technocracy

arXiv:2604.08578v1 Announce Type: new Abstract: High-quality labeled data is critical for training reliable machine learning and deep learning models, yet manual annotation remains costly and error-prone. Programmatic labeling addresses this challenge by using label functions (LFs), i.e., heuristic rules that automatically generate weak labels for training datasets. However, existing automated LF generation methods either rely on large language models (LLMs) to synthesize surface-level heuristics or employ model-based synthesis over hand-crafted primitives. These approaches often result in limited coverage […]

Ver mais

arXiv:2602.09038v1 Announce Type: new Abstract: LLMs have recently shown strong potential in enhancing node-level tasks on text-attributed graphs (TAGs) by providing explanation features. However, their practical use is severely limited by the high computational and monetary cost of repeated LLM queries. To illustrate, naively generating explanations for all nodes on a medium-sized benchmark like Photo (48k nodes) using a representative method (e.g., TAPE) would consume days of processing time. In this paper, we propose Bilevel-Optimized Sparse Querying (BOSQ), […]

Ver mais

arXiv:2603.00598v1 Announce Type: new Abstract: Research in Human-Computer Interaction (HCI) has shown that caring for others, including both humans (e.g., close friends) and computers (e.g., Tamagotchi), can have a positive effect on people’s wellbeing. However, we know less about the potential role of conversational AI in such settings. In this work, we explore how AI chatbots can support plant care and, in turn, positively influence people’s well-being. We developed a mobile application that allows users to `talk’ to […]

Ver mais

arXiv:2601.18858v1 Announce Type: new Abstract: Compositional generalization-the ability to interpret novel combinations of familiar components-remains a persistent challenge for neural networks. Behavioral evaluations reveal when models fail but offer limited insight into why failures arise at the representational level. We introduce Homomorphism Error (HE), a structural metric that quantifies deviations from approximate homomorphisms between the expression algebra and a model’s hidden-state space. We instantiate HE for two compositional operators in SCAN-style tasks: modifier HE for unary composition and […]

Ver mais

Standard deep learning relies on Backpropagation (BP), which is constrained by biologically implausible weight symmetry and suffers from significant gradient interference within dense representations. To mitigate these bottlenecks, we propose Selective Adaptive Learning (SAL), a training method that combines selective parameter activation with adaptive area partitioning. Specifically, SAL decomposes the parameter space into mutually exclusive, sample-dependent regions. This decoupling mitigates gradient interference across divergent semantic patterns and addresses explicit weight symmetry requirements through our refined feedback alignment. Empirically, […]

Ver mais