technocracy

arXiv:2602.16726v1 Announce Type: new Abstract: Large-scale human mobility simulation is critical for many science domains such as urban science, epidemiology, and transportation analysis. Recent works treat large language models (LLMs) as human agents to simulate realistic mobility trajectories by modeling individual-level cognitive processes. However, these approaches generate individual mobility trajectories independently, without any population-level coordination mechanism, and thus fail to capture the emergence of collective behaviors. To address this issue, we design M2LSimu, a mobility measures-guided multi-prompt adjustment […]

Ver mais

We study training algorithms with data following a Gaussian mixture model. For a specific family of such algorithms, we present a non-asymptotic result, connecting the evolution of the model to a surrogate dynamical system, which can be easier to analyze. The proof of our result is based on the celebrated Gordon comparison theorem. Using our theorem, we rigorously prove the validity of the dynamic mean-field (DMF) expressions in the asymptotic scenarios. Moreover, we suggest an iterative refinement scheme […]

Ver mais

arXiv:2011.07687v2 Announce Type: replace-cross Abstract: We consider the bandit problem of selecting $K$ out of $N$ arms at each time step. The reward can be a non-linear function of the rewards of the selected individual arms. The direct use of a multi-armed bandit algorithm requires choosing among $binom{N}{K}$ options, making the action space large. To simplify the problem, existing works on combinatorial bandits {typically} assume feedback as a linear function of individual rewards. In this paper, we prove […]

Ver mais

arXiv:2602.10464v1 Announce Type: cross Abstract: Recent advances in artificial intelligence have enabled the generation of large-scale, low-cost predictions with increasingly high fidelity. As a result, the primary challenge in statistical inference has shifted from data scarcity to data reliability. Prediction-powered inference methods seek to exploit such predictions to improve efficiency when labeled data are limited. However, existing approaches implicitly adopt a use-all philosophy, under which incorporating more predictions is presumed to improve inference. When prediction quality is heterogeneous, […]

Ver mais

Mesh-free numerical methods provide flexible discretisations for complex geometries; however, classical meshless discrete differential operators typically trade low computational cost for limited accuracy or high accuracy for substantial per-stencil computation. We introduce a parametrised framework for learning mesh-free discrete differential operators using a graph neural network trained via polynomial moment constraints derived from truncated Taylor expansions. The model maps local stencils relative positions directly to discrete operator weights. The current work demonstrates that neural networks can learn classical […]

Ver mais

arXiv:2604.06188v1 Announce Type: new Abstract: People increasingly hold sustained, open-ended conversations with large language models (LLMs). Public reports and early studies suggest that, in such settings, models can reinforce delusional or conspiratorial ideation or even amplify harmful beliefs and engagement patterns. We present an audit and benchmarking study that measures how different LLMs encourage, resist, or escalate disordered and conspiratorial thinking. We explicitly compare API outputs to user chat interfaces, like the ChatGPT desktop app or web interface, […]

Ver mais

Decoding from large language models (LLMs) typically relies on fixed sampling hyperparameters (e.g., temperature, top-p), despite substantial variation in task difficulty and uncertainty across prompts and individual decoding steps. We propose to learn adaptive decoding policies that dynamically select sampling strategies at inference time, conditioned on available compute resources. Rather than fine-tuning the language model itself, we introduce lightweight decoding adapters trained with reinforcement learning and verifiable terminal rewards (e.g. correctness on math and coding tasks). At the […]

Ver mais

arXiv:2602.12461v1 Announce Type: new Abstract: Recent studies have shown that CLIP model’s adversarial robustness in zero-shot classification tasks can be enhanced by adversarially fine-tuning its image encoder with adversarial examples (AEs), which are generated by minimizing the cosine similarity between images and a hand-crafted template (e.g., ”A photo of a {label}”). However, it has been shown that the cosine similarity between a single image and a single hand-crafted template is insufficient to measure the similarity for image-text pairs. […]

Ver mais

While everyone argues about which chatbot is marginally smarter, the real edge is in pipelines. Before 6–8 hours per company Bloomberg → Excel → EDGAR → news $24k/year Bloomberg seat Static assumptions, one “price target” After One command, ~2.5 minutes Live data from free public APIs $0 marginal cost per run Bull / Base / Bear + stress tests I realized this after watching a friend spent an entire day updating a single DCF model. Smart work buried […]

Ver mais

Multi–task learning seeks to improve the generalization error by leveraging the common information shared by multiple related tasks. One challenge in multi–task learning is identifying formulations capable of uncovering the common information shared between different but related tasks. This paper provides a precise asymptotic analysis of a popular multi–task formulation associated with misspecified perceptron learning models. The main contribution of this paper is to precisely determine the reasons behind the benefits gained from combining multiple related tasks. Specifically, […]

Ver mais