An iceberg sealed the penguin colony's entrance, triggering a 70% survival drop. A group of Emperor penguin chicks is walking on the fast ice at the Emperor penguin colony at Snow Hill Island in the Weddell Sea in Antarctica. Breakthroughs, discoveries, and DIY tips sent six days a week. A massive iceberg has triggered a catastrophic die-off of Emperor Penguin chicks in Antarctica, blocking thousands of parents from reaching their young. The event claimed the lives of approximately 14,000 chicks at the Coulman Island colony in the Ross Sea, the region's largest breeding ground.

Deep learning-based prediction models for High-Level Synthesis (HLS) of hardware designs often struggle to generalize. In this paper, we study how to close the generalizability gap of these models through pretraining on synthetic data and introduce Iceberg, a synthetic data augmentation approach that expands both large language model (LLM)-generated programs and weak labels of unseen design configurations. Our weak label generation method is integrated with an in-context model architecture, enabling meta-learning from actual and proximate labels. Iceberg improves the geometric mean modeling accuracy by $86.4\%$ when adapt to six real-world applications with few-shot examples and achieves a $2.47\times$ and a $1.12\times$ better offline DSE performance when adapting to two different test datasets. Our open-sourced code is here: https://github.com/UCLA-VAST/iceberg

Drifting icebergs in the polar oceans play a key role in the Earth's climate system, impacting freshwater fluxes into the ocean and regional ecosystems while also posing a challenge to polar navigation. However, accurately forecasting iceberg trajectories remains a formidable challenge, primarily due to the scarcity of spatiotemporal data and the complex, nonlinear nature of iceberg motion, which is also impacted by environmental variables. The iceberg motion is influenced by multiple dynamic environmental factors, creating a highly variable system that makes trajectory identification complex. These limitations hinder the ability of deep learning models to effectively capture the underlying dynamics and provide reliable predictive outcomes. To address these challenges, we propose a hybrid IDRIFTNET model, a physics-driven deep learning model that combines an analytical formulation of iceberg drift physics, with an augmented residual learning model. The model learns the pattern of mismatch between the analytical solution and ground-truth observations, which is combined with a rotate-augmented spectral neural network that captures both global and local patterns from the data to forecast future iceberg drift positions. We compare IDRIFTNET model performance with state-of-the-art models on two Antarctic icebergs: A23A and B22A. Our findings demonstrate that IDRIFTNET outperforms other models by achieving a lower Final Displacement Error (FDE) and Average Displacement Error (ADE) across a variety of time points. These results highlight IDRIFTNET's effectiveness in capturing the complex, nonlinear drift of icebergs for forecasting iceberg trajectories under limited data and dynamic environmental conditions.

Large language models (LLMs) are now widely accessible, reaching learners at all educational levels. This development has raised concerns that their use may circumvent essential learning processes and compromise the integrity of established assessment formats. In physics education, where problem solving plays a central role in instruction and assessment, it is therefore essential to understand the physics-specific problem-solving capabilities of LLMs. Such understanding is key to informing responsible and pedagogically sound approaches to integrating LLMs into instruction and assessment. This study therefore compares the problem-solving performance of a general-purpose LLM (GPT-4o, using varying prompting techniques) and a reasoning-optimized model (o1-preview) with that of participants of the German Physics Olympiad, based on a set of well-defined Olympiad problems. In addition to evaluating the correctness of the generated solutions, the study analyzes characteristic strengths and limitations of LLM-generated solutions. The findings of this study indicate that both tested LLMs (GPT-4o and o1-preview) demonstrate advanced problem-solving capabilities on Olympiad-type physics problems, on average outperforming the human participants. Prompting techniques had little effect on GPT-4o's performance, while o1-preview almost consistently outperformed both GPT-4o and the human benchmark. Based on these findings, the study discusses implications for the design of summative and formative assessment in physics education, including how to uphold assessment integrity and support students in critically engaging with LLMs.

When you hear the term'dark web,' a hacker in a hoodie, digital drug deals and hitmen for hire are probably what come to mind. Usually, our imaginations cook up scenarios that are a lot more dramatic than reality. But when it comes to this hidden corner of the internet that can only be reached using special software, it's pretty spot on. The sites we all visit every day are just the tip of the iceberg in the digital world. Beneath the surface is a hidden layer that goes un-indexed by search engines - it's called the deep web.

Thousands of university students in the UK have been caught misusing ChatGPT and other artificial intelligence tools in recent years, while traditional forms of plagiarism show a marked decline, a Guardian investigation can reveal. A survey of academic integrity violations found almost 7,000 proven cases of cheating using AI tools in 2023-24, equivalent to 5.1 for every 1,000 students. That was up from 1.6 cases per 1,000 in 2022-23. Figures up to May suggest that number will increase again this year to about 7.5 proven cases per 1,000 students – but recorded cases represent only the tip of the iceberg, according to experts. The data highlights a rapidly evolving challenge for universities: trying to adapt assessment methods to the advent of technologies such as ChatGPT and other AI-powered writing tools.

It has been 113 years since the Titanic sank beneath the waves, claiming the lives of more than 1,500 passengers and crew. But new evidence has finally cleared the tragedy's Scottish scapegoat: First Officer William Murdoch. For years, Officer Murdoch has been accused of taking bribes, abandoning his post, and was even depicted shooting a passenger in the James Cameron movie. Now, more than a century later, 3D scans show that Officer Murdoch did not flee his position, but died while helping passengers escape until the very end. Deep sea scanning company Magellan has snapped 715,000 photos of the Titanic wreck 12,500 feet beneath the Atlantic.

The RMS Titanic sank in the North Atlantic Ocean on April 15, 1912, after colliding with an iceberg during her maiden voyage from Southampton to New York. More than 1,500 people died when the ship, which was carrying 2,224 passengers and crew, sank under the command of Captain Edward Smith. Some of the wealthiest people in the world were on board, including property tycoon John Jacob Astor IV, great grandson of John Jacob Astor, founder of the Waldorf Astoria Hotel. Millionaire Benjamin Guggenheim, heir to his family's mining business, also perished, along with Isidor Straus, the German-born co-owner of Macy's department store. The ship was the largest afloat at the time and was designed in such a way that it was meant to be'unsinkable'.

Molecular machine learning has gained popularity with the advancements of geometric deep learning. In parallel, retrieval-augmented generation has become a principled approach commonly used with language models. However, the optimal integration of retrieval augmentation into molecular machine learning remains unclear. Graph neural networks stand to benefit from clever matching to understand the structural alignment of retrieved molecules to a query molecule. Neural graph matching offers a compelling solution by explicitly modeling node and edge affinities between two structural graphs while employing a noise-robust, end-to-end neural network to learn affinity metrics. We apply this approach to mass spectrum simulation and introduce MARASON, a novel model that incorporates neural graph matching to enhance a fragmentation-based neural network. Experimental results highlight the effectiveness of our design, with MARASON achieving 28% top-1 accuracy, a substantial improvement over the non-retrieval state-of-the-art accuracy of 19%. Moreover, MARASON outperforms both naive retrieval-augmented generation methods and traditional graph matching approaches.

Graph Neural Networks (GNNs) have achieved great success in dealing with non-Euclidean graph-structured data and have been widely deployed in many real-world applications. However, their effectiveness is often jeopardized under class-imbalanced training sets. Most existing studies have analyzed class-imbalanced node classification from a supervised learning perspective, but they do not fully utilize the large number of unlabeled nodes in semi-supervised scenarios. We claim that the supervised signal is just the tip of the iceberg and a large number of unlabeled nodes have not yet been effectively utilized. In this work, we propose IceBerg, a debiased self-training framework to address the class-imbalanced and few-shot challenges for GNNs at the same time. Specifically, to figure out the Matthew effect and label distribution shift in self-training, we propose Double Balancing, which can largely improve the performance of existing baselines with just a few lines of code as a simple plug-and-play module. Secondly, to enhance the long-range propagation capability of GNNs, we disentangle the propagation and transformation operations of GNNs. Therefore, the weak supervision signals can propagate more effectively to address the few-shot issue. In summary, we find that leveraging unlabeled nodes can significantly enhance the performance of GNNs in class-imbalanced and few-shot scenarios, and even small, surgical modifications can lead to substantial performance improvements. Systematic experiments on benchmark datasets show that our method can deliver considerable performance gain over existing class-imbalanced node classification baselines. Additionally, due to IceBerg's outstanding ability to leverage unsupervised signals, it also achieves state-of-the-art results in few-shot node classification scenarios. The code of IceBerg is available at: https://github.com/ZhixunLEE/IceBerg.