Record 15102026 · captured 2026-10-16
The world looked up Katie Zacharia. 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.
Kate Sharon Zacharia is an American political commentator who has served as the White House press secretary since October 2026.
Roy Frank "RJ" Mitte III was an American actor and disability rights activist. Born in Jackson, Mississippi, Mitte was diagnosed with cerebral palsy when he was three years old. He moved to Los Angeles in 2006 and worked with a personal talent manager to find
Mathematics is a field of knowledge concerned with abstract concepts such as numbers, geometric shapes, sets, functions, and probabilities. It uses logical reasoning and proof to study and establish their properties, often expressed as theorems, formulas, and
This is a list of equations, indicating each Wikipedia page under appropriate bands of their field.
Kimberly Ann Guilfoyle is an American media personality and politician who served as the United States ambassador to Greece from 2025 until her resignation in 2026. She previously served as an advisor and led the fundraising division of the Donald Trump 2020 p
VisionQuest is an American television miniseries created by Terry Matalas for the streaming service Disney+, based on Marvel Comics featuring the character Vision. A spin-off from the miniseries WandaVision (2021), it is the 18th television series in the Marve
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
Dancing with the Stars (American TV series) season 35
Season thirty-five of Dancing with the Stars premiered on ABC and Disney+ on September 15, 2026, and is scheduled to conclude on November 24, 2026. This season was the fourth to air live on both networks simultaneously. Season nineteen champion Alfonso Ribeiro
Carrie is an American supernatural horror television miniseries developed by Mike Flanagan, and produced by Amazon MGM Studios for Amazon Prime Video. The first series adaptation of the eponymous franchise, it is based on the 1974 novel by Stephen King, and is
Selma Blair is an American actress. She is known for her roles in Cruel Intentions, Legally Blonde, The Sweetest Thing, and the Hellboy franchise.
Karoline Claire Leavitt is an American political spokesperson who served as the 36th White House press secretary from January 2025 to August 2026. A member of the Republican Party, she was the party's nominee in the 2022 election for New Hampshire's 1st congre
Below is a 2026 Canadian thriller miniseries created by Jesse McKeown and starring Josh Hartnett, Mackenzie Davis, and Charlie Heaton. It premiered on Netflix on October 8, 2026. The series received generally positive reviews from critics.
Ilhan Abdullahi Omar is an American politician serving as the U.S. representative for Minnesota's 5th congressional district since 2019. The district includes all of Minneapolis and some of its first-ring suburbs. From 2017 to 2019, Omar served in the Minnesot
Christopher Michael Coke, also known as Dudus, is a convicted Jamaican drug lord and the leader of the Shower Posse, a violent drug gang started by his father Lester Coke in Jamaica, which exported "large quantities" of marijuana and cocaine into the United St
Parliaments and legislative bodies around the world impose certain rules and standards during debates. Tradition has evolved that there are words or phrases that are deemed inappropriate for use in the legislature whilst it is in session. In a Westminster syst
Nidal Malik Hasan is an American mass murderer and physician, who previously served as a United States Army major and perpetrated the 2009 Fort Hood shooting, in which he killed 13 soldiers and injured 32 others.
Narnia: The Magician's Nephew is an upcoming high fantasy film written for the screen, directed, and co-produced by Greta Gerwig, based on the 1955 novel The Magician's Nephew, the sixth published and first chronological novel in the children's book series The
Limonene is a slightly yellow-green liquid aliphatic hydrocarbon classified as a cyclic monoterpene, and is the major component in the fragrance and essential oil of citrus fruit peels, taking its name from Italian limone 'lemon'.
Pope Leo XIV is the head of the Catholic Church and sovereign of Vatican City.
Russell Edward Brand is an English comedian, actor, podcaster, and media personality. He was initially a stand-up comedian and radio and television presenter in the UK, where he rose to prominence as the host of Big Brother's Big Mouth, a spin-off of the reali
Neatsville is an unincorporated community in Adair County, located 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
Josie Totah, formerly known as J. J. Totah, is an American actress. She is known for her recurring role on the Disney Channel series Jessie and a supporting role on the 2013 ABC comedy series Back in the Game. She received praise from critics for her role in t
The Magician's Nephew is a portal fantasy novel by British author C. S. Lewis, published in 1955 by The Bodley Head. It is the sixth published of seven novels in The Chronicles of Narnia (1950–1956). In recent editions, which sequence the books in the chronolo
Digger is a 2026 American satirical black comedy film directed, co-written, and co-produced by Alejandro González Iñárritu. Tom Cruise, who also produced the film, stars as Digger Rockwell, an aging oil magnate whose drilling sets off an ecological disaster. T
Drishyam: The Conclusion is a 2026 Indian Hindi-language crime thriller film co-written, produced, and directed by Abhishek Pathak. Produced by Panorama Studios and Star Studio18, it is a sequel to Drishyam 2 (2022). Unlike its predecessors, the film features
Lizzie Andrew Borden was an American woman who was tried and acquitted of the murders of her father and stepmother in Fall River, Massachusetts. No other individuals were charged with the murders.
Christa Gail Pike is an American convicted murderer on death row in Tennessee. In 1995, when she was 18, Pike and her boyfriend lured their 19-year-old classmate Colleen Slemmer into a wooded area in Knoxville where they tortured and killed her. Slemmer was be
Wikipedia is a free online encyclopedia written and maintained by a community of volunteer editors, known as Wikipedians, through open collaboration and the wiki software MediaWiki. Founded by Jimmy Wales and Larry Sanger in 2001, Wikipedia has been hosted sin
Street Fighter is a 2026 martial arts comedy film directed by Kitao Sakurai and written by Sakurai and T. J. Fixman, with a story by Dalan Musson and Gary Dauberman. It is the third live-action feature-length film based on the Street Fighter video game series
East of Eden (2026 miniseries)
East of Eden is a 2026 American historical drama television limited series created by Zoe Kazan, starring Florence Pugh. It is adapted from the 1952 novel by John Steinbeck and premiered on Netflix on October 1, 2026. It received generally positive reviews fro
What the people building things argued about, from Hacker News.
Papers submitted to arXiv cs.AI that day.
LIBERO-PeRM: Benchmarking Personalized Robotic Manipulation
Personalization is essential for general-purpose robots to transition into household environments and achieve true practicality. While general robotic manipulation has been extensively studied, personalized robotic manipulation (PeRM) lacks a controlled benchmark for separating task completion from preference satisfaction. We introduce LIBERO-PeRM, a benchmark for preference learning in embodied agents. LIBERO-PeRM s
Discovering state-of-the-art quantum circuits with large language models
Significant efforts are currently being directed toward the implementation of large-scale quantum information processors, but realizing useful quantum advantage also requires the development of efficient quantum algorithms. While for many practical problems the dominant resource costs are associated with a small set of computational primitives, optimizing them in the quantum setting presents unique challenges, includ
T2-z: Test-Time Optimization of Environment Latents for Robotic World Models
Predicting how the world responds to an action requires more than what can be seen: robots must account for environmental factors that are neither directly observable nor explicitly specified, from physical properties such as friction and mass to human-defined environmental rules. We introduce T2-Z for test-time optimization of environment latents, which augments a robotic world model with a learnable environment lat
CoDA: Co-Evolution of Data Engines and Action Policies
Generative simulation can automate robot environment construction, but physically valid environments are not necessarily useful for training. The challenge is to identify environments that address a policy's failures and supervision that helps it overcome them. We introduce CoDA, a framework in which a simulation data engine and an action policy co-evolve through a shared heterogeneous memory of environment construct
Rethinking Routing Exploration in Modern Mixture-of-Experts
Mixture-of-experts (MoE) models have become an important approach for scaling model parameters. Modern MoE architectures increasingly combine two design choices: fine-grained expert segmentation and shared experts. The former increases expressiveness by enabling more expert combinations at a fixed activation ratio, and the latter introduces experts that are active for every token. We identify an exploration dilemma b
FDE-Gym: The Last Mile of AI Delivery
Existing agent benchmarks typically evaluate agents on well-specified tasks defined by issue reports, specifications, or task tickets. Real-world customer delivery is different: forward-deployed engineers (FDEs) must clarify ambiguous requirements, work in live systems, and uncover unstated constraints. We introduce FDE-Gym, a benchmark of 95 end-to-end delivery tasks from 20 customer scenarios across 18 sectors, eac
MLExpert: Towards a Generalist Agentic Model for Autonomous Machine Learning Engineering
Large language models (LLMs) are expanding from assisting scientific research and engineering to autonomously developing and improving AI systems, advancing AI for AI (AI4AI) as a pathway toward recursive self-improvement (RSI). Workflow-driven machine learning engineering (MLE) systems provide a practical path toward this pursuit through complex orchestration that manages long-horizon experimentation, while recent M
GeoState: Learning View-Decoupled Geometry States for 3D World Modeling
Recent 3D world models increasingly use features from geometry foundation models (GFMs) as predictive world states, benefiting from their rich geometric priors. However, the view dependence of these features entangles scene dynamics with camera-induced variation, making the resulting state evolution harder to predict. We propose GeoState, a view-decoupled geometry representation for predictive 3D world modeling that
3DCodeVerse: Exploring 3D Worlds as Code
We introduce 3DCodeVerse, a research ecosystem that enables coding agents to create editable and verifiable 3D content at scale. 3DCodeVerse comprises large-scale, high-quality datasets of executable 3D code, a coding harness for spatial reasoning and automated verification, and practical guidance for 3D coding. First, we construct 3DCodeVerse-2M, a large-scale curated dataset of standalone 3D executable code. We bui
Dexterity from Supervised Play
How can robots autonomously collect the contact-rich experience needed to learn dexterous manipulation? We present DSP: Dexterity from supervised play, a framework in which a robot learns a play policy from minutes of human play through behavior cloning, then deploys it autonomously to collect hours of interaction data to train a world model. During inference, the same play policy then guides model-predictive control
Evaluation Awareness Beyond English: Do LLMs Act Differently When Tested in Indic Languages?
Large language models (LLMs) can often tell when they are being tested. This ability, known as evaluation awareness, can lead models to act more cautiously during safety evaluations than in real use. Existing work has studied evaluation awareness almost entirely in English, although models serve users in many languages. Indic languages are spoken by over a billion people, yet evaluation awareness remains almost entir
KnowGPO: Knowledge-Grouped Policy Optimization for Search Agents
Deep search agents solve knowledge-intensive tasks through long-horizon, multi-turn interactions, where assigning credit to individual search decisions is fundamentally difficult. Outcome-based reinforcement learning provides only a single terminal reward shared across an entire trajectory. Recent process-supervision methods aim to assign credit at finer granularity, but they typically anchor credit to either surface
Designing Transformers for Continuous Diffusion Language Models
Continuous diffusion language models (CDLMs) offer an alternative approach to parallel language generation; however, most existing studies directly use transformer architectures from either causal large language models (LLMs) or Diffusion Transformers (DiTs) for image generation, which were not optimized for CDLMs. In this paper, we conduct a systematic study on Transformer architectures for CDLMs and introduce Langu
ACEdit: Stable Multi-Turn Image Editing via Asymmetric Conditioning
Image editing models produce impressive results for individual edits, but their quality often deteriorates over multiple editing turns. Each editing turn introduces small distribution shifts that accumulate over successive edits, creating a gap between the input distributions encountered during the editor's original training and multi-turn inference. We introduce a training scheme that makes multi-turn image editing
Twice Upon a Time: Complementary Representations for Time-Series Reasoning
Time Series Language Models (TSLMs) enable language-based understanding and reasoning over temporal data, yet a fundamental question remains: what information should their time-series representations preserve, and what variation should they factor out? Existing TSLMs typically expose the language model to a single representation, imposing a fixed inductive bias across downstream tasks. We instead introduce complement
Learning Self-Orchestration in Decentralized Agent Swarms
The capabilities of an agent swarm depend on both its individual members and how they coordinate. Yet existing multi-agent systems often train agents within fixed orchestration structures, separating the learning of individual capabilities from the organization of collective behavior. We introduce market-based post-training (MPT), a framework for jointly learning action policies and self-orchestration in decentralize
AVC-Reward: Event-Centric Audio-Video Consistency Evaluation
As joint audio-video generation models become more capable, they can generate audio-visual scenes exhibiting three forms of complexity: multi-event composition, multi-layer audio mixture, and asymmetric cross-modal relations. However, current evaluations largely reuse metrics from earlier simple and unidirectional tasks. They typically evaluate an audio-video clip as a whole and rely on simple predefined relations, m
A team of Gemini 4 Argon agents beats Minecraft
We placed four Gemini 4 Argon agents in a sandboxed Minecraft survival world and gave them one goal: defeat the Ender Dragon. Each agent controlled a player via an open-source library called Mineflayer and coordinated with its teammates through in-game chat and shared memory. No one assigned roles or wrote game logic. The agents planned, wrote, and debugged every program themselves. Researchers could watch the run on
Learning to Steer LLM Agents and Multi-Agent Systems
Large language model (LLM)-based agents and multi-agent systems increasingly tackle complex tasks through long-horizon tool use and inter-agent collaboration. However, these systems are prone to deviating from the overall goal as execution unfolds, which wastes execution resources and leads to undesired outcomes, a failure termed goal drift. In this work, we propose a steering agent that supervises execution on the f
Knowledge That Is Linear Before Fine-Tuning Generalizes After It
Not all facts a language model can recall support further learning equally well. We distinguish active facts, which support generalization beyond their own recall, from inert facts, which can be recalled but do not support such generalization in a given task. We study this distinction by constructing new relations from existing ones. Take the relation that maps a place to its continent (Paris -> Europe) and assign
AI Consilium: a Benchmark of LLM Clinical Multidisciplinary Second Opinions
Large language models (LLMs) can generate differential diagnoses for complex cases, but a useful second opinion must also be factually grounded, clinically coherent, actionable, and safe. We developed a multidimensional benchmark using 300 diagnostically resolved NEJM--MedQA cases: 110 for physician reference ratings and Judge calibration and 190 for held-out evaluation. Eight single-model pipelines generated indepen
Private Retrieval Augmented Generation via Random Projection
Retrieval-Augmented Generation (RAG) enhances the capabilities of large language models (LLMs) by querying external structured knowledge. However, it can also introduce privacy risks by leaking sensitive information from the retrieval datastore. We propose a simple method to preserve datastore privacy in RAG systems via random projection. By applying the same projection to both datastore embeddings and query embeddin
Towards Continual Learning: Mitigating Forgetting With Subspace Tuning
Large language models (LLMs) acquire new skills through fine-tuning, but it can destroy capabilities they already have: catastrophic forgetting remains a central obstacle to continual learning in LLMs. Recent works connect forgetting to how far, and along which directions, fine-tuning moves the weights. On-policy methods such as reinforcement learning and on-policy distillation avoid updating the principal singular d
EliteReplay: Preserving Diverse Solutions in RL Post-Training via Quality-Diversity Search
Reinforcement learning has become a common post-training technique to improve the accuracy of LLMs on verifiable tasks. However, such training can narrow the set of solutions the model can produce. Several approaches have attempted to address this behavior-sharpening effect, but they often optimize metrics that do not reflect the diversity of correct solutions. Ideally, we want a model that can produce multiple good
Improving Environment-Agnostic Coding Agents: The Role of Scaffolding
Stronger language models may increasingly construct useful procedures for themselves, reducing the advantage of developer-supplied scaffolding. We investigate why this advantage persists and whether an environment-agnostic agent can be improved without environment-specific engineering. We evaluate a Codex-based agent in two nearly identical prompt variants on ARC-AGI-3, AGI Maze, and Terminal-Bench. Each variant is d
Origins publishing files written for machines rather than people. Measured against a frozen cohort, so a change in the number means a change in adoption.
| Signal | Web head Tranco top 1,000 n=1,000 | Web tail sampled to rank 100k n=1,000 | AI-native model & dev platforms n=110 |
|---|---|---|---|
| Any agent-facing signal | 12.9% (129) | 6.2% (62) | 73.64% (81) |
| llms.txt (apex domain) | 10.5% (105) | 5.2% (52) | 60% (66) |
| llms.txt (docs subdomain) | 4.2% (42) | 1.1% (11) | 46.36% (51) |
| .well-known/mcp.json | 0.6% (6) | 0.3% (3) | 9.09% (10) |
| .well-known/agents.txt | 0.3% (3) | 0.2% (2) | 0% (0) |
| ai.txt | 0.3% (3) | 0.1% (1) | 0% (0) |
| ai-plugin.json (deprecated) | 0.7% (7) | 0.3% (3) | 0.91% (1) |
Notable events recorded on this day and month across all years.