arXiv:2509.18349v3 Announce Type: replace Abstract: Meta-learning aims to leverage information across related tasks to improve prediction on unlabeled data for new tasks when only a small number of labeled observations are available (“few-shot” learning). Increased task diversity is often believed to enhance meta-learning by providing richer information across tasks. However, recent work by Kumar et al. (2022) shows that increasing task diversity, quantified through the overall geometric spread of task representations, can in fact degrade meta-learning prediction performance […]

Ver mais

arXiv:2601.09805v1 Announce Type: new Abstract: Modern logical reasoning with LLMs primarily relies on employing complex interactive frameworks that decompose the reasoning process into subtasks solved through carefully designed prompts or requiring external resources (e.g., symbolic solvers) to exploit their strong logical structures. While interactive approaches introduce additional overhead, hybrid approaches depend on external components, which limit their scalability. A non-interactive, end-to-end framework enables reasoning to emerge within the model itself — improving generalization while preserving analyzability without any […]

Ver mais

arXiv:2601.05253v1 Announce Type: new Abstract: We introduce $mathbf{SP-Rank}$, the first large-scale, publicly available dataset for benchmarking algorithms that leverage both first-order preferences and second-order predictions in ranking tasks. Each datapoint includes a personal vote (first-order signal) and a meta-prediction of how others will vote (second-order signal), allowing richer modeling than traditional datasets that capture only individual preferences. SP-Rank contains over 12,000 human-generated datapoints across three domains — geography, movies, and paintings, and spans nine elicitation formats with varying […]

Ver mais

We often hear that “neurons” in DNNs are just a loose analogy for biological neurons. The consensus seems to be that while abstract ideas (like hierarchies) match, the actual architectures are fundamentally different, largely because biological mechanisms are seen as either computationally expensive or incompatible with current silicon hardware. However, as I’ve recently begun bridging the gap between my PhD in applied math and a BS in Neuroscience, I’ve started to question if we are moving away from […]

Ver mais

arXiv:2603.00616v1 Announce Type: new Abstract: Modern cyber-physical systems, such as automotive control, rely on feedback controllers that regulate the system towards desired a setpoint. In practice, however, the controller must also be scheduled efficiently on resource-constrained processors, where the choice of numerical precision for controller implementation directly affects both control quality and computational cost. This trade-off is critical: higher precision improves control performance but increases runtime, while lower precision executes faster in the processor but may degrade overall […]

Ver mais

When the bubble bursts, it will be the indestructible code programmers who will learn to use these tools and new languages, but who also have the discipline required to deploy all these operations at scale. AI adoption numbers are impressive; 78% of global companies use AI in their daily operations, and 90% are exploring it. While some experts, such as Nobel Prize winner Joel Mokyr, say it has a very positive impact on economic growth, by helping people […]

Ver mais

Covering electricity price increases from our data centers One of the sub-threads of the AI energy usage discourse has been the impact new data centers have on the cost of electricity to nearby residents. Here’s detailed analysis from Bloomberg in September reporting “Wholesale electricity costs as much as 267% more than it did five years ago in areas near data centers”. Anthropic appear to be taking on this aspect of the problem directly, promising to cover 100% of […]

Ver mais