Researchers and innovators have made enormous efforts in developing ideation methods, such as morphological analysis and design-by-analogy, to aid engineering design ideation for problem solving and innovation. Among these, the Theory of Inventive Problem Solving (TRIZ) stands out as one of the most well-known approaches, widely applied for systematic innovation. However, the complexity of TRIZ resources and concepts, coupled with its reliance on users' knowledge, experience, and reasoning capabilities, limits its practicality. Therefore, we explore the recent advances of large language models (LLMs) for a generative approach to bridge this gap. This paper proposes AutoTRIZ, an artificial ideation tool that uses LLMs to automate and enhance the TRIZ methodology. By leveraging the broad knowledge and advanced reasoning capabilities of LLMs, AutoTRIZ offers a novel approach for design automation and interpretable ideation with artificial intelligence. AutoTRIZ takes a problem statement from the user as its initial input, and automatically generates a solution report after the reasoning process. We demonstrate and evaluate the effectiveness of AutoTRIZ through consistency experiments in contradiction detection, and a case study comparing solutions generated by AutoTRIZ with the experts' analyses from the textbook. Moreover, the proposed LLM-based framework holds the potential for extension to automate other knowledge-based ideation methods, including SCAMPER, Design Heuristics, and Design-by-Analogy, paving the way for a new era of artificial ideation for design innovation.

In IoT environments, large amounts of procedural data are generated from IoT devices, information systems, and other software applications. The use of this data can foster the development of innovative applications in process control [63, 75, 56, 54, 35, 52, 42, 68], process conformance checking [23, 81, 83, 28], and process enhancement [67, 59], among others. Particularly, the use of process mining techniques to analyze not only process data but also IoT-collected data could provide important insights into processes and interactions as shown in different applications in the manufacturing domain, such as [58, 75, 56, 59, 67]. In these applications, IoT actuators are used to realize and execute process activities, while IoT sensors and smart tags are used to closely monitor the execution environment and involved resources [79, 75, 26, 37, 54]. IoT technology can therefore capture the context in which certain process tasks are performed, allowing process mining techniques to better understand and analyze the processes [7, 76, 12]. As such, besides the procedural data generated from the process execution systems, the data captured by IoT should also be considered an integral part of the process execution in the form of IoT-enriched event logs [57, 53]. Both the procedural nature of sensor logs, and the tight integration of these with the process executions and the executing resources [24] makes sensor data an integral part of process-based application scenarios in IoT [76, 75, 7]. However, the integration of IoT data and process data to be used for process mining is still often done ex-post in a manual fashion during a separate pre-processing phase [95, 73, 53]. In these cases, the data from the IoT environment is still collected and stored separately, and only later it is explicitly connected to the notion of a process, which is non-trivial as pointed out in the challenge "Bridging the Gap Between Event-based and Process-based Systems" in the BPM-IoT manifesto [37].

Despite significant advancements in robotic locomotion, navigating diverse landscapes for tasks such as search and rescue in complex environments (e.g., sandy terrains, wet forests, and regolith-covered landscapes), as well as responding to mudslides and avalanches, remains a formidable challenge for robotic systems (1,2). While conventional wheeled and legged robots excel on solid ground, they often struggle on granular media such as sand, grains, or pebbles (3) due to the non-uniform and deformable nature of the terrain (4). Moreover, factors like high resistance to penetration, instability, and limited load-bearing capacity of granular terrains can impede the mobility of these robots, leading to issues such as entrapment or slippage (5, 6). In addressing the limitations of traditional wheeled and legged robots, flipper-based locomotion offers a promising alternative. This concept draws inspiration from animals such as penguins, with their agile underwater propulsion using flippers (7, 8), and seals, known for their maneuverability in both water and land (9). Similarly, the fin-based locomotion of mudskippers, effective in terrestrial and aquatic settings, mirrors the adaptability of flipper-based systems, offering parallel insights for robotic design (10,11). Drawing inspiration from aquatic and amphibious animals, we can equip robots with flexible and powerful flippers, enhancing adaptable propulsion and maneuverability in diverse environments, from aquatic to granular terrains (12-16). Among the various examples of flipper-based locomotion in nature, sea turtles are particu-2 Figure 1: Biological and robotic sea turtle hatchlings navigating diverse terrains: Sea turtle hatchling (left) and its robotic counterpart (right) are shown traversing dry sand, small and big rocks, wet sand, and vegetation, illustrating the bio-inspired robot's design effectiveness and its capability to adapt to complex environmental conditions.

We present a new challenge to examine whether large language models understand social norms. In contrast to existing datasets, our dataset requires a fundamental understanding of social norms to solve. Our dataset features the largest set of social norm skills, consisting of 402 skills and 12,383 questions covering a wide set of social norms ranging from opinions and arguments to culture and laws. We design our dataset according to the K-12 curriculum. This enables the direct comparison of the social understanding of large language models to humans, more specifically, elementary students. While prior work generates nearly random accuracy on our benchmark, recent large language models such as GPT3.5-Turbo and LLaMA2-Chat are able to improve the performance significantly, only slightly below human performance. We then propose a multi-agent framework based on large language models to improve the models' ability to understand social norms. This method further improves large language models to be on par with humans. Given the increasing adoption of large language models in real-world applications, our finding is particularly important and presents a unique direction for future improvements.

We introduce a new challenge to test the STEM skills of neural models. The problems in the real world often require solutions, combining knowledge from STEM (science, technology, engineering, and math). Unlike existing datasets, our dataset requires the understanding of multimodal vision-language information of STEM. Our dataset features one of the largest and most comprehensive datasets for the challenge. It includes 448 skills and 1,073,146 questions spanning all STEM subjects. Compared to existing datasets that often focus on examining expert-level ability, our dataset includes fundamental skills and questions designed based on the K-12 curriculum. We also add state-of-the-art foundation models such as CLIP and GPT-3.5-Turbo to our benchmark. Results show that the recent model advances only help master a very limited number of lower grade-level skills (2.5% in the third grade) in our dataset. In fact, these models are still well below (averaging 54.7%) the performance of elementary students, not to mention near expert-level performance. To understand and increase the performance on our dataset, we teach the models on a training split of our dataset. Even though we observe improved performance, the model performance remains relatively low compared to average elementary students. To solve STEM problems, we will need novel algorithmic innovations from the community.

Learning to represent and simulate the dynamics of physical systems is a crucial yet challenging task. Existing equivariant Graph Neural Network (GNN) based methods have encapsulated the symmetry of physics, \emph{e.g.}, translations, rotations, etc, leading to better generalization ability. Nevertheless, their frame-to-frame formulation of the task overlooks the non-Markov property mainly incurred by unobserved dynamics in the environment. In this paper, we reformulate dynamics simulation as a spatio-temporal prediction task, by employing the trajectory in the past period to recover the Non-Markovian interactions. We propose Equivariant Spatio-Temporal Attentive Graph Networks (ESTAG), an equivariant version of spatio-temporal GNNs, to fulfill our purpose. At its core, we design a novel Equivariant Discrete Fourier Transform (EDFT) to extract periodic patterns from the history frames, and then construct an Equivariant Spatial Module (ESM) to accomplish spatial message passing, and an Equivariant Temporal Module (ETM) with the forward attention and equivariant pooling mechanisms to aggregate temporal message. We evaluate our model on three real datasets corresponding to the molecular-, protein- and macro-level. Experimental results verify the effectiveness of ESTAG compared to typical spatio-temporal GNNs and equivariant GNNs.

Robots have been successfully deployed in both traditional and novel manufacturing processes. However, they are still difficult to program by non-experts, which limits their accessibility to a wider range of potential users. Programming robots requires expertise in both robotics and the specific manufacturing process in which they are applied. Robot programs created offline often lack parameters that represent relevant manufacturing skills when executing a specific task. These skills encompass aspects like robot orientation and velocity. This paper introduces an intuitive robot programming system designed to capture manufacturing skills from task demonstrations performed by skilled workers. Demonstration data, including orientations and velocities of the working paths, are acquired using a magnetic tracking system fixed to the tools used by the worker. Positional data are extracted from CAD/CAM. Robot path poses are transformed into Cartesian space and validated in simulation, subsequently leading to the generation of robot programs. PathML, an AutomationML-based syntax, integrates robot and manufacturing data across the heterogeneous elements and stages of the manufacturing systems considered. Experiments conducted on the glass adhesive application and welding processes showcased the intuitive nature of the system, with path errors falling within the functional tolerance range.

Predictive Maintenance (PdM) emerged as one of the pillars of Industry 4.0, and became crucial for enhancing operational efficiency, allowing to minimize downtime, extend lifespan of equipment, and prevent failures. A wide range of PdM tasks can be performed using Artificial Intelligence (AI) methods, which often use data generated from industrial sensors. The steel industry, which is an important branch of the global economy, is one of the potential beneficiaries of this trend, given its large environmental footprint, the globalized nature of the market, and the demanding working conditions. This survey synthesizes the current state of knowledge in the field of AI-based PdM within the steel industry and is addressed to researchers and practitioners. We identified 219 articles related to this topic and formulated five research questions, allowing us to gain a global perspective on current trends and the main research gaps. We examined equipment and facilities subjected to PdM, determined common PdM approaches, and identified trends in the AI methods used to develop these solutions. We explored the characteristics of the data used in the surveyed articles and assessed the practical implications of the research presented there. Most of the research focuses on the blast furnace or hot rolling, using data from industrial sensors. Current trends show increasing interest in the domain, especially in the use of deep learning. The main challenges include implementing the proposed methods in a production environment, incorporating them into maintenance plans, and enhancing the accessibility and reproducibility of the research.

Searching through chemical space is an exceptionally challenging problem because the number of possible molecules grows combinatorially with the number of atoms. Large, autoregressive models trained on databases of chemical compounds have yielded powerful generators, but we still lack robust strategies for generating molecules with desired properties. This molecular search problem closely resembles the "alignment" problem for large language models, though for many chemical tasks we have a specific and easily evaluable reward function. Here, we introduce an algorithm called energy rank alignment (ERA) that leverages an explicit reward function to produce a gradient-based objective that we use to optimize autoregressive policies. We show theoretically that this algorithm is closely related to proximal policy optimization (PPO) and direct preference optimization (DPO), but has a minimizer that converges to an ideal Gibbs-Boltzmann distribution with the reward playing the role of an energy function. Furthermore, this algorithm is highly scalable, does not require reinforcement learning, and performs well relative to DPO when the number of preference observations per pairing is small. We deploy this approach to align molecular transformers to generate molecules with externally specified properties and find that it does so robustly, searching through diverse parts of chemical space. While our focus here is on chemical search, we also obtain excellent results on an AI supervised task for LLM alignment, showing that the method is scalable and general.

Research on jailbreaking has been valuable for testing and understanding the safety and security issues of large language models (LLMs). In this paper, we introduce Iterative Refinement Induced Self-Jailbreak (IRIS), a novel approach that leverages the reflective capabilities of LLMs for jailbreaking with only black-box access. Unlike previous methods, IRIS simplifies the jailbreaking process by using a single model as both the attacker and target. This method first iteratively refines adversarial prompts through self-explanation, which is crucial for ensuring that even well-aligned LLMs obey adversarial instructions. IRIS then rates and enhances the output given the refined prompt to increase its harmfulness. We find IRIS achieves jailbreak success rates of 98% on GPT-4 and 92% on GPT-4 Turbo in under 7 queries. It significantly outperforms prior approaches in automatic, black-box and interpretable jailbreaking, while requiring substantially fewer queries, thereby establishing a new standard for interpretable jailbreaking methods.