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.

Human face generation and editing represent an essential task in the era of computer vision and the digital world. Recent studies have shown remarkable progress in multi-modal face generation and editing, for instance, using face segmentation to guide image generation. However, it may be challenging for some users to create these conditioning modalities manually. Thus, we introduce M3Face, a unified multi-modal multilingual framework for controllable face generation and editing. This framework enables users to utilize only text input to generate controlling modalities automatically, for instance, semantic segmentation or facial landmarks, and subsequently generate face images. We conduct extensive qualitative and quantitative experiments to showcase our frameworks face generation and editing capabilities. Additionally, we propose the M3CelebA Dataset, a large-scale multi-modal and multilingual face dataset containing high-quality images, semantic segmentations, facial landmarks, and different captions for each image in multiple languages. The code and the dataset will be released upon publication.

Predicting 3D human poses in real-world scenarios, also known as human pose forecasting, is inevitably subject to noisy inputs arising from inaccurate 3D pose estimations and occlusions. To address these challenges, we propose a diffusion-based approach that can predict given noisy observations. We frame the prediction task as a denoising problem, where both observation and prediction are considered as a single sequence containing missing elements (whether in the observation or prediction horizon). All missing elements are treated as noise and denoised with our conditional diffusion model. To better handle long-term forecasting horizon, we present a temporal cascaded diffusion model. We demonstrate the benefits of our approach on four publicly available datasets (Human3.6M, HumanEva-I, AMASS, and 3DPW), outperforming the state-of-the-art. Additionally, we show that our framework is generic enough to improve any 3D pose prediction model as a pre-processing step to repair their inputs and a post-processing step to refine their outputs. The code is available online: \url{https://github.com/vita-epfl/DePOSit}.