Claims that humanoid robots achieve ``human-level'' actuation are common but rarely quantified. Peak torque or speed specifications tell us little about whether a joint can deliver the right combination of torque, power, and endurance at task-relevant postures and rates. We introduce a comprehensive framework that makes ``human-level'' measurable and comparable across systems. Our approach has three components. First, a kinematic \emph{DoF atlas} standardizes joint coordinate systems and ranges of motion using ISB-based conventions, ensuring that human and robot joints are compared in the same reference frames. Second, \emph{Human-Equivalence Envelopes (HEE)} define per-joint requirements by measuring whether a robot meets human torque \emph{and} power simultaneously at the same joint angle and rate $(q,ω)$, weighted by positive mechanical work in task-specific bands (walking, stairs, lifting, reaching, and hand actions). Third, the \emph{Human-Level Actuation Score (HLAS)} aggregates six physically grounded factors: workspace coverage (ROM and DoF), HEE coverage, torque-mode bandwidth, efficiency, and thermal sustainability. We provide detailed measurement protocols using dynamometry, electrical power monitoring, and thermal testing that yield every HLAS input from reproducible experiments. A worked example demonstrates HLAS computation for a multi-joint humanoid, showing how the score exposes actuator trade-offs (gearing ratio versus bandwidth and efficiency) that peak-torque specifications obscure. The framework serves as both a design specification for humanoid development and a benchmarking standard for comparing actuation systems, with all components grounded in published human biomechanics data.

The quadratic cost of scaled dot-product attention is a central obstacle to scaling autoregressive language models to long contexts. Linear-time attention and State Space Models (SSMs) provide scalable alternatives but are typically restricted to first-order or kernel-based approximations, which can limit expressivity. We introduce Higher-order Linear Attention (HLA), a causal, streaming mechanism that realizes higher interactions via compact prefix sufficient statistics. In the second-order case, HLA maintains a constant-size state and computes per-token outputs in linear time without materializing any $n \times n$ matrices. We give closed-form streaming identities, a strictly causal masked variant using two additional summaries, and a chunk-parallel training scheme based on associative scans that reproduces the activations of a serial recurrence exactly. We further outline extensions to third and higher orders. Collectively, these results position HLA as a principled, scalable building block that combines attention-like, data-dependent mixing with the efficiency of modern recurrent architectures. Project Page: https://github.com/yifanzhang-pro/HLA.

It has become increasingly important to optimize backpropagation to reduce memory usage and computational overhead. Achieving this goal is highly challenging, as multiple objectives must be considered jointly while maintaining training quality. In this paper, we focus on matrix multiplication, which accounts for the largest portion of training costs, and analyze its backpropagation in detail to identify lightweight techniques that offer the best benefits. Based on this analysis, we introduce a novel method, Hadamard-based Optimized Training (HOT). In this approach, we apply Hadamard-based optimizations, such as Hadamard quantization and Hadamard low-rank approximation, selectively and with awareness of the suitability of each optimization for different backward paths. Additionally, we introduce two enhancements: activation buffer compression and layer-wise quantizer selection. Our extensive analysis shows that HOT achieves up to 75% memory savings and a 2.6 times acceleration on real GPUs, with negligible accuracy loss compared to FP32 precision.

Humanoid robots must master numerous tasks with sparse rewards, posing a challenge for reinforcement learning (RL). We propose a method combining RL and automated planning to address this. Our approach uses short goal-conditioned policies (GCPs) organized hierarchically, with Monte Carlo Tree Search (MCTS) planning using high-level actions (HLAs). Instead of primitive actions, the planning process generates HLAs. A single plan-tree, maintained during the agent's lifetime, holds knowledge about goal achievement. This hierarchy enhances sample efficiency and speeds up reasoning by reusing HLAs and anticipating future actions. Our Hierarchical Goal-Conditioned Policy Planning (HGCPP) framework uniquely integrates GCPs, MCTS, and hierarchical RL, potentially improving exploration and planning in complex tasks.

With the rapid increase in model size and the growing importance of various fine-tuning applications, lightweight training has become crucial. Since the backward pass is twice as expensive as the forward pass, optimizing backpropagation is particularly important. However, modifications to this process can lead to suboptimal convergence, so training optimization should minimize perturbations, which is a highly challenging task. In this study, we introduce a novel optimization strategy called Hadamard Low-rank Quantization (HLQ), focusing on reducing the cost of backpropagation in convolutional and linear layers. We first analyze the sensitivity of gradient computation with respect to activation and weight, and judiciously design the HLQ pipeline to apply 4-bit Hadamard quantization to the activation gradient and Hadamard low-rank approximation to the weight gradient. This combination was found to be the best for maximizing benefits, and our extensive experiments demonstrate the outstanding performance of HLQ in both training from scratch and fine-tuning, achieving significant memory savings and acceleration on real GPUs with negligible quality degradation.

Learning anticipation is a reasoning paradigm in multi-agent reinforcement learning, where agents, during learning, consider the anticipated learning of other agents. There has been substantial research into the role of learning anticipation in improving cooperation among self-interested agents in general-sum games. Two primary examples are Learning with Opponent-Learning Awareness (LOLA), which anticipates and shapes the opponent's learning process to ensure cooperation among self-interested agents in various games such as iterated prisoner's dilemma, and Look-Ahead (LA), which uses learning anticipation to guarantee convergence in games with cyclic behaviors. So far, the effectiveness of applying learning anticipation to fully-cooperative games has not been explored. In this study, we aim to research the influence of learning anticipation on coordination among common-interested agents. We first illustrate that both LOLA and LA, when applied to fully-cooperative games, degrade coordination among agents, causing worst-case outcomes. Subsequently, to overcome this miscoordination behavior, we propose Hierarchical Learning Anticipation (HLA), where agents anticipate the learning of other agents in a hierarchical fashion. Specifically, HLA assigns agents to several hierarchy levels to properly regulate their reasonings. Our theoretical and empirical findings confirm that HLA can significantly improve coordination among common-interested agents in fully-cooperative normal-form games. With HLA, to the best of our knowledge, we are the first to unlock the benefits of learning anticipation for fully-cooperative games.

For conversational AI and virtual assistants to communicate with humans in a realistic way, they must exhibit human characteristics such as expression of emotion and personality. Current attempts toward constructing human-like dialogue agents have presented significant difficulties. We propose Human Level Attributes (HLAs) based on tropes as the basis of a method for learning dialogue agents that can imitate the personalities of fictional characters. Tropes are characteristics of fictional personalities that are observed recurrently and determined by viewers' impressions. By combining detailed HLA data with dialogue data for specific characters, we present a dataset that models character profiles and gives dialogue agents the ability to learn characters' language styles through their HLAs. We then introduce a three-component system, ALOHA (which stands for Artificial Learning On Human Attributes), that combines character space mapping, character community detection, and language style retrieval to build a character (or personality) specific language model. Our preliminary experiments demonstrate that ALOHA, combined with our proposed dataset, can outperform baseline models at identifying correct dialogue responses of any chosen target character, and is stable regardless of the character's identity, genre of the show, and context of the dialogue.

Humans somehow manage to choose quite intelligently planner should fill in to produce a concrete plan that accomplishes the 20 trillion primitive motor commands that constitute a the goal as quickly as possible. It has long been thought that hierarchical structure in Planning at multiple levels of abstraction has long been a behavior is essential in managing this complexity. For instance, Shakey the exists at many levels, ranging from small (hundred-step?) robot used STRIPS for high-level task planning, then called motor programs for typing characters and saying phonemes out to separate low-level planning/control algorithms to execute up to large (billion-step?) actions such as writing an ICAPS each of the planned actions (Fikes and Nilsson 1971). This hard separation of levels, where a high-level plan is We believe that leveraging hierarchical structure will be chosen before considering low-level details, greatly simplifies equally important in achieving robust, efficient robotic behaviors. However, the resulting plans While your household robot probably won't get may be inefficient or even infeasible due to missed lowerlevel tenure anytime soon, even simple domestic tasks still have synergies and conflicts.