Neural Information Processing Systems http://nips.cc/

Afundamental challenge indeep metric learning isthegeneralization capability of the feature embedding network model since the embedding network learned ontraining classes needtobeevaluated onnewtestclasses.

Deep neural networks are the state-of-the-art for various applications. However,one of the biggest challenges facing them is the lack of labeled data to train these complex networks.

As the markets for unmanned aerial vehicles (UAVs) and mixed reality (MR) headsets continue to grow, recent research has increasingly explored their integration, which enables more intuitive, immersive, and situationally aware control systems. We present IGUANA, an MR-based immersive guidance, navigation, and control system for consumer UAVs. IGUANA introduces three key elements beyond conventional control interfaces: (1) a 3D terrain map interface with draggable waypoint markers and live camera preview for high-level control, (2) a novel spatial control metaphor that uses a virtual ball as a physical analogy for low-level control, and (3) a spatial overlay that helps track the UAV when it is not visible with the naked eye or visual line of sight is interrupted. We conducted a user study to evaluate our design, both quantitatively and qualitatively, and found that (1) the 3D map interface is intuitive and easy to use, relieving users from manual control and suggesting improved accuracy and consistency with lower perceived workload relative to conventional dual-stick controller, (2) the virtual ball interface is intuitive but limited by the lack of physical feedback, and (3) the spatial overlay is very useful in enhancing the users' situational awareness.

In 2000 TIME's editors sat down to select three inventions of the year, one each in consumer technology, medical science, and basic industry. They found so many interesting ones along the way that they included dozens of others, from an unbreakable lightbulb to paper that was easier to recycle. It was the start of our annual hunt for the most exciting innovations changing our lives, and the future. Since then, TIME has covered hundreds of inventions, from the esoteric (clouds featured more than once) to essential, including life-changing medicines, technological breakthroughs, new foods, nearly every new Apple product category, and even a few great ideas that didn't quite catch on. As TIME publishes the 2025 list, we're also assembling the Best Inventions Hall of Fame: the 25 most iconic inventions we covered in the past quarter century. Almost all women in the U.S. use contraception at some point in their lives, and in 2001 a new option came on the market, the vaginal ring. As TIME wrote when including it among the year's best inventions, "Some women hate taking pills. In early October the FDA approved use of the NuvaRing, a thin flexible plastic ring that women can flatten like a rubber band and insert once a month into the vagina."

Neural Information Processing Systems http://nips.cc/

The UN's AI warnings grow louder Welcome back to In the Loop, new twice-weekly newsletter about AI. It was a busy week for our team: Tharin Pillay was on site during the UN General Assembly in New York, while Harry Booth and Nikita Ostrovsky were at the "All In AI" event in Montreal. If you're reading this in your browser, why not subscribe to have the next one delivered straight to your inbox? The United Nations General Assembly met this week in New York. While the assembly members spent much of their time on the crises in Palestine and Sudan, they also devoted a good chunk to AI.

The 34rd International Joint Conference on Artificial Intelligence (IJCAI-25) is currently taking place in Montréal, Canada. The first couple of days saw the attendees enjoy some of the many tutorials and workshops on offer, with the doctoral consortium also being held. The official opening ceremony took place this morning (Tuesday 19 August). Find out what the participants have been getting up to so far. Find out more about what the event has in store: @ijcai.org

AI for good initiatives often rely on the assumption that technical interventions can resolve complex social problems. In the context of human trafficking (HT), such techno-solutionism risks oversimplifying exploitation, reinforcing power imbalances and causing harm to the very communities AI claims to support. In this paper, we introduce the Radical Questioning (RQ) framework as a five step, pre-project ethical assessment tool to critically evaluate whether AI should be built at all, especially in domains involving marginalized populations and entrenched systemic injustice. RQ does not replace principles based ethics but precedes it, offering an upstream, deliberative space to confront assumptions, map power, and consider harms before design. Using a case study in AI for HT, we demonstrate how RQ reveals overlooked sociocultural complexities and guides us away from surveillance based interventions toward survivor empowerment tools. While developed in the context of HT, RQ's five step structure can generalize to other domains, though the specific questions must be contextual. This paper situates RQ within a broader AI ethics philosophy that challenges instrumentalist norms and centers relational, reflexive responsibility.

Cities are not monolithic; they are arenas of negotiation among groups that hold varying needs, values, and experiences. Conventional methods of urban assessment -- from standardized surveys to AI-driven evaluations -- frequently rely on a single consensus metric (e.g., an average measure of inclusivity or safety). Although such aggregations simplify design decisions, they risk obscuring the distinct perspectives of marginalized populations. In this paper, we present findings from a community-centered study in Montreal involving 35 residents with diverse demographic and social identities, particularly wheelchair users, seniors, and LGBTQIA2+ individuals. Using rating and ranking tasks on 20 urban sites, we observe that disagreements are systematic rather than random, reflecting structural inequalities, differing cultural values, and personal experiences of safety and accessibility. Based on these empirical insights, we propose negotiative alignment, an AI framework that treats disagreement as an essential input to be preserved, analyzed, and addressed. Negotiative alignment builds on pluralistic models by dynamically updating stakeholder preferences through multi-agent negotiation mechanisms, ensuring no single perspective is marginalized. We outline how this framework can be integrated into urban analytics -- and other decision-making contexts -- to retain minority viewpoints, adapt to changing stakeholder concerns, and enhance fairness and accountability. The study demonstrates that preserving and engaging with disagreement, rather than striving for an artificial consensus, can produce more equitable and responsive AI-driven outcomes in urban design.