We introduce Variational Joint Embedding (VJE), a framework that synthesizes joint embedding and variational inference to enable self-supervised learning of probabilistic representations in a reconstruction-free, non-contrastive setting. Compared to energy-based predictive objectives that optimize pointwise discrepancies, VJE maximizes a symmetric conditional evidence lower bound (ELBO) for a latent-variable model defined directly on encoder embeddings. We instantiate the conditional likelihood with a heavy-tailed Student-$t$ model using a polar decomposition that explicitly decouples directional and radial factors to prevent norm-induced instabilities during training. VJE employs an amortized inference network to parameterize a diagonal Gaussian variational posterior whose feature-wise variances are shared with the likelihood scale to capture anisotropic uncertainty without auxiliary projection heads. Across ImageNet-1K, CIFAR-10/100, and STL-10, VJE achieves performance comparable to standard non-contrastive baselines under linear and k-NN evaluation. We further validate these probabilistic semantics through one-class CIFAR-10 anomaly detection, where likelihood-based scoring under the proposed model outperforms comparable self-supervised baselines.

Effective reinforcement learning (RL) for complex stochastic systems requires leveraging historical data collected in previous iterations to accelerate policy optimization. Classical experience replay treats all past observations uniformly and fails to account for their varying contributions to learning. To overcome this limitation, we propose Variance Reduction Experience Replay (VRER), a principled framework that selectively reuses informative samples to reduce variance in policy gradient estimation. VRER is algorithm-agnostic and integrates seamlessly with existing policy optimization methods, forming the basis of our sample-efficient off-policy algorithm, Policy Gradient with VRER (PG-VRER). Motivated by the lack of rigorous theoretical analysis of experience replay, we develop a novel framework that explicitly captures dependencies introduced by Markovian dynamics and behavior-policy interactions. Using this framework, we establish finite-time convergence guarantees for PG-VRER and reveal a fundamental bias-variance trade-off: reusing older experience increases bias but simultaneously reduces gradient variance. Extensive empirical experiments demonstrate that VRER consistently accelerates policy learning and improves performance over state-of-the-art policy optimization algorithms.

Neural scaling laws relate loss to model size in large language models (LLMs), yet depth and width may contribute to performance differently, requiring more detailed studies. Here, we quantify how depth affects loss via analysis of LLMs and toy residual networks. We find loss scales inversely proportional to depth in LLMs, probably due to functionally similar layers reducing error through ensemble averaging rather than compositional learning or discretizing smooth dynamics. This regime is inefficient yet robust and may arise from the architectural bias of residual networks and target functions incompatible with smooth dynamics. The findings suggest that improving LLM efficiency may require architectural innovations to encourage compositional use of depth.

Controlling the false discovery rate (FDR) in high-dimensional variable selection requires balancing rigorous error control with statistical power. Existing methods with provable guarantees are often overly conservative, creating a persistent gap between the realized false discovery proportion (FDP) and the target FDR level. We introduce a learning-augmented enhancement of the T-Rex Selector framework that narrows this gap. Our approach replaces the analytical FDP estimator with a neural network trained solely on diverse synthetic datasets, enabling a substantially tighter and more accurate approximation of the FDP. This refinement allows the procedure to operate much closer to the desired FDR level, thereby increasing discovery power while maintaining effective approximate control. Through extensive simulations and a challenging synthetic genome-wide association study (GWAS), we demonstrate that our method achieves superior detection of true variables compared to existing approaches.

Membership Inference Attacks (MIAs) are widely used to quantify training data memorization and assess privacy risks. Standard evaluation requires repeated retraining, which is computationally costly for large models. One-run methods (single training with randomized data inclusion) and zero-run methods (post hoc evaluation) are often used instead, though their statistical validity remains unclear. To address this gap, we frame MIA evaluation as a causal inference problem, defining memorization as the causal effect of including a data point in the training set. This novel formulation reveals and formalizes key sources of bias in existing protocols: one-run methods suffer from interference between jointly included points, while zero-run evaluations popular for LLMs are confounded by non-random membership assignment. We derive causal analogues of standard MIA metrics and propose practical estimators for multi-run, one-run, and zero-run regimes with non-asymptotic consistency guarantees. Experiments on real-world data show that our approach enables reliable memorization measurement even when retraining is impractical and under distribution shift, providing a principled foundation for privacy evaluation in modern AI systems.

Things to Do in L.A. Tap to enable a layout that focuses on the article. Man who videotaped himself BASE jumping in Yosemite arrested, federal officials say. This is read by an automated voice. Please report any issues or inconsistencies here . A California man faces a federal charge for allegedly BASE jumping off Glacier Point in Yosemite National Park during last year's government shutdown.

Founders used to be wedded to their companies. Now, anyone can be lured away for the right price. Since the middle of last year, there have been at least three major AI "acqui-hires" in Silicon Valley. Meta invested more than $14 billion in Scale AI and brought on its CEO, Alexandr Wang; Google spent a cool $2.4 billion to license Windsurf's technology and fold its cofounders and research teams into DeepMind; and Nvidia wagered $20 billion on Groq's inference technology and hired its CEO and other staffers. The frontier AI labs, meanwhile, have been playing a high stakes and seemingly never-ending game of talent musical chairs.

X's latest Community Notes experiment allows AI to write the first draft The platform is testing collaborative notes. X wants community notes writers to collaborate with AI. (X Corp.) X is experimenting with a new way for AI to write Community Notes. The company is testing a new collaborative notes feature that allows human writers to request an AI-written Community Note. It's not the first time the platform has experimented with AI in Community Notes. The company started a pilot program last year to allow developers to create dedicated AI note writers.

ICE and CBP's Face-Recognition App Can't Actually Verify Who People Are ICE has used Mobile Fortify to identify immigrants and citizens alike over 100,000 times, by one estimate. It wasn't built to work like that--and only got approved after DHS abandoned its own privacy rules. The face-recognition app Mobile Fortify, now used by United States immigration agents in towns and cities across the US, is not designed to reliably identify people in the streets and was deployed without the scrutiny that has historically governed the rollout of technologies that impact people's privacy, according to records reviewed by WIRED. The Department of Homeland Security launched Mobile Fortify in the spring of 2025 to "determine or verify" the identities of individuals stopped or detained by DHS officers during federal operations, records show. DHS explicitly linked the rollout to an executive order, signed by President Donald Trump on his first day in office, which called for a "total and efficient" crackdown on undocumented immigrants through the use of expedited removals, expanded detention, and funding pressure on states, among other tactics. Despite DHS repeatedly framing Mobile Fortify as a tool for identifying people through facial recognition, however, the app does not actually "verify" the identities of people stopped by federal immigration agents--a well-known limitation of the technology and a function of how Mobile Fortify is designed and used.

Having won only one of their past six Premier League games and drawn 2-2 at Tottenham after being 2-0 up, can second-placed Manchester City get back on track at Liverpool on Sunday? I wouldn't rule City out of anything at the moment said BBC Sport football expert Chris Sutton. But the way they folded in the second half against Tottenham was a real worry. Sutton is making predictions for all 380 Premier League games this season, against AI, BBC Sport readers and a variety of guests. His guest for week 25 is Gladiators star Apollo, real name Alex Gray, who supports Newcastle . Before becoming a Gladiator, the 6ft 6in Gray played Premiership rugby for three teams and also American Football for NFL side Atlanta Falcons.