arXiv:2602.07051v1 Announce Type: new Abstract: Traditional Automatic License Plate Recognition (ALPR) systems employ multi-stage pipelines consisting of object detection networks followed by separate Optical Character Recognition (OCR) modules, introducing compounding errors, increased latency, and architectural complexity. This research presents Neural Sentinel, a novel unified approach that leverages Vision Language Models (VLMs) to perform license plate recognition, state classification, and vehicle attribute extraction through a single forward pass. Our primary contribution lies in demonstrating that a fine-tuned PaliGemma 3B […]

Ver mais

Most Probable Explanation (MPE) inference in Probabilistic Graphical Models (PGMs) is a fundamental yet computationally challenging problem arising in domains such as diagnosis, planning, and structured prediction. In many practical settings, the graphical model remains fixed while inference must be performed repeatedly for varying evidence patterns. Stochastic Local Search (SLS) algorithms scale to large models but rely on myopic best-improvement rule that prioritizes immediate likelihood gains and often stagnate in poor local optima. Heuristics such as Guided Local […]

Ver mais

Polymer-based long-acting injectables (LAIs) have transformed the treatment of chronic diseases by enabling controlled drug delivery, thus reducing dosing frequency and extending therapeutic duration. Achieving controlled drug release from LAIs requires extensive optimization of the complex underlying physicochemical properties. Machine learning (ML) can accelerate LAI development by modeling the complex relationships between LAI properties and drug release. However, recent ML studies have provided limited information on key properties that modulate drug release, due to the lack of custom […]

Ver mais

TL;DR: Current schedulers in PyTorch are limited to just learning rate (lr) changes and often lead to hardcoded, error-prone logic in training loops for anything more complex. I built a flexible suite for scheduling any optimizer hyperparam (LR, momentum, betas, etc.), with support for custom functions, presets, cyclic patterns, and per-group overrides. It’s stateless where possible, picklable for checkpointing, and well-tested. It currently lives in my research monorepo, but I can separate it into a standalone package if […]

Ver mais

Energy efficiency has become an integral aspect of modern computing infrastructure design, impacting the performance, cost, scalability, and durability of production systems. The incorporation of power actuation and sensing capabilities in CPU designs is indicative of this, enabling the deployment of system software that can actively monitor and adjust energy consumption and performance at runtime. While reinforcement learning (RL) would seem ideal for the design of such energy efficiency control systems, online training presents challenges ranging from the […]

Ver mais

arXiv:2602.11337v1 Announce Type: new Abstract: Deploying robots at scale demands robustness to the long tail of everyday situations. The countless variations in scene layout, object geometry, and task specifications that characterize real environments are vast and underrepresented in existing robot benchmarks. Measuring this level of generalization requires infrastructure at a scale and diversity that physical evaluation alone cannot provide. We introduce MolmoSpaces, a fully open ecosystem to support large-scale benchmarking of robot policies. MolmoSpaces consists of over 230k […]

Ver mais

Reinforcement learning has been widely applied to diffusion and flow models for visual tasks such as text-to-image generation. However, these tasks remain challenging because diffusion models have intractable likelihoods, which creates a barrier for directly applying popular policy-gradient type methods. Existing approaches primarily focus on crafting new objectives built on already heavily engineered LLM objectives, using ad hoc estimators for likelihood, without a thorough investigation into how such estimation affects overall algorithmic performance. In this work, we provide […]

Ver mais