Frontier reasoning models are produced by posttraining base language models with reinforcement learning. Recent work has challenged this by showing that sampling from a sharpened version of the base model's distribution, a so-called power distribution, elicits comparable reasoning without additional training, curated datasets, or verifiers. However, making this method practical requires efficiently sampling from the power distribution. A sampler needs to "mix" to the power distribution, which necessitates moving between modes of the target distribution; intuitively, e.g., trying different reasoning strategies. The samplers proposed in prior works repeatedly select a "cut" position in the current reasoning trace uniformly at random and resample the suffix from that position onward. However, reasoning traces typically contain a few consequential decisions (e.g., the choice of proof strategy or algorithm), and we observe that a uniformly chosen cut tends to rewrite local details rather than revisit decision points. We introduce an algorithm (Entropy-Cut Metropolis-Hastings) that uses the base model's next-token entropy as a proxy to identify key decision points and resample from those positions. We empirically verify that entropy jumps are a useful proxy for decision points and, in a stylized model of reasoning, prove that our method's mixing time scales with the number of decisions in a trace rather than with the number of tokens, which can be much larger. Across MATH500, HumanEval, GPQA Diamond, and AIME26, our method consistently improves over baselines and RL-trained models.

Welcome to our monthly digest, where you can catch up with any AIhub stories you may have missed, peruse the latest news, recap recent events, and more. This month, we learn about AI for science, delve into world models, research transparent and trustworthy AI, and hear about the lottery ticket hypothesis. The latest interview in our series with the AAAI/SIGAI Doctoral Consortium participants featured Ximing Wen who is researching transparent and trustworthy AI systems. We found out more about her work, her experience as a research intern, and what inspired her to study AI. In this wide-ranging conversation, Jonathan Frankle delves into empiricism versus theoretical proofs, how the approach to computer science has changed (even if the fundamental problems haven't), how younger researchers are rapidly adapting to a world that values impact above all else, and what it means to be a researcher.

A representation that scrambles the true degrees of freedom of the world cannot support reliable planning or compositional generalization. We prove that LeJEPA (alignment plus Gaussian regularization) linearly recovers the world's latent variables from nonlinear observations, a property known as linear identifiability, in a broad class of worlds where latents evolve under stationary, additive-noise transitions. Our main result is that among all such worlds, the Gaussian is the unique latent distribution for which this guarantee holds. The forward direction rests on a spectral decomposition in which each degree of nonlinearity is strictly penalized by alignment, making the linear map the optimum; the converse rules out every non-Gaussian alternative. We further prove an approximate identifiability result where the guarantee degrades gracefully, and show that linear, orthogonal identifiability enables optimal latent-space planning. We validate the theory with experiments ranging from 2D examples to 1024-dimensional latents, including distributional ablations and pixel-based robotic control. Our theory turns an empirically successful recipe into a mathematical guarantee, providing the foundation for building World Models that provably recover the structure of the world.

World models for partially observed environments must imagine multiple compatible hidden futures and steer between them under counterfactual actions. Joint Embedding Predictive Architectures (JEPAs) do this in latent space, but a vector-valued latent has no internal structure for carrying the belief over hidden continuations through blind rollout. We introduce the Unitary World Model JEPA (UWM-JEPA), a JEPA world model with a density-matrix latent on a joint system-environment space and a learned unitary predictor. The construction preserves the joint-state spectrum exactly during rollout, so the predictor itself cannot dissipate the represented uncertainty. On a hidden-velocity indicator task requiring five-step forward simulation under a given action sequence with the target observation masked, UWM-JEPA reaches 0.77 accuracy and degrades monotonically as actions are perturbed; a parameter-matched LSTM-JEPA trained under the same counterfactual-target objective and action head collapses to majority-class accuracy (0.53) under every action condition. Under blind rollout, UWM-JEPA loses fewer than ten points of probe R^2 at short horizons while vector-latent baselines lose forty-one and sixty-eight; both nevertheless tie on a held-out context probe, locating the separation in the predictor rather than the encoder. Action sensitivity itself requires training against counterfactual rather than teacher-forced targets, a finding that applies beyond the unitary parameterisation. For JEPA world models to imagine under partial observability, latent geometry and predictor dynamics matter, not frozen context-encoding capacity alone.

Causal discovery from multivariate time series is challenging when causal effects may occur both across time and within the same sampling interval. This issue is especially important in applications such as neuroscience, where the sampling rate may be coarse relative to the underlying dynamics and contemporaneous effects need not form an acyclic graph. We study causal discovery in linear Gaussian structural VAR models under an equal noise variance assumption, meaning that the structural noise terms have a common variance. Unlike the DAG-based cross-sectional equal noise variance setting, the time-series setting considered here does not generally yield point identification of a unique causal graph. Instead, multiple structural VAR parameterizations can induce the same stationary observed process law. We introduce a notion of observational equivalence tailored to this setting and show that the corresponding equivalence class is characterized by orthogonal transformations of the structural equations together with a global positive scale. This characterization leads to an equivalence-aware model discrepancy, the observational alignment discrepancy, which compares structural models modulo transformations that preserve the observed law. Building on this theory, we propose ENVAR, a sparsity-based procedure that searches over the induced observational equivalence class for a sparse normalized structural representative. We evaluate the proposed methodology on synthetic structural VAR data and on an fMRI dataset.

Mother's Day chaos at a steakhouse includes knives thrown at waiters and a touching mother-daughter arrest Japanese bear-fightin' robo-wolves are pure unleaded nightmare fuel but they're working Jennifer Lopez's dress holds on for dear life at her Netflix event, Trump powers through some wine & Kay Adams Eric Church's uses his guitar to deliver one of the most powerful addresses ever at UNC commencement Ella Langley crushes online troll with just four words, reminds the internet she doesn't miss Victoria's Secret should sign Rachel Pizzolato to face Sydney Sweeney in lingerie war, Reds fan is dumb & MEAT Morgan Wallen fan goes viral kicking a phone out of someone's hand as she's being escorted out in handcuffs Are teams that insist on singing'Sweet Caroline' during games the worst thing in sports? If this hasn't been said before, it should've been -- you can't hide in the bushes at a bachelorette pool party Shakira cranks up the heat with a World Cup song that has people dancing, buy Elvis' rhinestone jock & BBQ Eric Church's'six strings' commencement speech goes viral Trump reaffirms US policy on Taiwan after Xi's warning Louisiana Senate primary tests Trump's influence, redistricting battle This is the'challenge' in Trump-Xi talks, national security expert observes President Donald Trump is'getting these trade deals,' Rep. John James says'Both sides are coming out on top': Key takeaways from the Trump-Xi summit OutKick Retired Navy admiral makes bombshell claim about UFOs and'non-human intelligence' controlling them Gallaudet's military background brings extra gravity to claims about unexplained sightings in the sky and ocean May 14, 2026 - Tomi sits down with retired Rear Admiral, former Navy SEAL, and former head of NOAA, Tim Gallaudet, to pull back the curtain on the government's latest UFO and UAP data dump. Are UFOs controlled by non-human entities? There are few topics in America that generate more attention and interest than UFOs/UAPs. One of the big reasons why is that there's no clear answer for what is going on up in the sky or down in the ocean.

The 10th International Workshop on Health Intelligence (W3PHIAI-26) celebrated a decade of bringing AI and health research together, building on a lineage that began with the AAAI-W3PHI workshops focused on population health (2014-2016), the AAAI-HIAI workshops focused on personalized health (2013-2016), and the subsequent joint W3PHIAI workshops held annually from 2017 through 2025. Over this decade, the series has produced hundreds of talks and high-impact publications that have collectively received thousands of citations, shaping the research agenda in both population health intelligence and personalized healthcare AI. This year's special theme, "Foundation Models and AI Agents," reflected the field's rapidly evolving frontier: the emergence of autonomous and semi-autonomous AI systems reshaping clinical workflows, patient management, health system operations, and public health surveillance. Day 1 of the workshop focused on medical imaging and the translation of AI for clinical ...

Join a subscriber-only discussion live on Thursday, May 21. A woman's uterus has been kept alive outside the body for the first time Jessica Hamzelou Want to understand the current state of AI? Check out these charts. A woman's uterus has been kept alive outside the body for the first time The team behind the feat plan to study uterine disorders and the early stages of pregnancy--and potentially grow a human fetus. Want to understand the current state of AI? Check out these charts. According to Stanford's 2026 AI Index, AI is sprinting, and we're struggling to keep up. The ultimate plan to live forever is a brand new body.

Ahead of the hit show's finale, cocreators Paul W. Downs and Lucia Aniello talk about media consolidation, the perils of censorship, and why they find AI "deeply disturbing." If you're a WIRED reader who uses AI in any creative context, I'd suggest staying far, far away from anyone involved in the TV show . In an interview earlier this year, actor Hannah Einbinder (who plays young comedy writer Ava Daniels on the show) described AI creators as "losers," "not artists," and "not special." In a wide-ranging conversation for ahead of the series finale on HBO Max, Paul W. Downs and Lucia Aniello were resolute about the value of human creativity--and what can be lost when AI enters the picture. If their work on is any indication, Downs and Aniello (along with their third cocreator, Jen Statsky) would be wise to stick with the tough, tiring, absolutely-no-shortcuts approach they take to making entertainment. Across five excellent seasons--if you haven't seen the show, I really do recommend it-- has been praised for its sharp writing and wit, and its thoughtful portrayal of Deborah Vance and Ava's complex, constantly evolving relationship. The show has also acted as something of a mirror for the real-world entertainment industry, weaving in plotlines that tackle everything from media consolidation to corporate censorship to, yes, artificial intelligence. The show's cast and creators have been on a media whirlwind as it all comes to an end. When they came knocking on WIRED's door, we jumped at the chance to chat, and I was lucky enough to spend an hour with Downs and Aniello--both WIRED subscribers, much to my delight--earlier this month. KATIE DRUMMOND: Lucia Aniello and Paul Downs, who I just learned are married, congratulations and welcome to . You should have been there. You should have been there. Ugh, why didn't we bring you? We are going to renew for our 10-year at the same place though. Lucia was born in Italy, so it was closer to a lot of family. And you were married in what year? You have time to find your look. A major priority for me in my life is perfecting my look. We do work at Condé Nast, and my boss is Anna Wintour.

Colloquially, OCD is known as the doubting disorder. In his new book, Simone Stolzoff explores whether treating that uncertainty with magic mushrooms can help people through it. Adam Strauss is standing in his New York City apartment, holding the limp cord of his headphones, trying to choose between the two MP3 players on his desk: the iPod and the iRiver, its Korean counterpart. He tries different songs, different genres, different instruments. The iRiver tends to sound better overall, but the iPod offers a little more nuance in the midrange. The iPod has a better battery life, but the iRiver still lasts eight hours-- longer than he's ever continuously listened to music. Then again, he's never owned an MP3 player. He goes back and forth, back and forth, testing vocal ranges, button resistance, interface aesthetics. It would be one thing if it were just Adam's decision of which MP3 player to buy. After all, it was 2003, the height of the personal audio device revolution, and Adam was a 29-year-old audiophile. For Adam, it was also other decisions-- what shirt to wear to work, what to order for lunch, even what side of the street to walk down. At one point, in an effort to simplify his decisionmaking process for what to wear, Adam bought 11 identical blue button-down shirts. But he quickly found variations in each shirt's fit and fading. He believed there was a shirt to pick; each morning he would spend 20, 30, then 45 minutes trying to find it. If he could only determine which shirt was best, he could control his fate.