Given trajectory data, a domain-specific study area, and a user-defined threshold, we aim to find anomalous trajectories indicative of possible GPS spoofing (e.g., fake trajectory). The problem is societally important to curb illegal activities in international waters, such as unauthorized fishing and illicit oil transfers. The problem is challenging due to advances in AI generated in deep fakes generation (e.g., additive noise, fake trajectories) and lack of adequate amount of labeled samples for ground-truth verification. Recent literature shows promising results for anomalous trajectory detection using generative models despite data sparsity. However, they do not consider fine-scale spatiotemporal dependencies and prior physical knowledge, resulting in higher false-positive rates. To address these limitations, we propose a physics-informed diffusion model that integrates kinematic constraints to identify trajectories that do not adhere to physical laws. Experimental results on real-world datasets in the maritime and urban domains show that the proposed framework results in higher prediction accuracy and lower estimation error rate for anomaly detection and trajectory generation methods, respectively. Our implementation is available at https://github.com/arunshar/Physics-Informed-Diffusion-Probabilistic-Model.

It's an idea that sounds straight from the latest science fiction blockbuster. But scientists at the University of Miami have warned that the world's oceans are teeming with'giant viruses', also known as giruses. Most viruses are less than 0.5 per cent the width of a human hair – too small to be seen with the naked human eye. In contrast, the researchers say that the giant viruses are five times bigger, rivaling bacteria in terms of size. Concerningly, all 230 giant viruses are previously unknown to science.

Breakthroughs, discoveries, and DIY tips sent every weekday. A shipwreck accidentally discovered off France's southeastern coast near Saint-Tropez appears to be a striking well-preserved 16th-century Italian merchant ship. At 8,422 feet below sea level, the vessel is likely the deepest of its kind ever found in French waters, according to the official announcement. But next to scattered ceramics, metal bars, and rigging rests what appear to be jarring reminders of modern life. Earlier this year, French military personnel noticed an odd ping while guiding an underwater drone along a routine surveying expedition. Although intended to monitor potential oceanic resources and deepsea cable routes, the equipment flagged something sizable already laying over 1.5 miles below the surface of the Mediterranean Sea.

Understanding complex systems by inferring trajectories from sparse sample snapshots is a fundamental challenge in a wide range of domains, e.g., single-cell biology, meteorology, and economics. Despite advancements in Bridge and Flow matching frameworks, current methodologies rely on pairwise interpolation between adjacent snapshots. This hinders their ability to capture long-range temporal dependencies and potentially affects the coherence of the inferred trajectories. To address these issues, we introduce \textbf{Momentum Multi-Marginal Schrödinger Bridge Matching (3MSBM)}, a novel matching framework that learns smooth measure-valued splines for stochastic systems that satisfy multiple positional constraints. This is achieved by lifting the dynamics to phase space and generalizing stochastic bridges to be conditioned on several points, forming a multi-marginal conditional stochastic optimal control problem. The underlying dynamics are then learned by minimizing a variational objective, having fixed the path induced by the multi-marginal conditional bridge. As a matching approach, 3MSBM learns transport maps that preserve intermediate marginals throughout training, significantly improving convergence and scalability. Extensive experimentation in a series of real-world applications validates the superior performance of 3MSBM compared to existing methods in capturing complex dynamics with temporal dependencies, opening new avenues for training matching frameworks in multi-marginal settings.

The United States ambassador to NATO, Matthew Whitaker, said the Ukrainian drone attack on Russian strategic bombers at their airbases earlier this month was "badass" but also "a little bit reckless, and a little bit dangerous". Ukrainian President Volodymyr Zelenskyy, addressing a conference of southeast European leaders in the Black Sea port of Odesa, said Russia was determined to destroy the south of his country as well as nearby Moldova and Romania, as he called for increased pressure on Moscow to prevent further military threats. It is the first time the leader has visited Ukraine during his 12 years in power. Finland's Ministry for Foreign Affairs said it had summoned a Russian diplomat over a suspected June 10 violation of Finnish airspace by Russian aircraft, the second such event in under three weeks. Slovakia will not back the European Union's 18th package of sanctions against Russia unless the European Commission provides a solution to the situation the country faces if the bloc phases out Russian energy as planned, the country's Prime Minister Robert Fico has said. Germany's imports of goods from Russia fell by 95 percent in the 2021-2024 period, while its exports of goods to Russia were cut by 72 percent, the country's statistics office Destatis has reported.

Kyiv, Ukraine – Swarms of Russian kamikaze drones broke through Ukrainian air defence fire early on Tuesday, screeching and shrilling over Kyiv in one of the largest wartime attacks. Oleksandra Yaremchuk, who lives in the Ukrainian capital, said the hours-long sound of two or perhaps three drones above her house felt new and alarming. "This horrible buzz is the sound of death, it makes you feel helpless and panicky," the 38-year-old bank clerk told Al Jazeera, describing her sleepless night in the northern district of Obolon. "This time I heard it in stereo and in Dolby surround," she quipped. Back in 2022, she crisscrossed duct tape over her apartment's windows to avoid being hit by glass shards and spent most of the night in a shaky chair in her hallway.

Lt. Gen. Keith Kellogg discusses the latest with the Ukraine and Russia war after a deadly Russian attack on'America Reports.' The massive Ukrainian drone strike on Russia has strong implications for the future of all warfare. The sophisticated operation taught us that the use of low-cost, highly scalable, lethal drone technology is here to stay. Our leaders must pay attention, because the Ukraine-Russia war is a blueprint for not only how we will fight future wars but how we will have to defend ourselves from a more sophisticated and capable enemy than ever before. America's defense leaders need to start reflecting on the realities of modern warfare and fully understand that, as a country, we are not ready.

Ukrainian drones struck multiple military airbases deep inside Russia on Sunday in a major operation a day before the neighbours held peace talks in Istanbul. The Russian Defence Ministry said Ukraine had launched drone strikes targeting Russian military airfields across five regions, causing several aircraft to catch fire. The attacks occurred in the Murmansk, Irkutsk, Ivanovo, Ryazan, and Amur regions. Air defences repelled the assaults in all but two regions – Murmansk and Irkutsk, the ministry said. "In the Murmansk and Irkutsk regions, the launch of FPV drones from an area in close proximity to airfields resulted in several aircraft catching fire," the Defence Ministry said.

Kyiv, Ukraine – Any description of Ukraine's attacks on Russia's fleet of strategic bombers could leave one scrambling for superlatives. Forty-one planes – including supersonic Tu-22M long-range bombers, Tu-95 flying fortresses and A-50 early warning warplanes – were hit and damaged on Sunday on four airfields, including ones in the Arctic and Siberia, Ukrainian authorities and intelligence said. Moscow did not comment on the damage to the planes but confirmed that the airfields were hit by "Ukrainian terrorist attacks". Videos posted by the Ukrainian Security Service (SBU), which planned and carried out the operation, which was called The Spiderweb, showed only a handful of planes being hit. The strategic bombers have been used to launch ballistic and cruise missiles from Russian airspace to hit targets across Ukraine, causing wide scale damage and casualties.

Scientists often want to make predictions beyond the observed time horizon of "snapshot" data following latent stochastic dynamics. For example, in time course single-cell mRNA profiling, scientists have access to cellular transcriptional state measurements (snapshots) from different biological replicates at different time points, but they cannot access the trajectory of any one cell because measurement destroys the cell. Researchers want to forecast (e.g.) differentiation outcomes from early state measurements of stem cells. Recent Schrödinger-bridge (SB) methods are natural for interpolating between snapshots. But past SB papers have not addressed forecasting -- likely since existing methods either (1) reduce to following pre-set reference dynamics (chosen before seeing data) or (2) require the user to choose a fixed, state-independent volatility since they minimize a Kullback-Leibler divergence. Either case can lead to poor forecasting quality. In the present work, we propose a new framework, SnapMMD, that learns dynamics by directly fitting the joint distribution of both state measurements and observation time with a maximum mean discrepancy (MMD) loss. Unlike past work, our method allows us to infer unknown and state-dependent volatilities from the observed data. We show in a variety of real and synthetic experiments that our method delivers accurate forecasts. Moreover, our approach allows us to learn in the presence of incomplete state measurements and yields an $R^2$-style statistic that diagnoses fit. We also find that our method's performance at interpolation (and general velocity-field reconstruction) is at least as good as (and often better than) state-of-the-art in almost all of our experiments.