generative outpainting from modal (visible) masks using a pretrained video diffusi
Learnable Sparsity for Vision Generative Models
Diffusion models have achieved impressive advancements in various vision tasks. However, these gains often rely on increasing model size, which escalates computational complexity and memory demands, complicating deployment, raising inference costs, and causing environmental impact. While some studies have explored pruning techniques to improve the memory efficiency of diffusion models, most existing methods require e
Flatness Guided Test-Time Adaptation for Vision-Language Models
Test-time adaptation (TTA) of Vision-Language Models (VLMs) has emerged as a technique for tackling distribution shifts during the test time. Recent research indicates that the test-time adaptation is intrinsically linked to the model's training history. However, existing TTA methods, such as Test-time Prompt Tuning, often design adaptation strategies in isolation from the models' training characteristics, wh
Path Planning for Masked Diffusion Model Sampling
Any order generation of discrete data using masked diffusion models (MDMs) offers a compelling alternative to traditional autoregressive models, especially in domains that lack a natural causal ordering of data. However, current popular MDMs depart from their successful continuous diffusion model counterparts with simplified masked inference wherein unmasked tokens cannot be iteratively refined -- even if there is a
Curse of Dimensionality in Neural Network Optimization
This paper demonstrates that when a shallow neural network with a Lipschitz continuous activation function is trained using either empirical or population risk to approximate a target function that is $r$ times continuously differentiable on $[0,1]^d$, the population risk may not decay at a rate faster than $t^{-\frac{4r}{d-2r}}$, where $t$ denotes the time parameter of the gradient flow dynamics. This result highlig
Generalization Bounds for Markov Algorithms through Entropy Flow Computations
Many learning algorithms can be represented as Markov processes, and understanding their generalization error is a central topic in learning theory. For specific continuous-time noisy algorithms, a prominent analysis technique relies on information-theoretic tools and the so-called ``entropy flow'' method. This technique is compatible with a broad range of assumptions and leverages the convergence properties
Sink equilibria and the attractors of learning in games
Characterizing the limit behavior -- that is, the attractors -- of learning dynamics is one of the most fundamental open questions in game theory. In recent work on this front, it was conjectured that the attractors of the replicator dynamic are in one-to-one correspondence with the sink equilibria of the game -- the sink strongly connected components of a game's preference graph -- and it was established that th
Double Momentum and Error Feedback for Clipping with Fast Rates and Differential Privacy
Strong Differential Privacy (DP) and Optimization guarantees are two desirable properties for a method in Federated Learning (FL). However, existing algorithms do not achieve both properties at once: they either have optimal DP guarantees but rely on restrictive assumptions such as bounded gradients/bounded data heterogeneity, or they ensure strong optimization performance but lack DP guarantees. To address this gap
MedFuncta: A Unified Framework for Learning Efficient Medical Neural Fields
Research in medical imaging primarily focuses on discrete data representations that poorly scale with grid resolution and fail to capture the often continuous nature of the underlying signal. Neural Fields (NFs) offer a powerful alternative by modeling data as continuous functions. While single-instance NFs have successfully been applied in medical contexts, extending them to large-scale medical datasets remains an o
Notable events recorded on this day and month across all years.