Learning-based robotics research driven by data demands a new approach to robot hardware design-one that serves as both a platform for policy execution and a tool for embodied data collection to train policies. We introduce ToddlerBot, a low-cost, open-source humanoid robot platform designed for scalable policy learning and research in robotics and AI. ToddlerBot enables seamless acquisition of high-quality simulation and real-world data. The plug-and-play zero-point calibration and transferable motor system identification ensure a high-fidelity digital twin, enabling zero-shot policy transfer from simulation to the real world. A user-friendly teleoperation interface facilitates streamlined real-world data collection for learning motor skills from human demonstrations. Utilizing its data collection ability and anthropomorphic design, ToddlerBot is an ideal platform to perform whole-body loco-manipulation. Additionally, ToddlerBot's compact size (0.56m, 3.4kg) ensures safe operation in real-world environments. Reproducibility is achieved with an entirely 3D-printed, open-source design and commercially available components, keeping the total cost under 6,000 USD. Comprehensive documentation allows assembly and maintenance with basic technical expertise, as validated by a successful independent replication of the system. We demonstrate ToddlerBot's capabilities through arm span, payload, endurance tests, loco-manipulation tasks, and a collaborative long-horizon scenario where two robots tidy a toy session together. By advancing ML-compatibility, capability, and reproducibility, ToddlerBot provides a robust platform for scalable learning and dynamic policy execution in robotics research.

Spiking Neural Networks (SNNs) are emerging as a promising alternative to Artificial Neural Networks (ANNs) due to their inherent energy efficiency. Owing to the inherent sparsity in spike generation within SNNs, the in-depth analysis and optimization of intermediate output spikes are often neglected. This oversight significantly restricts the inherent energy efficiency of SNNs and diminishes their advantages in spatiotemporal feature extraction, resulting in a lack of accuracy and unnecessary energy expenditure. In this work, we analyze the inherent spiking characteristics of SNNs from both temporal and spatial perspectives. In terms of spatial analysis, we find that shallow layers tend to focus on learning vertical variations, while deeper layers gradually learn horizontal variations of features. Regarding temporal analysis, we observe that there is not a significant difference in feature learning across different time steps. This suggests that increasing the time steps has limited effect on feature learning. Based on the insights derived from these analyses, we propose a Frequency-based Spatial-Temporal Attention (FSTA) module to enhance feature learning in SNNs. This module aims to improve the feature learning capabilities by suppressing redundant spike features.The experimental results indicate that the introduction of the FSTA module significantly reduces the spike firing rate of SNNs, demonstrating superior performance compared to state-of-the-art baselines across multiple datasets.

Materials design is an important component of modern science and technology, yet traditional approaches rely heavily on trial-and-error and can be inefficient. Computational techniques, enhanced by modern artificial intelligence (AI), have greatly accelerated the design of new materials. Among these approaches, inverse design has shown great promise in designing materials that meet specific property requirements. In this mini-review, we summarize key computational advancements for materials design over the past few decades. We follow the evolution of relevant materials design techniques, from high-throughput forward machine learning (ML) methods and evolutionary algorithms, to advanced AI strategies like reinforcement learning (RL) and deep generative models. We highlight the paradigm shift from conventional screening approaches to inverse generation driven by deep generative models. Finally, we discuss current challenges and future perspectives of materials inverse design. This review may serve as a brief guide to the approaches, progress, and outlook of designing future functional materials with technological relevance.

Generating novel crystalline materials has potential to lead to advancements in fields such as electronics, energy storage, and catalysis. The defining characteristic of crystals is their symmetry, which plays a central role in determining their physical properties. However, existing crystal generation methods either fail to generate materials that display the symmetries of real-world crystals, or simply replicate the symmetry information from examples in a database. To address this limitation, we propose SymmCD, a novel diffusion-based generative model that explicitly incorporates crystallographic symmetry into the generative process. We decompose crystals into two components and learn their joint distribution through diffusion: 1) the asymmetric unit, the smallest subset of the crystal which can generate the whole crystal through symmetry transformations, and; 2) the symmetry transformations needed to be applied to each atom in the asymmetric unit. We also use a novel and interpretable representation for these transformations, enabling generalization across different crystallographic symmetry groups. We showcase the competitive performance of SymmCD on a subset of the Materials Project, obtaining diverse and valid crystals with realistic symmetries and predicted properties.

Based on structured SVM, the authors combine the structured prediction and the learning using hinge loss, the results is a novel model, Graph Structured Prediction Energy Networks. Overall the model is novel and the theory is mostly solid. However, I have some concerns about the inference part. 1. Marginal Polytope. The relaxation of the marginal polytope is always tricky for structured prediction. A loose relaxation might result in an efficient algorithm, but the bad quality of the solution.

All the reviewers thought that generalizing the structured prediction energy network (SPEN) to incorporate factored potentials (following graph structure) with proposed approximate inference schemes for structured prediction make a nice contribution to NeurIPS. The extensive experiments were lauded, but concerns were expressed with the theoretical backing of the methods. After discussion and looking at the paper, the AC agrees with R2 that the paper makes an interesting practical contribution, and that the theory could be clarified in follow-up work. The authors should include their timing results as well as additional clarification from the rebuttal in their camera ready version. Additional side notes: - [*] from the rebuttal should be mentioned in the main paper as a way to handle the entropy term over the marginal polytope in a principled manner with Frank-Wolfe.

Large Language Models (LLM)-based systems, i.e. interconnected elements that include an LLM as a central component (e.g., conversational agents), are typically monolithic static architectures that rely on a single LLM for all user queries. However, they often require different preprocessing strategies, levels of reasoning, or knowledge. Generalist LLMs (e.g. GPT-4) trained on very large multi-topic corpora can perform well in a variety of tasks. They require significant financial, energy, and hardware resources that may not be justified for basic tasks. This implies potentially investing in unnecessary costs for a given query. To overcome this problem, a routing mechanism routes user queries to the most suitable components, such as smaller LLMs or experts in specific topics. This approach may improve response quality while minimising costs. Routing can be expanded to other components of the conversational agent architecture, such as the selection of optimal embedding strategies. This paper explores key considerations for integrating routing into LLM-based systems, focusing on resource management, cost definition, and strategy selection. Our main contributions include a formalisation of the problem, a novel taxonomy of existing approaches emphasising relevance and resource efficiency, and a comparative analysis of these strategies in relation to industry practices. Finally, we identify critical challenges and directions for future research.

Residual transformation is critical to improving representational depth and expressive power of large language models (LLMs). However, the use of static residual transformations across all tokens during auto-regressive generation induces a suboptimal balance between inference efficiency and generation fidelity. Existing methods, including Early Exiting, Skip Decoding, and Mixture-of-Depth, attempt to address this by modulating the residual transformation based on token-level complexity. Nevertheless, these approaches predominantly consider the distance traversed by tokens through the model layers, neglecting the underlying velocity of residual evolution. In this work, we introduce Mixture of Multi-rate Residuals, a novel framework that dynamically modulates the velocity of residual transformations to optimize early residual alignment. This modification improves inference efficiency by better aligning intermediate representations at earlier stages. We show the efficacy of our technique in diverse optimization setups such as dynamic computing, speculative decoding, and MoE Ahead-of-Time (AoT) loading using challenging reasoning tasks from Koala, Self-Instruct, WizardLM and MT Bench. Our approach empirically outperforms state-of-the-art distance-based residual strategies, enabling a better trade-off between generation metrics and speedup in dynamic computing settings. In self-speculative decoding setups, M2R2 achieves up to 2.8X speedups on MT-Bench under lossless conditions, outperforming SOTA approaches such as 2-model speculative decoding, Medusa, LookAhead Decoding, and DEED. In Mixture-of-Experts (MoE) architectures, we enhance decoding speed by coupling early residual alignment with ahead-oftime expert loading into high-bandwidth memory (HBM). This enables concurrent memory access and computation, reducing the latency bottlenecks inherent in expert switching during decoding. Empirical results show that our method delivers a speedup of 2.9X in MoE architectures, positioning it as a highly effective strategy in resource-constrained environments.

This paper introduces a learning-based visual planner for agile drone flight in cluttered environments. The proposed planner generates collision-free waypoints in milliseconds, enabling drones to perform agile maneuvers in complex environments without building separate perception, mapping, and planning modules. Learning-based methods, such as behavior cloning (BC) and reinforcement learning (RL), demonstrate promising performance in visual navigation but still face inherent limitations. BC is susceptible to compounding errors due to limited expert imitation, while RL struggles with reward function design and sample inefficiency. To address these limitations, this paper proposes an inverse reinforcement learning (IRL)-based framework for high-speed visual navigation. By leveraging IRL, it is possible to reduce the number of interactions with simulation environments and improve capability to deal with high-dimensional spaces while preserving the robustness of RL policies. A motion primitive-based path planning algorithm collects an expert dataset with privileged map data from diverse environments, ensuring comprehensive scenario coverage. By leveraging both the acquired expert and learner dataset gathered from the agent's interactions with the simulation environments, a robust reward function and policy are learned across diverse states. While the proposed method is trained in a simulation environment only, it can be directly applied to real-world scenarios without additional training or tuning. The performance of the proposed method is validated in both simulation and real-world environments, including forests and various structures. The trained policy achieves an average speed of 7 m/s and a maximum speed of 8.8 m/s in real flight experiments. To the best of our knowledge, this is the first work to successfully apply an IRL framework for high-speed visual navigation of drones.

The fields of MPC and RL consider two successful control techniques for Markov decision processes. Both approaches are derived from similar fundamental principles, and both are widely used in practical applications, including robotics, process control, energy systems, and autonomous driving. Despite their similarities, MPC and RL follow distinct paradigms that emerged from diverse communities and different requirements. Various technical discrepancies, particularly the role of an environment model as part of the algorithm, lead to methodologies with nearly complementary advantages. Due to their orthogonal benefits, research interest in combination methods has recently increased significantly, leading to a large and growing set of complex ideas leveraging MPC and RL. This work illuminates the differences, similarities, and fundamentals that allow for different combination algorithms and categorizes existing work accordingly. Particularly, we focus on the versatile actor-critic RL approach as a basis for our categorization and examine how the online optimization approach of MPC can be used to improve the overall closed-loop performance of a policy.