technocracy

Continual reinforcement learning must balance retention with adaptation, yet many methods still rely on emph{single-model preservation}, committing to one evolving policy as the main reusable solution across tasks. Even when a previously successful policy is retained, it may no longer provide a reliable starting point for rapid adaptation after interference, reflecting a form of emph{loss of plasticity} that single-policy preservation cannot address. Inspired by quality-diversity methods, we introduce textsc{TeLAPA} (Transfer-Enabled Latent-Aligned Policy Archives), a continual RL framework that […]

Ver mais

arXiv:2603.26261v1 Announce Type: cross Abstract: Contrastive learning produces coherent semantic feature embeddings by encouraging positive samples to cluster closely while separating negative samples. However, existing contrastive learning methods lack principled guarantees on coverage within the semantic feature space. We extend conformal prediction to this setting by introducing minimum-volume covering sets equipped with learnable generalized multi-norm constraints. We propose a method that constructs conformal sets guaranteeing user-specified coverage of positive samples while maximizing negative sample exclusion. We establish theoretically […]

Ver mais

Privacy-preserving training on sensitive data commonly relies on differentially private stochastic optimization with gradient clipping and Gaussian noise. The clipping threshold is a critical control knob: if set too small, systematic over-clipping induces optimization bias; if too large, injected noise dominates updates and degrades accuracy. Existing adaptive clipping methods often depend on per-example gradient norm statistics, adding computational overhead and introducing sensitivity to datasets and architectures. We propose a control-driven clipping strategy that adapts the threshold using a […]

Ver mais

We have witnessed remarkable advances in LLM reasoning capabilities with the advent of DeepSeek-R1. However, much of this progress has been fueled by the abundance of internet question-answer (QA) pairs, a major bottleneck going forward, since such data is limited in scale and concentrated mainly in domains like mathematics. In contrast, other sciences such as physics lack large-scale QA datasets to effectively train reasoning-capable models. In this work, we show that physics simulators can serve as a powerful […]

Ver mais

arXiv:2604.05039v1 Announce Type: new Abstract: Humans have remarkable selective sensitivity to identities — easily distinguishing between highly similar identities, even across significantly different contexts such as diverse viewpoints or lighting. Vision models have struggled to match this capability, and progress toward identity-focused tasks such as personalized image generation is slowed by a lack of identity-focused evaluation metrics. To help facilitate progress, we propose ID-Sim, a feed-forward metric designed to faithfully reflect human selective sensitivity. To build ID-Sim, we […]

Ver mais

arXiv:2602.06253v1 Announce Type: new Abstract: We develop a second-order extension of intuitionistic modal logic, allowing quantification over propositions, both syntactically and semantically. A key feature of second-order logic is its capacity to define positive connectives from the negative fragment. Duly we are able to recover the diamond (and its associated theory) using only boxes, as long as we include both forward and backward modalities (`tense’ modalities). We propose axiomatic, proof theoretic and model theoretic definitions of `second-order intuitionistic […]

Ver mais

arXiv:2407.10417v2 Announce Type: replace Abstract: A fundamental challenge in machine learning is the choice of a loss as it characterizes our learning task, is minimized in the training phase, and serves as an evaluation criterion for estimators. Proper losses are commonly chosen, ensuring minimizers of the full risk match the true probability vector. Estimators induced from a proper loss are widely used to construct forecasters for downstream tasks such as classification and ranking. In this procedure, how does […]

Ver mais

Table of Links Abstract and 1. Introduction Related Works Convex Relaxation Techniques for Hyperbolic SVMs 3.1 Preliminaries 3.2 Original Formulation of the HSVM 3.3 Semidefinite Formulation 3.4 Moment-Sum-of-Squares Relaxation Experiments 4.1 Synthetic Dataset 4.2 Real Dataset Discussions, Acknowledgements, and References A. Proofs B. Solution Extraction in Relaxed Formulation C. On Moment Sum-of-Squares Relaxation Hierarchy D. Platt Scaling [31] E. Detailed Experimental Results F. Robust Hyperbolic Support Vector Machine Abstract Hyperbolic spaces have increasingly been recognized for their outstanding […]

Ver mais

arXiv:2603.12382v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) have advanced from image-level reasoning to pixel-level grounding, but extending these capabilities to videos remains challenging as models must achieve spatial precision and temporally consistent reference tracking. Existing video MLLMs often rely on a static segmentation token ([SEG]) for frame-wise grounding, which provides semantics but lacks temporal context, causing spatial drift, identity switches, and unstable initialization when objects move or reappear. We introduce SPARROW, a pixel-grounded video MLLM […]

Ver mais