Rapid developments in advanced sensing and imaging have significantly enhanced information visibility, opening opportunities for predictive modeling of complex dynamic systems. However, sensing signals acquired from such complex systems are often distributed across 3D geometries and rapidly evolving over time, posing significant challenges in spatiotemporal predictive modeling. This paper proposes a geometry-aware active learning framework for modeling spatiotemporal dynamic systems. Specifically, we propose a geometry-aware spatiotemporal Gaussian Process (G-ST-GP) to effectively integrate the temporal correlations and geometric manifold features for reliable prediction of high-dimensional dynamic behaviors. In addition, we develop an adaptive active learning strategy to strategically identify informative spatial locations for data collection and further maximize the prediction accuracy. This strategy achieves the adaptive trade-off between the prediction uncertainty in the G-ST-GP model and the space-filling design guided by the geodesic distance across the 3D geometry. We implement the proposed framework to model the spatiotemporal electrodynamics in a 3D heart geometry. Numerical experiments show that our framework outperforms traditional methods lacking the mechanism of geometric information incorporation or effective data collection.

Cybersecurity is one of the key AI risk areas (OpenAI 2024b; The White House 2023; UK Government 2023): advanced LLMs could hack real-world systems at speeds far exceeding human capabilities (OpenAI 2024a). To quantify AI cyber capabilities, researchers use benchmarks, with InterCode-CTF (Yang, Prabhakar, Narasimhan, et al. 2023) among the most popular. InterCode-CTF adapts traditional Capture The Flag competitions to assess LLM hacking skills. Previously, Phuong et al. 2024 showed low performance on this benchmark and suggested low cyber exploitation capabilities. A recent follow-up by Abramovich et al. 2024 claimed state-ofthe-art results (72%) due to a particular novel harness design choice.

Current approaches to identifying driving heterogeneity face challenges in comprehending fundamental patterns from the perspective of underlying driving behavior mechanisms. The concept of Action phases was proposed in our previous work, capturing the diversity of driving characteristics with physical meanings. This study presents a novel framework to further interpret driving patterns by classifying Action phases in an unsupervised manner. In this framework, a Resampling and Downsampling Method (RDM) is first applied to standardize the length of Action phases. Then the clustering calibration procedure including ''Feature Selection'', ''Clustering Analysis'', ''Difference/Similarity Evaluation'', and ''Action phases Re-extraction'' is iteratively applied until all differences among clusters and similarities within clusters reach the pre-determined criteria. Application of the framework using real-world datasets revealed six driving patterns in the I80 dataset, labeled as ''Catch up'', ''Keep away'', and ''Maintain distance'', with both ''Stable'' and ''Unstable'' states. Notably, Unstable patterns are more numerous than Stable ones. ''Maintain distance'' is the most common among Stable patterns. These observations align with the dynamic nature of driving. Two patterns ''Stable keep away'' and ''Unstable catch up'' are missing in the US101 dataset, which is in line with our expectations as this dataset was previously shown to have less heterogeneity. This demonstrates the potential of driving patterns in describing driving heterogeneity. The proposed framework promises advantages in addressing label scarcity in supervised learning and enhancing tasks such as driving behavior modeling and driving trajectory prediction.

While language models (LMs) offer significant capability in zero-shot reasoning tasks across a wide range of domains, they do not perform satisfactorily in problems which requires multi-step reasoning. Previous approaches to mitigate this involves breaking a larger, multi-step task into sub-tasks and asking the language model to generate proposals ("thoughts") for each sub-task and using exhaustive planning approaches such as DFS to compose a solution. In this work, we leverage this idea to introduce two new contributions: first, we formalize a planning-based approach to perform multi-step problem solving with LMs via Partially Observable Markov Decision Processes (POMDPs), with the LM's own reflections about the value of a state used as a search heuristic; second, leveraging the online POMDP solver POMCP, we demonstrate a superior success rate of 89.4% on the Game of 24 task as compared to existing approaches while also offering better anytime performance characteristics than fixed tree-search which is used previously. Taken together, these contributions allow modern LMs to decompose and solve larger-scale reasoning tasks more effectively.

Contrastive learning-based methods, such as unsup-SimCSE, have achieved state-of-the-art (SOTA) performances in learning unsupervised sentence embeddings. However, in previous studies, each embedding used for contrastive learning only derived from one sentence instance, and we call these embeddings instance-level embeddings. In other words, each embedding is regarded as a unique class of its own, whichmay hurt the generalization performance. In this study, we propose IS-CSE (instance smoothing contrastive sentence embedding) to smooth the boundaries of embeddings in the feature space. Specifically, we retrieve embeddings from a dynamic memory buffer according to the semantic similarity to get a positive embedding group. Then embeddings in the group are aggregated by a self-attention operation to produce a smoothed instance embedding for further analysis. We evaluate our method on standard semantic text similarity (STS) tasks and achieve an average of 78.30%, 79.47%, 77.73%, and 79.42% Spearman's correlation on the base of BERT-base, BERT-large, RoBERTa-base, and RoBERTa-large respectively, a 2.05%, 1.06%, 1.16% and 0.52% improvement compared to unsup-SimCSE.

At a time when the US and China are divided on everything from economics to human rights, artificial intelligence is still a point of particular friction. With the potential to revolutionise everything from food production and health care to financial markets and surveillance, it's a technology that sparks both optimism and paranoia. One of the field's most influential figures is Andrew Chi-Chih Yao, whose education and professional life have straddled the world's two biggest economies. China-born and Harvard-trained, Yao is his country's only recipient of the Turing Award, computer science's equivalent of a Nobel Prize. After almost 40 years in the US, he returned to China in 2004.

A group of scientists at the U.S. Department of Energy's Ames Laboratory has developed computational quantum algorithms that are capable of efficient and highly accurate simulations of static and dynamic properties of quantum systems. The algorithms are valuable tools to gain greater insight into the physics and chemistry of complex materials, and they are specifically designed to work on existing and near-future quantum computers. Scientist Yong-Xin Yao and his research partners at Ames Lab use the power of advanced computers to speed discovery in condensed matter physics, modeling incredibly complex quantum mechanics and how they change over ultra-fast timescales. Current high performance computers can model the properties of very simple, small quantum systems, but larger or more complex systems rapidly expand the number of calculations a computer must perform to arrive at an accurate model, slowing the pace not only of computation, but also discovery. "This is a real challenge given the current early-stage of existing quantum computing capabilities," said Yao, "but it is also a very promising opportunity, since these calculations overwhelm classical computer systems, or take far too long to provide timely answers."

This is in order to give personalized probability of in vitro fertilisation (IVF) success. A secondary aim is to bring more transparency to the success and cost of IVF. Moreover, by using Univfy patients can learn about the costs of IVF treatment and their probability of success after one, two or three IVF cycles. The platform, therefore, also helps couples to make better financial decisions. To discover more about this combination of artificial intelligence and predictive technology, we spoke with the Chief Executive Officer, Dr. Mylene Yao.

One of China's leading tech companies is building an AI lab that could soon rival those operated by the likes of Google, Facebook, Baidu, and Amazon. Tencent, based in Shenzhen, in southern China, operates a range of online and mobile services, including the hugely popular social mobile apps WeChat and QQ. The company created its AI lab in April, and it is growing rapidly. Tencent sent a delegation of AI researchers, recruiters, and business representatives to the industry's preeminent event, the Neural Information Processing Systems conference, held in Barcelona, Spain, this week. Tencent's push into AI research reflects a broader shift across China's consumer technology industry toward more fundamental research designed to spur real innovation.

To encourage developers to build better chatbots, Seattle-based start-up, KITT.AI, has launched ChatFlow in private beta. ChatFlow framework makes it easier for developers to build better chatbots that can hold multi-turn conversations and work on multiple platforms. In 2015, Xuchen Yao was inspired to build KITT.AI when he realized there where "no good dialogue systems, and no good tools to create good dialogue systems," he said. KITT.AI originally focused on Amazon's Alexa platform, then received Amazon's Alexa Fund in 2015, and that's when Yao set out to build his talented team. How did the KITT.AI team meet?