The effect of regularizers such as weight decay when training deep neural networks is not well understood. We study the influence of weight decay as well as $L2$-regularization when training neural network models in which parameter matrices interact multiplicatively. This combination is of particular interest as this parametrization is common in attention layers, the workhorse of transformers. Here, key-query, as well as value-projection parameter matrices, are multiplied directly with each other: $W_K^TW_Q$ and $PW_V$. We extend previous results and show on one hand that any local minimum of a $L2$-regularized loss of the form $L(AB^\top) + \lambda (\|A\|^2 + \|B\|^2)$ coincides with a minimum of the nuclear norm-regularized loss $L(AB^\top) + \lambda\|AB^\top\|_*$, and on the other hand that the 2 losses become identical exponentially quickly during training. We thus complement existing works linking $L2$-regularization with low-rank regularization, and in particular, explain why such regularization on the matrix product affects early stages of training.Based on these theoretical insights, we verify empirically that the key-query and value-projection matrix products $W_K^TW_Q, PW_V$ within attention layers, when optimized with weight decay, as usually done in vision tasks and language modelling, indeed induce a significant reduction in the rank of $W_K^TW_Q$ and $PW_V$, even in fully online training.We find that, in accordance with existing work, inducing low rank in attention matrix products can damage language model performance, and observe advantages when decoupling weight decay in attention layers from the rest of the parameters.

Restless multi-armed bandits (RMAB) have demonstrated success in optimizing resource allocation for large beneficiary populations in public health settings. Unfortunately, RMAB models lack flexibility to adapt to evolving public health policy priorities. Concurrently, Large Language Models (LLMs) have emerged as adept automated planners across domains of robotic control and navigation. In this paper, we propose a Decision Language Model (DLM) for RMABs, enabling dynamic fine-tuning of RMAB policies in public health settings using human-language commands. We propose using LLMs as automated planners to (1) interpret human policy preference prompts, (2) propose reward functions as code for a multi-agent RMAB environment, and (3) iterate on the generated reward functions using feedback from grounded RMAB simulations. We illustrate the application of DLM in collaboration with ARMMAN, an India-based non-profit promoting preventative care for pregnant mothers, that currently relies on RMAB policies to optimally allocate health worker calls to low-resource populations. We conduct a technology demonstration in simulation using the Gemini Pro model, showing DLM can dynamically shape policy outcomes using only human prompts as input.

Watermarking generative content serves as a vital tool for authentication, ownership protection, and mitigation of potential misuse. Existing watermarking methods face the challenge of balancing robustness and concealment. They empirically inject a watermark that is both invisible and robust and passively achieve concealment by limiting the strength of the watermark, thus reducing the robustness. In this paper, we propose to explicitly introduce a watermark hiding process to actively achieve concealment, thus allowing the embedding of stronger watermarks. To be specific, we implant a robust watermark in an intermediate diffusion state and then guide the model to hide the watermark in the final generated image. We employ an adversarial optimization algorithm to produce the optimal hiding prompt guiding signal for each watermark. The prompt embedding is optimized to minimize artifacts in the generated image, while the watermark is optimized to achieve maximum strength. The watermark can be verified by reversing the generation process. Experiments on various diffusion models demonstrate the watermark remains verifiable even under significant image tampering and shows superior invisibility compared to other state-of-the-art robust watermarking methods.

Existing promptable segmentation methods in the medical imaging field primarily consider either textual or visual prompts to segment relevant objects, yet they often fall short when addressing anomalies in medical images, like tumors, which may vary greatly in shape, size, and appearance. Recognizing the complexity of medical scenarios and the limitations of textual or visual prompts, we propose a novel dual-prompt schema that leverages the complementary strengths of visual and textual prompts for segmenting various organs and tumors. Specifically, we introduce $\textbf{\textit{CAT}}$, an innovative model that $\textbf{C}$oordinates $\textbf{A}$natomical prompts derived from 3D cropped images with $\textbf{T}$extual prompts enriched by medical domain knowledge. The model architecture adopts a general query-based design, where prompt queries facilitate segmentation queries for mask prediction. To synergize two types of prompts within a unified framework, we implement a ShareRefiner, which refines both segmentation and prompt queries while disentangling the two types of prompts. Trained on a consortium of 10 public CT datasets, $\textbf{\textit{CAT}}$ demonstrates superior performance in multiple segmentation tasks. Further validation on a specialized in-house dataset reveals the remarkable capacity of segmenting tumors across multiple cancer stages. This approach confirms that coordinating multimodal prompts is a promising avenue for addressing complex scenarios in the medical domain.

Nvidia CEO Jensen Huang defends DLSS 5 against user backlash, calling critics "completely wrong" about the generative AI graphics technology's function. PCWorld notes the controversy stems from concerns that DLSS 5 applies an "AI skin" over game models rather than true enhancement. Huang clarifies DLSS 5 offers developers controllability at the geometry level, describing it as real-time neural rendering that infuses photorealism into pixels. In just a day, Nvidia's DLSS 5 technology has become the hot button for most of the PC and gaming world. Now Nvidia's chief executive has weighed in, claiming that everyone is "completely wrong" about the technology. At a question-and-answer session at Nvidia's own Game Technology Conference, Nvidia chief executive Jensen Huang said that "as I have explained very carefully, DLSS 5 fuses controllability of the of geometry and textures and everything about the game with generative AI," he said. Huang went on to say of the controversy: "They're completely wrong." Nvidia's DLSS 5 has sparked controversy because it essentially applies a generative AI filter to computer graphics. Nvidia describes DLSS 5 as a "real-time neural rendering model that infuses pixels with photoreal lighting and materials," and a "GPT moment for graphics -- blending hand-crafted rendering with generative AI".

Solar power is a critical source of renewable energy, offering significant potential to lower greenhouse gas emissions and mitigate climate change. However, the cloud induced-variability of solar radiation reaching the earth's surface presents a challenge for integrating solar power into the grid (e.g., storage and backup management). The new generation of geostationary satellites such as GOES-16 has become an important data source for large-scale and high temporal frequency solar radiation forecasting. However, no machine-learning-ready dataset has integrated geostationary satellite data with fine-grained solar radiation information to support forecasting model development and benchmarking with consistent metrics.

Goal-directed planning presents a challenge for classical RL algorithms due to the vastness of the combinatorial state and goal spaces, while humans and animals adapt to complex environments, especially with diverse, non-stationary objectives, often employing intermediate goals for long-horizon tasks.Here, we propose a goal reduction mechanism for effectively deriving subgoals from arbitrary and distant original goals, using a novel loop-removal technique.The product of the method, called goal-reducer, distills high-quality subgoals from a replay buffer, all without the need for prior global environmental knowledge.Simulations show that the goal-reducer can be integrated into RL frameworks like Deep Q-learning and Soft Actor-Critic.It accelerates performance in both discrete and continuous action space tasks, such as grid world navigation and robotic arm manipulation, relative to the corresponding standard RL models.Moreover, the goal-reducer, when combined with a local policy, without iterative training, outperforms its integrated deep RL counterparts in solving a navigation task.This goal reduction mechanism also models human problem-solving.Comparing the model's performance and activation with human behavior and fMRI data in a treasure hunting task, we found matching representational patterns between an goal-reducer agent's components and corresponding human brain areas, particularly the vmPFC and basal ganglia. The results suggest that humans may use a similar computational framework for goal-directed behaviors.

Yellowstone, Yosemite, and Grand Canyon all make the list, but aren't number one. Yosemite National Park came in at number five on the National Parks Service list. Breakthroughs, discoveries, and DIY tips sent six days a week. In 2025, the parks received 323 million recreation visits, according to new data release by the National Parks Service. The data includes visitors to National Parks, National Historic Sites, National Memorials, National Seashores, National Parkways, and other designated public lands.

Support journalism that doesn't flinch . Support journalism that doesn't flinch . Elon Musk leaves a meeting with House Republicans in the basement of the US Capitol building on March 5, 2025 in Washington, DC. Get your news from a source that's not owned and controlled by oligarchs. Tennessee teenagers are suing Elon Musk's company xAI over allegations that its artificial intelligence tool Grok undressed photos of them as minors--the latest challenge against the wealthiest living person's chatbot .

After the rise (and fall) of reservation scalping, DoorDash and a host of apps are fighting to book you a seat at the country's most exclusive restaurants. At The Eighty-Six in Manhattan, exclusivity is the point. The luxe, 11-table steakhouse is the sort of place that lavishes caviar and aged mimolette cheese on its potatoes, and crows that your market-price duck was raised by one Dr. Taylor Swift has reportedly dined there in a Miu Miu skirt. Reservations are a scarce commodity that the restaurant, and New York law forbids you from selling one. "Access is the main asset," wrote food writer Helen Rosner in a recent New Yorker review of The Eighty-Six. "The product is the door, and what a door!