Benchmarks are important tools for tracking the rapid advancements in large language model (LLM) capabilities. However, benchmarks are not keeping pace in difficulty: LLMs now achieve over 90\% accuracy on popular benchmarks like MMLU, limiting informed measurement of state-of-the-art LLM capabilities. In response, we introduce Humanity's Last Exam (HLE), a multi-modal benchmark at the frontier of human knowledge, designed to be the final closed-ended academic benchmark of its kind with broad subject coverage. HLE consists of 3,000 questions across dozens of subjects, including mathematics, humanities, and the natural sciences. HLE is developed globally by subject-matter experts and consists of multiple-choice and short-answer questions suitable for automated grading. Each question has a known solution that is unambiguous and easily verifiable, but cannot be quickly answered via internet retrieval. State-of-the-art LLMs demonstrate low accuracy and calibration on HLE, highlighting a significant gap between current LLM capabilities and the expert human frontier on closed-ended academic questions. To inform research and policymaking upon a clear understanding of model capabilities, we publicly release HLE at https://lastexam.ai.

Estimating depth from a sequence of posed RGB images is a fundamental computer vision task, with applications in augmented reality, path planning etc. Prior work typically makes use of previous frames in a multi view stereo framework, relying on matching textures in a local neighborhood. In contrast, our model leverages historical predictions by giving the latest 3D geometry data as an extra input to our network. This self-generated geometric hint can encode information from areas of the scene not covered by the keyframes and it is more regularized when compared to individual predicted depth maps for previous frames. We introduce a Hint MLP which combines cost volume features with a hint of the prior geometry, rendered as a depth map from the current camera location, together with a measure of the confidence in the prior geometry. We demonstrate that our method, which can run at interactive speeds, achieves state-of-the-art estimates of depth and 3D scene reconstruction in both offline and incremental evaluation scenarios.

The collaborative robot market is flourishing as there is a trend towards simplification, modularity, and increased flexibility on the production line. But when humans and robots are collaborating in a shared environment, the safety of humans should be a priority. We introduce a novel wearable robotic system to enhance safety during Human-Robot Interaction (HRI). The proposed wearable robot is designed to hold a fiducial marker and maintain its visibility to a motion capture system, which, in turn, localizes the user's hand with good accuracy and low latency and provides vibrotactile feedback to the user's wrist. The vibrotactile feedback guides the user's hand movement during collaborative tasks in order to increase safety and enhance collaboration efficiency. A user study was conducted to assess the recognition and discriminability of ten designed vibration patterns applied to the upper (dorsal) and the down (volar) parts of the user's wrist. The results show that the pattern recognition rate on the volar side was higher, with an average of 75.64% among all users. Four patterns with a high recognition rate were chosen to be incorporated into our system. A second experiment was carried out to evaluate users' response to the chosen patterns in real-world collaborative tasks. Results show that all participants responded to the patterns correctly, and the average response time for the patterns was between 0.24 and 2.41 seconds.

Currently, High-Definition (HD) maps are a prerequisite for the stable operation of autonomous vehicles. Such maps contain information about all static road objects for the vehicle to consider during navigation, such as road edges, road lanes, crosswalks, and etc. To generate such an HD map, current approaches need to process pre-recorded environment data obtained from onboard sensors. However, recording such a dataset often requires a lot of time and effort. In addition, every time actual road environments are changed, a new dataset should be recorded to generate a relevant HD map. This paper addresses a novel approach that allows to continuously generate or update the HD map using onboard sensor data. When there is no need to pre-record the dataset, updating the HD map can be run in parallel with the main autonomous vehicle navigation pipeline. The proposed approach utilizes the VectorMapNet framework to generate vector road object instances from a sensor data scan. The PolyMerge technique is aimed to merge new instances into previous ones, mitigating detection errors and, therefore, generating or updating the HD map. The performance of the algorithm was confirmed by comparison with ground truth on the NuScenes dataset. Experimental results showed that the mean error for different levels of environment complexity was comparable to the VectorMapNet single instance error.