New Natural Langauge Process (NLP) benchmarks are urgently needed to align with the rapid development of large language models (LLMs). We present Xiezhi, the most comprehensive evaluation suite designed to assess holistic domain knowledge. Xiezhi comprises multiple-choice questions across 516 diverse disciplines ranging from 13 different subjects with 249,587 questions and accompanied by Xiezhi-Specialty and Xiezhi-Interdiscipline, both with 15k questions. We conduct evaluation of the 47 cutting-edge LLMs on Xiezhi. Results indicate that LLMs exceed average performance of humans in science, engineering, agronomy, medicine, and art, but fall short in economics, jurisprudence, pedagogy, literature, history, and management.

Humans navigate in their environment by learning a mental model of the world through passive observation and active interaction. Their world model allows them to anticipate what might happen next and act accordingly with respect to an underlying objective. Such world models hold strong promises for planning in complex environments like in autonomous driving. A human driver, or a self-driving system, perceives their surroundings with their eyes or their cameras. They infer an internal representation of the world which should: (i) have spatial memory (e.g. occlusions), (ii) fill partially observable or noisy inputs (e.g. when blinded by sunlight), and (iii) be able to reason about unobservable events probabilistically (e.g. predict different possible futures). They are embodied intelligent agents that can predict, plan, and act in the physical world through their world model. In this thesis we present a general framework to train a world model and a policy, parameterised by deep neural networks, from camera observations and expert demonstrations. We leverage important computer vision concepts such as geometry, semantics, and motion to scale world models to complex urban driving scenes. First, we propose a model that predicts important quantities in computer vision: depth, semantic segmentation, and optical flow. We then use 3D geometry as an inductive bias to operate in the bird's-eye view space. We present for the first time a model that can predict probabilistic future trajectories of dynamic agents in bird's-eye view from 360{\deg} surround monocular cameras only. Finally, we demonstrate the benefits of learning a world model in closed-loop driving. Our model can jointly predict static scene, dynamic scene, and ego-behaviour in an urban driving environment.

This paper studies recent developments in large language models' (LLM) abilities to pass assessments in introductory and intermediate Python programming courses at the postsecondary level. The emergence of ChatGPT resulted in heated debates of its potential uses (e.g., exercise generation, code explanation) as well as misuses in programming classes (e.g., cheating). Recent studies show that while the technology performs surprisingly well on diverse sets of assessment instruments employed in typical programming classes the performance is usually not sufficient to pass the courses. The release of GPT-4 largely emphasized notable improvements in the capabilities related to handling assessments originally designed for human test-takers. This study is the necessary analysis in the context of this ongoing transition towards mature generative AI systems. Specifically, we report the performance of GPT-4, comparing it to the previous generations of GPT models, on three Python courses with assessments ranging from simple multiple-choice questions (no code involved) to complex programming projects with code bases distributed into multiple files (599 exercises overall). Additionally, we analyze the assessments that were not handled well by GPT-4 to understand the current limitations of the model, as well as its capabilities to leverage feedback provided by an auto-grader. We found that the GPT models evolved from completely failing the typical programming class' assessments (the original GPT-3) to confidently passing the courses with no human involvement (GPT-4). While we identified certain limitations in GPT-4's handling of MCQs and coding exercises, the rate of improvement across the recent generations of GPT models strongly suggests their potential to handle almost any type of assessment widely used in higher education programming courses. These findings could be leveraged by educators and institutions to adapt the design of programming assessments as well as to fuel the necessary discussions into how programming classes should be updated to reflect the recent technological developments. This study provides evidence that programming instructors need to prepare for a world in which there is an easy-to-use widely accessible technology that can be utilized by learners to collect passing scores, with no effort whatsoever, on what today counts as viable programming knowledge and skills assessments.

In-context learning (ICL) is one of the most powerful and most unexpected capabilities to emerge in recent transformer-based large language models (LLMs). Yet the mechanisms that underlie it are poorly understood. In this paper, we demonstrate that comparable ICL capabilities can be acquired by an alternative sequence prediction learning method using clone-structured causal graphs (CSCGs). Moreover, a key property of CSCGs is that, unlike transformer-based LLMs, they are {\em interpretable}, which considerably simplifies the task of explaining how ICL works. Specifically, we show that it uses a combination of (a) learning template (schema) circuits for pattern completion, (b) retrieving relevant templates in a context-sensitive manner, and (c) rebinding of novel tokens to appropriate slots in the templates. We go on to marshall evidence for the hypothesis that similar mechanisms underlie ICL in LLMs. For example, we find that, with CSCGs as with LLMs, different capabilities emerge at different levels of overparameterization, suggesting that overparameterization helps in learning more complex template (schema) circuits. By showing how ICL can be achieved with small models and datasets, we open up a path to novel architectures, and take a vital step towards a more general understanding of the mechanics behind this important capability.

This paper investigates an interference-aware joint path planning and power allocation mechanism for a cellular-connected unmanned aerial vehicle (UAV) in a sparse suburban environment. The UAV's goal is to fly from an initial point and reach a destination point by moving along the cells to guarantee the required quality of service (QoS). In particular, the UAV aims to maximize its uplink throughput and minimize the level of interference to the ground user equipment (UEs) connected to the neighbor cellular BSs, considering the shortest path and flight resource limitation. Expert knowledge is used to experience the scenario and define the desired behavior for the sake of the agent (i.e., UAV) training. To solve the problem, an apprenticeship learning method is utilized via inverse reinforcement learning (IRL) based on both Q-learning and deep reinforcement learning (DRL). The performance of this method is compared to learning from a demonstration technique called behavioral cloning (BC) using a supervised learning approach. Simulation and numerical results show that the proposed approach can achieve expert-level performance. We also demonstrate that, unlike the BC technique, the performance of our proposed approach does not degrade in unseen situations.

This article describes and evaluates a new online AI-creativity course. The course is based around three near-state-of-the-art AI models combined into a pop song generating system. A fine-tuned GPT-2 model writes lyrics, Music-VAE composes musical scores and instrumentation and Diffsinger synthesises a singing voice. We explain the decisions made in designing the course which is based on Piagetian, constructivist 'learning-by-doing'. We present details of the five-week course design with learning objectives, technical concepts, and creative and technical activities. We explain how we overcame technical challenges to build a complete pop song generator system, consisting of Python scripts, pre-trained models, and Javascript code that runs in a dockerised Linux container via a web-based IDE. A quantitative analysis of student activity provides evidence on engagement and a benchmark for future improvements. A qualitative analysis of a workshop with experts validated the overall course design, it suggested the need for a stronger creative brief and ethical and legal content.

Few-shot learning (FSL) is one of the significant and hard problems in the field of image classification. However, in contrast to the rapid development of the visible light dataset, the progress in SAR target image classification is much slower. The lack of unified benchmark is a key reason for this phenomenon, which may be severely overlooked by the current literature. The researchers of SAR target image classification always report their new results on their own datasets and experimental setup. It leads to inefficiency in result comparison and impedes the further progress of this area. Motivated by this observation, we propose a novel few-shot SAR image classification benchmark (FewSAR) to address this issue. FewSAR consists of an open-source Python code library of 15 classic methods in three categories for few-shot SAR image classification. It provides an accessible and customizable testbed for different few-shot SAR image classification task. To further understanding the performance of different few-shot methods, we establish evaluation protocols and conduct extensive experiments within the benchmark. By analyzing the quantitative results and runtime under the same setting, we observe that the accuracy of metric learning methods can achieve the best results. Meta-learning methods and fine-tuning methods perform poorly on few-shot SAR images, which is primarily due to the bias of existing datasets. We believe that FewSAR will open up a new avenue for future research and development, on real-world challenges at the intersection of SAR image classification and few-shot deep learning. We will provide our code for the proposed FewSAR at https://github.com/solarlee/FewSAR.

In this paper, we study the role of feedback in online learning with switching costs. It has been shown that the minimax regret is $\widetilde{\Theta}(T^{2/3})$ under bandit feedback and improves to $\widetilde{\Theta}(\sqrt{T})$ under full-information feedback, where $T$ is the length of the time horizon. However, it remains largely unknown how the amount and type of feedback generally impact regret. To this end, we first consider the setting of bandit learning with extra observations; that is, in addition to the typical bandit feedback, the learner can freely make a total of $B_{\mathrm{ex}}$ extra observations. We fully characterize the minimax regret in this setting, which exhibits an interesting phase-transition phenomenon: when $B_{\mathrm{ex}} = O(T^{2/3})$, the regret remains $\widetilde{\Theta}(T^{2/3})$, but when $B_{\mathrm{ex}} = \Omega(T^{2/3})$, it becomes $\widetilde{\Theta}(T/\sqrt{B_{\mathrm{ex}}})$, which improves as the budget $B_{\mathrm{ex}}$ increases. To design algorithms that can achieve the minimax regret, it is instructive to consider a more general setting where the learner has a budget of $B$ total observations. We fully characterize the minimax regret in this setting as well and show that it is $\widetilde{\Theta}(T/\sqrt{B})$, which scales smoothly with the total budget $B$. Furthermore, we propose a generic algorithmic framework, which enables us to design different learning algorithms that can achieve matching upper bounds for both settings based on the amount and type of feedback. One interesting finding is that while bandit feedback can still guarantee optimal regret when the budget is relatively limited, it no longer suffices to achieve optimal regret when the budget is relatively large.

Reinforcement learning (RL) has shown promise in creating robust policies for robotics tasks. However, contemporary RL algorithms are data-hungry, often requiring billions of environment transitions to train successful policies. This necessitates the use of fast and highly-parallelizable simulators. In addition to speed, such simulators need to model the physics of the robots and their interaction with the environment to a level acceptable for transferring policies learned in simulation to reality. We present QuadSwarm, a fast, reliable simulator for research in single and multi-robot RL for quadrotors that addresses both issues. QuadSwarm, with fast forward-dynamics propagation decoupled from rendering, is designed to be highly parallelizable such that throughput scales linearly with additional compute. It provides multiple components tailored toward multi-robot RL, including diverse training scenarios, and provides domain randomization to facilitate the development and sim2real transfer of multi-quadrotor control policies. Initial experiments suggest that QuadSwarm achieves over 48,500 simulation samples per second (SPS) on a single quadrotor and over 62,000 SPS on eight quadrotors on a 16-core CPU. The code can be found in https://github.com/Zhehui-Huang/quad-swarm-rl.

Reinforcement Learning (RL) has shown promising results learning policies for complex tasks, but can often suffer from low sample efficiency and limited transfer. We introduce the Hierarchy of Interaction Skills (HIntS) algorithm, which uses learned interaction detectors to discover and train a hierarchy of skills that manipulate factors in factored environments. Inspired by Granger causality, these unsupervised detectors capture key events between factors to sample efficiently learn useful skills and transfer those skills to other related tasks -- tasks where many reinforcement learning techniques struggle. We evaluate HIntS on a robotic pushing task with obstacles -- a challenging domain where other RL and HRL methods fall short. The learned skills not only demonstrate transfer using variants of Breakout, a common RL benchmark, but also show 2-3x improvement in both sample efficiency and final performance compared to comparable RL baselines. Together, HIntS demonstrates a proof of concept for using Granger-causal relationships for skill discovery.