Many roboticists dream of presenting a robot with a task in the evening and returning the next morning to find the robot capable of solving the task. What is preventing us from achieving this? Sim-to-real reinforcement learning (RL) has achieved impressive performance on challenging robotics tasks, but requires substantial human effort to set up the task in a way that is amenable to RL. It's our position that algorithmic improvements in policy optimization and other ideas should be guided towards resolving the primary bottleneck of shaping the training environment, i.e., designing observations, actions, rewards and simulation dynamics. Most practitioners don't tune the RL algorithm, but other environment parameters to obtain a desirable controller. We posit that scaling RL to diverse robotic tasks will only be achieved if the community focuses on automating environment shaping procedures.

Semantic Scene Completion (SSC) is pivotal in autonomous driving perception, frequently confronted with the complexities of weather and illumination changes. The long-term strategy involves fusing multi-modal information to bolster the system's robustness. Radar, increasingly utilized for 3D target detection, is gradually replacing LiDAR in autonomous driving applications, offering a robust sensing alternative. In this paper, we focus on the potential of 3D radar in semantic scene completion, pioneering cross-modal refinement techniques for improved robustness against weather and illumination changes, and enhancing SSC performance.Regarding model architecture, we propose a three-stage tight fusion approach on BEV to realize a fusion framework for point clouds and images. Based on this foundation, we designed three cross-modal distillation modules-CMRD, BRD, and PDD. Our approach enhances the performance in both radar-only (R-LiCROcc) and radar-camera (RC-LiCROcc) settings by distilling to them the rich semantic and structural information of the fused features of LiDAR and camera. Finally, our LC-Fusion (teacher model), R-LiCROcc and RC-LiCROcc achieve the best performance on the nuScenes-Occupancy dataset, with mIOU exceeding the baseline by 22.9%, 44.1%, and 15.5%, respectively. The project page is available at https://hr-zju.github.io/LiCROcc/.

In this work, we propose Wasserstein distributionally robust shallow convex neural networks (WaDiRo-SCNNs) to provide reliable nonlinear predictions when subject to adverse and corrupted datasets. Our approach is based on a new convex training program for ReLU shallow neural networks which allows us to cast the problem as an exact, tractable reformulation of its order-1 Wasserstein distributionally robust equivalent. Our training procedure is conservative by design, has low stochasticity, is solvable with open-source solvers, and is scalable to large industrial deployments. We provide out-of-sample performance guarantees and show that hard convex physical constraints can be enforced in the training program. WaDiRo-SCNN aims to make neural networks safer for critical applications, such as in the energy sector. Finally, we numerically demonstrate the performance of our model on a synthetic experiment and a real-world power system application, i.e., the prediction of nonresidential buildings' hourly energy consumption. The experimental results are convincing and showcase the strengths of the proposed model. Keywords: distributionally robust optimization, shallow convex neural networks, trustworthy machine learning, physics constrained, energy.

Question Answering (QA) effectively evaluates language models' reasoning and knowledge depth. While QA datasets are plentiful in areas like general domain and biomedicine, academic chemistry is less explored. Chemical QA plays a crucial role in both education and research by effectively translating complex chemical information into readily understandable format. Addressing this gap, we introduce ScholarChemQA, a large-scale QA dataset constructed from chemical papers. This dataset reflects typical real-world challenges, including an imbalanced data distribution and a substantial amount of unlabeled data that can be potentially useful. Correspondingly, we introduce a QAMatch model, specifically designed to effectively answer chemical questions by fully leveraging our collected data. We first address the issue of imbalanced label distribution by re-weighting the instance-wise loss based on the inverse frequency of each class, ensuring minority classes are not dominated by majority ones during optimization. Next, we utilize the unlabeled data to enrich the learning process, generating a variety of augmentations based on a SoftMix operation and ensuring their predictions align with the same target, i.e., pseudo-labels. To ensure the quality of the pseudo-labels, we propose a calibration procedure aimed at closely aligning the pseudo-label estimates of individual samples with a desired ground truth distribution. Experiments show that our QAMatch significantly outperforms the recent similar-scale baselines and Large Language Models (LLMs) not only on our ScholarChemQA dataset but also on four benchmark datasets. We hope our benchmark and model can facilitate and promote more research on chemical QA.

Transferring learned skills across diverse situations remains a fundamental challenge for autonomous agents, particularly when agents are not allowed to interact with an exact target setup. While prior approaches have predominantly focused on learning domain translation, they often struggle with handling significant domain gaps or out-of-distribution tasks. In this paper, we present a simple approach for cross-domain policy transfer that learns a shared latent representation across domains and a common abstract policy on top of it. Our approach leverages multi-domain behavioral cloning on unaligned trajectories of proxy tasks and employs maximum mean discrepancy (MMD) as a regularization term to encourage cross-domain alignment. The MMD regularization better preserves structures of latent state distributions than commonly used domain-discriminative distribution matching, leading to higher transfer performance. Moreover, our approach involves training only one multi-domain policy, which makes extension easier than existing methods. Empirical evaluations demonstrate the efficacy of our method across various domain shifts, especially in scenarios where exact domain translation is challenging, such as cross-morphology or cross-viewpoint settings. Our ablation studies further reveal that multi-domain behavioral cloning implicitly contributes to representation alignment alongside domain-adversarial regularization. Humans have an astonishing ability to learn skills in a highly transferable way. Once we learn a route from home to the station, for example, we can get to the destination using various modes of transportation (e.g., walking, cycling, or driving) in different environments (e.g., on a map or in the real world), disregarding irrelevant perturbations (e.g., weather, time, or traffic conditions). We identify the underlying structural similarities across situations, perceive the world, and accumulate knowledge in our way of abstraction. Such abstract knowledge can be readily employed in diverse similar situations. However, it is not easy for autonomous agents. Agents trained with reinforcement learning (RL) or imitation learning (IL) often struggle to transfer knowledge acquired in a specific situation to another. This is because the learned policies are strongly tied to the representations obtained under a particular training configuration, which is not robust to changes in an agent or an environment. Previous studies have attempted to address this problem through various approaches. Domain randomization (Tobin et al., 2017; Peng et al., 2018; Andrychowicz et al., 2020) aims to learn a policy that is robust to environmental changes by utilizing multiple training domains. However, it is unable to handle significant domain gaps that go beyond the assumed domain distribution during training, such as drastically different observations or agent morphologies. Numerous methods have been proposed to overcome such domain discrepancies.

Cross-domain Aspect Sentiment Triplet Extraction (ASTE) aims to extract fine-grained sentiment elements from target domain sentences by leveraging the knowledge acquired from the source domain. Due to the absence of labeled data in the target domain, recent studies tend to rely on pre-trained language models to generate large amounts of synthetic data for training purposes. However, these approaches entail additional computational costs associated with the generation process. Different from them, we discover a striking resemblance between table-filling methods in ASTE and two-stage Object Detection (OD) in computer vision, which inspires us to revisit the cross-domain ASTE task and approach it from an OD standpoint. This allows the model to benefit from the OD extraction paradigm and region-level alignment. Building upon this premise, we propose a novel method named \textbf{T}able-\textbf{F}illing via \textbf{M}ean \textbf{T}eacher (TFMT). Specifically, the table-filling methods encode the sentence into a 2D table to detect word relations, while TFMT treats the table as a feature map and utilizes a region consistency to enhance the quality of those generated pseudo labels. Additionally, considering the existence of the domain gap, a cross-domain consistency based on Maximum Mean Discrepancy is designed to alleviate domain shift problems. Our method achieves state-of-the-art performance with minimal parameters and computational costs, making it a strong baseline for cross-domain ASTE.

In the last decade, the widespread advances in computer science and its growing presence into the organization of everyday life have established a strong interest in its inclusion in the school curriculum. The recent mass dissemination of generative artificial intelligence (AI) tools has only strengthened this interest worldwide. In Latin America, for example, the Omar Dengo Foundation and the Ministry of Education in Costa Rica have led the design and implementation of the National Computing Program in schools. Other countries, such as Uruguay or Chile, are taking steps forward through different initiatives.4 In Argentina, a public ICT institution called the Sadosky Foundationa launched the Program.AR Initiative in 2013 and has since developed a comprehensive policy for the inclusion of computer science in the formal schooling system of Argentina.

The world's shortest IQ test not only reveals your intelligence but also your level of patience. The test, called a Cognitive Reflection Test (CRT), consists of three math-based questions that target a person's ability to ignore their initial gut response in favor of a more rational thought process. Many quickly assume the answers are simple, but the Yale University professor who created the exam warned it isn't as straightforward as it may seem. Professor Shane Frederick created the CRT in 2005 and only 20 to 40 percent of students who have attempted it have passed. A Yale University professor designed a Cognitive Reflection Test ( CRT) that consists of three math-based questions that target a person's ability to ignore their initial gut response in favor of a more rational thought process Mathematical brain teasers are useful in helping people develop logical thinking by promoting brain stimulation and build visual and spatial reasoning skills.

Training intelligent agents to navigate highly interactive environments presents significant challenges. While guided meta reinforcement learning (RL) approach that first trains a guiding policy to train the ego agent has proven effective in improving generalizability across various levels of interaction, the state-of-the-art method tends to be overly sensitive to extreme cases, impairing the agents' performance in the more common scenarios. This study introduces a novel training framework that integrates guided meta RL with importance sampling (IS) to optimize training distributions for navigating highly interactive driving scenarios, such as T-intersections. Unlike traditional methods that may underrepresent critical interactions or overemphasize extreme cases during training, our approach strategically adjusts the training distribution towards more challenging driving behaviors using IS proposal distributions and applies the importance ratio to de-bias the result. By estimating a naturalistic distribution from real-world datasets and employing a mixture model for iterative training refinements, the framework ensures a balanced focus across common and extreme driving scenarios. Experiments conducted with both synthetic dataset and T-intersection scenarios from the InD dataset demonstrate not only accelerated training but also improvement in agent performance under naturalistic conditions, showcasing the efficacy of combining IS with meta RL in training reliable autonomous agents for highly interactive navigation tasks.

Similarly to the factors of anthropomorphism summarized by [11], we identified the following factors as relevant when Large Language Models (LLMs) are increasingly being used LLM-based chatbots are used in learning scenarios: The learning in learning environments to support teaching--be it as learning agent, i.e., chatbot, the learner itself, and environmental companions or as tutors [1]-[3]. With our contribution, we factors which influence the learner (see Figure 1). According to the media equation [4], people tend to respond to media in the same way as they would respond to another person. A study conducted by the Georgia Institute of Technology showed that chatbots can be successfully implemented in learning environments. As LLM-based chatbots such as OpenAI's GPT Looking at the agent, several factors can contribute to series are increasingly used in educational tools, it is important anthropomorphization. Cognitive intelligence refers to the to understand how the attribution processes to LLM-based ability to perceive, reason, and act on problems; to combine chatbots in terms of anthropomorphization affect learners' efficient, useful, goal-oriented, and autonomous actions with emotions.