technocracy

Tldr; my sac model experienced catastrophic failure after 950k steps. Entropy through the roof, mean reward and episode length down to almost 0. What the hell happened?? How do I stop it from happening again? Is the model recoverable? I’ve been working on a bipedal robot with point feet, trying to get it to just pace on the spot. After weeks of models settling on useless policies, I discovered the constraints as terminators (CaT) framework from this paper. […]

Ver mais

arXiv:2602.11321v1 Announce Type: new Abstract: Building a low-latency humanoid teleoperation system is essential for collecting diverse reactive and dynamic demonstrations. However, existing approaches rely on heavily pre-processed human-to-humanoid motion retargeting and position-only PD control, resulting in substantial latency that severely limits responsiveness and prevents tasks requiring rapid feedback and fast reactions. To address this problem, we propose ExtremControl, a low latency whole-body control framework that: (1) operates directly on SE(3) poses of selected rigid links, primarily humanoid extremities, […]

Ver mais

arXiv:2604.16954v1 Announce Type: new Abstract: Category-level object pose estimation is fundamental for embodied intelligence, yet achieving robust generalization to unseen instances remains challenging. However, existing methods mainly rely on simple feature extraction and aggregation, which struggle to capture category-shared topological structures and conduct semantic keypoint modeling, limiting their generalization. To address these, we propose a textbf{T}opology-Aware Learning with textbf{S}emantic textbf{M}amba for Category-Level textbf{P}ose Estimation framework (TSM-Pose). Specifically, we introduce a Topology Extractor to capture the global topological representation […]

Ver mais

Weather data, comprising multiple variables, poses significant challenges due to its high dimensionality and multimodal nature. Creating low-dimensional embeddings requires compressing this data into a compact, shared latent space. This compression is required to improve the efficiency and performance of downstream tasks, such as forecasting or extreme-weather detection. Self-supervised learning, particularly contrastive learning, offers a way to generate low-dimensional, robust embeddings from unlabelled data, enabling downstream tasks when labelled data is scarce. Despite initial exploration of contrastive learning […]

Ver mais

arXiv:2601.16462v1 Announce Type: new Abstract: Retrieval-Augmented Generation (RAG) has emerged as a dominant paradigm for mitigating hallucinations in Large Language Models (LLMs) by incorporating external knowledge. Nevertheless, effectively integrating and interpreting key evidence scattered across noisy documents remains a critical challenge for existing RAG systems. In this paper, we propose GraphAnchor, a novel Graph-Anchored Knowledge Indexing approach that reconceptualizes graph structures from static knowledge representations into active, evolving knowledge indices. GraphAnchor incrementally updates a graph during iterative retrieval […]

Ver mais

Internet of Things (IoT) Analytics often involves applying machine learning (ML) models on data streams. In such scenarios, traditional ML paradigms face obstacles related to continuous learning while dealing with concept drifts, temporal dependence, and avoiding forgetting. Moreover, in IoT, different edge devices build up a network. When learning models on those devices, connecting them could be useful in improving performance and reusing others’ knowledge. This work proposes Mutual Assisted Learning, a learning paradigm grounded on Vygotsky’s popular […]

Ver mais

Deep Neural Networks (DNNs) are increasingly utilized in high-stakes domains like medical diagnostics and autonomous driving where model reliability is critical. However, the research landscape for ensuring this reliability is terminologically fractured across communities that pursue the same goal of ensuring models rely on causally relevant features rather than confounding signals. While frameworks such as distributionally robust optimization (DRO), invariant risk minimization (IRM), shortcut learning, simplicity bias, and the Clever Hans effect all address model failure due to […]

Ver mais