arXiv:2603.05618v1 Announce Type: new Abstract: Chain-of-Thought (CoT) prompting improves LLM reasoning but can increase privacy risk by resurfacing personally identifiable information (PII) from the prompt into reasoning traces and outputs, even under policies that instruct the model not to restate PII. We study such direct, inference-time PII leakage using a model-agnostic framework that (i) defines leakage as risk-weighted, token-level events across 11 PII types, (ii) traces leakage curves as a function of the allowed CoT budget, and (iii) […]

Ver mais

arXiv:2602.23408v1 Announce Type: new Abstract: The specification of the action space plays a pivotal role in imitation-based robotic manipulation policy learning, fundamentally shaping the optimization landscape of policy learning. While recent advances have focused heavily on scaling training data and model capacity, the choice of action space remains guided by ad-hoc heuristics or legacy designs, leading to an ambiguous understanding of robotic policy design philosophies. To address this ambiguity, we conducted a large-scale and systematic empirical study, confirming […]

Ver mais

arXiv:2601.22345v1 Announce Type: new Abstract: We evaluate language models on their ability to explore interactive environments under a limited interaction budget. We introduce three parametric tasks with controllable exploration difficulty, spanning continuous and discrete environments. Across state-of-the-art models, we find systematic under-exploration and suboptimal solutions, with performance often significantly worse than simple explore–exploit heuristic baselines and scaling weakly as the budget increases. Finally, we study two lightweight interventions: splitting a fixed budget into parallel executions, which surprisingly improves […]

Ver mais

arXiv:2601.22324v1 Announce Type: new Abstract: Modern clinical practice relies on evidence-based guidelines implemented as compact scoring systems composed of a small number of interpretable decision rules. While machine-learning models achieve strong performance, many fail to translate into routine clinical use due to misalignment with workflow constraints such as memorability, auditability, and bedside execution. We argue that this gap arises not from insufficient predictive power, but from optimizing over model classes that are incompatible with guideline deployment. Deployable guidelines […]

Ver mais

Why long context eats VRAM, how to estimate it in one line, and what actually fixes it If you’ve ever tried to run a model with a longer prompt, increased batch size, or enabled beam search and suddenly hit CUDA out-of-memory, there’s a high chance the culprit wasn’t the model weights. It was the KV cache. Weights are fixed. KV cache grows with tokens. So at inference time, memory pressure often comes from the thing you are generating: sequence length. Photo by Santiago […]

Ver mais

Community commerce is quickly becoming one of the most powerful growth levers for brands, yet most companies still underestimate its impact. As paid acquisition costs rise and consumer trust in traditional advertising continues to fall, community commerce offers a more sustainable path to growth by turning customers into connected, engaged participants who drive trust, influence purchasing decisions, and fuel long-term revenue. Brands that understand how to build and activate community commerce are no longer competing on ads alone—they’re […]

Ver mais

arXiv:2602.04975v1 Announce Type: new Abstract: This work introduces a stochastic hierarchical optimization framework inspired by Sloppy Model theory for the efficient calibration of physical models. Central to this method is the use of a reduced Hessian approximation, which identifies and targets the stiff parameter subspace using minimal simulation queries. This strategy enables efficient navigation of highly anisotropic landscapes, avoiding the computational burden of exhaustive sampling. To ensure rigorous inference, we integrate this approach with a probabilistic formulation that […]

Ver mais

arXiv:2603.08827v1 Announce Type: new Abstract: Smart city research envisions a future in which data-driven solutions and sustainable infrastructure work together to define urban living at the crossroads of urbanization and technology. Within this framework, smart parking systems play an important role in reducing urban congestion and supporting sustainable transportation. Automating parking solutions have considerable benefits, such as increased efficiency and less reliance on human involvement, but obstacles such as sensor limitations and integration complications remain. To overcome them, […]

Ver mais

This paper presents a controlled empirical study of biologically motivated local learning for handwritten digit recognition. We evaluate an STDP-inspired competitive proxy and a practical hybrid benchmark built on the same spiking population encoder. The proxy is motivated by leaky integrate-and-fire E/I circuit models with three-factor delayed reward modulation. The hybrid update is local in pre x post rates but uses supervised labels and no timing-based credit assignment. On sklearn digits, fixed-seed evaluation shows classical pixel baselines from […]

Ver mais

Photo by Resource Database on Unsplash Authors: Shon Mohsin, D. Eng AIJeremiah Lowhorn, D. Eng AISeth ThorMatthew Morais, D. Eng AI What if you could ask your data: “What did we know about this research topic in June 2024?” — and get a precise, structured answer? Scientific Research generates a web of interconnected entities — subjects, methods, outcomes, organizations, publications — that evolves over time. A spreadsheet can track individual facts. A relational database can join tables. But neither preserves the shape of knowledge: the web […]

Ver mais