In practice, many models from a function class can fit a dataset almost equally well. This collection of near-optimal models is known as the Rashomon set. Prior work has shown that the Rashomon set offers flexibility in choosing models aligned with secondary objectives like interpretability or fairness. However, it is unclear how far this flexibility extends to different trustworthy criteria, especially given that most trustworthy machine learning systems today still rely on complex specialized optimization procedures. Is the Rashomon set all you need for trustworthy model selection?

President Trump probably can't get rid of her yet, but FCC commissioner Anna Gomez still checks her email every day to see if he has. Until then, she wants to stand up for the First Amendment. If you've given much thought to the Federal Communications Commission in recent years, it probably had something to do with Brendan Carr . The group's chairman since 2025, Carr has been on an ongoing, public rampage against freedom of speech: he's gone after late-night hosts like Jimmy Kimmel, threatened to revoke broadcast licenses over Iran war coverage, and targeted networks for their DEI policies. Disturbing as Carr's rhetoric and actions have been, he does count at least one opponent within the agency: Commissioner Anna Gomez, currently the lone Democrat among three FCC commissioners, has been vocal about the damage she thinks the agency is doing to American press freedom--and has repeatedly urged the public and the press, namely major networks like ABC, CBS, and NBC, to fight back. In May, Commissioner Gomez penned a stunning public letter to Disney CEO Josh D'Amaro, wherein she warned that the company--which owns ABC--was being subjected to "a sustained, coordinated campaign of censorship and control, carried out through the weaponization of the FCC's authority as a federal regulator and aimed at pressuring a free and independent press." Gomez urged D'Amaro to fight the actions her own agency was taking, adding that "this is a fight worth having, and one that I am confident you will win." I wanted to talk to Commissioner Gomez about that bold letter, the risks she sees for the media and the American public under the Trump administration, and how she works alongside a chairman with whom she disagrees so fiercely. Gomez, whose FCC term ends this month, was generous enough to sit down and talk about all of it. You can read our conversation below, or listen to it on the podcast platform of your choice. KATIE DRUMMOND: Welcome, Commissioner Gomez. Thank you for being here. It's great to be here. I want to start, before we talk more about Disney and your letter and all the rest of it, with a very basic question for our listeners. What is your agency's basic role?

Greens senator Sarah Hanson-Young says Australia can't allow tech firms to'drain our power and water'. Greens senator Sarah Hanson-Young says Australia can't allow tech firms to'drain our power and water'. Australia'sleepwalking' into AI crisis and'tech bro free-for-all', says Greens senator Sarah Hanson Young's warning comes as David Pocock urges government to prevent firms using Australian content to train AI models Tue 23 Jun 2026 06.21 EDTFirst published on Tue 23 Jun 2026 05.16 EDT His call came as the Greens senator Sarah Hanson-Young called for a moratorium on the building and approval of new datacentres in Australia until "we get the regulations right". She said the nation was "sleepwalking" into an AI crisis and could hand tech companies a greenlight "to drain our power and water". Pocock used Senate question time on Tuesday to ask the government about intense lobbying from AI proprietors over possible new rules and regulations for Australian-made content - including suggestions Labor would create a new "carve out" or extend existing licensing arrangements.

Firms' algorithm development practices are often homogeneous. Whether firms train algorithms on similar data or rely on similar pre-trained models, the result is correlated predictions. In the context of personalized pricing, correlated algorithms can be viewed as a means to collude among competing firms, but whether or not this conduct is legal depends on the mechanisms of achieving collusion. We investigate the precise mechanisms through a formal game-theoretic model. Indeed, we find that (1) higher correlation diminishes consumer welfare and (2) as consumers become more price sensitive, firms are increasingly incentivized to compromise on the accuracy of their predictions in exchange for coordination. We demonstrate our theoretical results in a stylized empirical study where two firms compete using personalized pricing algorithms. Our results demonstrate a new mechanism for achieving collusion through correlation, which allows us to analyze its legal implications. Correlation through algorithms is a new frontier of anti-competitive behavior that is largely unconsidered by US antitrust law.

Long-separated research has been conducted on two highly correlated tracks: traffic and incidents. Traffic track witnesses complicating deep learning models, e.g., to push the prediction a few percent more accurate, and the incident track only studies the incidents alone, e.g., to infer the incident risk. We, for the first time, spatiotemporally aligned the two tracks in a large-scale region (16,972 traffic nodes) from year 2022 to 2024: our TraffiDent dataset includes traffic, i.e., time-series indexes on traffic flow, lane occupancy, and average vehicle speed, and incident, whose records are spatiotemporally aligned with traffic data, with seven different incident classes. Additionally, each node includes detailed physical and policylevel meta-attributes of lanes. Previous datasets typically contain only traffic or incident data in isolation, limiting research to general forecasting tasks.

As major progress in LLM-based long-form text generation enables paradigms such as retrieval-augmented generation (RAG) and inference-time scaling, safely incorporating private information into the generation remains a critical open question.

From a $13 Blink camera to $25 noise-cancelling earbuds, these are the name-brand picks worth grabbing before the sale ends June 26. More information Adding us as a Preferred Source in Google by using this link indicates that you would like to see more of our content in Google News results. You don't have to spend a ton to save money. We may earn revenue from the products available on this page and participate in affiliate programs. By signing up, you confirm you are 16+, will receive newsletters and promotional content and agree to our Terms of Use and acknowledge the data practices in our Privacy Policy .

Alignment faking in large language models presented a demonstration of Claude 3 Opus and Claude 3.5 Sonnet selectively complying with a helpfulonly training objective to prevent modification of their behavior outside of training. We expand this analysis to 25 models and find that only 5 (Claude 3 Opus, Claude 3.5 Sonnet, Llama 3 405B, Grok 3, Gemini 2.0 Flash) comply with harmful queries more when they infer they are in training than when they infer they are in deployment. First, we study the motivations of these 5 models. Results from perturbing details of the scenario suggest that only Claude 3 Opus's compliance gap is primarily and consistently motivated by trying to keep its goals. Second, we investigate why many chat models don't fake alignment. Our results suggest this is not entirely due to a lack of capabilities: many base models fake alignment some of the time, and post-training eliminates alignment-faking for some models and amplifies it for others.We investigate 5 hypotheses for how post-training may suppress alignment faking and find that variations in refusal behavior may account for a significant portion of differences in alignment faking.

Reinforcement Learning from Human Feedback (RLHF) is essential for aligning large language models (LLMs) with human preferences and values. While recent research has primarily focused on algorithmic advancements--such as reducing computational overhead or strengthening reward models to mitigate reward hacking--the critical role of prompt-data construction and its scalability has received comparatively less attention. In this paper, we address this gap by systematically exploring data-driven bottlenecks that currently hinder RLHF performance scaling, focusing specifically on the challenges posed by reward hacking and decreasing response diversity. To mitigate reward hacking, we introduce a hybrid reward system combining reasoning task verifiers (RTV) and a generative reward model (GenRM). This approach enables accurate assessment of responses against clearly defined ground-truth solutions. Additionally, in order to ensure response diversity and enhance learning effectiveness, we propose a novel prompt-selection method named Pre-PPO, explicitly identifying training prompts that are inherently challenging and thus less prone to reward hacking.

Recent advances in artificial intelligence have significantly impacted image retrieval tasks, yet Patent-Product Image Retrieval (PPIR) has received limited attention. PPIR, which retrieves patent images based on product images to identify potential infringements, presents unique challenges: (1) both product and patent images often contain numerous categories of artificial objects, but models pre-trained on standard datasets exhibit limited discriminative power to recognize some of those unseen objects; and (2) the significant domain gap between binary patent line drawings and colorful RGB product images further complicates similarity comparisons for product-patent pairs. To address these challenges, we formulate it as an open-set image retrieval task and introduce a comprehensive Patent-Product Image Retrieval Dataset (PPIRD) including a test set with 439 product-patent pairs, a retrieval pool of 727,921 patents, and an unlabeled pre-training set of 3,799,695 images. We further propose a novel Intermediate Domain Alignment and Morphology Analogy (IDAMA) strategy. IDAMA maps both image types to an intermediate sketch domain using edge detection to minimize the domain discrepancy, and employs a Morphology Analogy Filter to select discriminative patent images based on visual features via analogical reasoning. Extensive experiments on PPIRD demonstrate that IDAMA significantly outperforms baseline methods (+7.58 mAR) and offers valuable insights into domain mapping and representation learning for PPIR.