I’m exploring an idea and would love feedback from people who work with ML / agents / RL. Instead of generating synthetic datasets, the idea is to generate synthetic worlds: – populations – economic dynamics – constraints – shocks – time evolution The goal wouldn’t be prediction, but providing controllable environments where AI agents can be trained or stress-tested on long-horizon decisions (policy, planning, resource allocation, etc.). Think more like “SimCity-style environments for AI training” rather than tabular […]

Ver mais

arXiv:2603.06726v1 Announce Type: new Abstract: Electricity market prices exhibit extreme volatility, nonlinearity, and non-stationarity, making accurate forecasting a significant challenge. While cutting-edge time series foundation models (TSFMs) effectively capture temporal dependencies, they typically underutilize cross-variate correlations and non-periodic patterns that are essential for price forecasting. Conversely, regression models excel at capturing feature interactions but are limited to future-available inputs, ignoring crucial historical drivers that are unavailable at forecast time. To bridge this gap, we propose FutureBoosting, a novel […]

Ver mais

The problem almost nobody warns you about If you’ve tried training a manipulation policy in Isaac Sim or MuJoCo on assets pulled from Sketchfab, TurboSquid, Objaverse, or your team’s internal CAD library, you’ve probably hit one or more of these: Gripper passes through the object. Object has “infinite mass” and refuses to move. Stacking collapses in bizarre non-physical ways. Contact forces spike to NaN and the sim explodes. Your policy trains to 99% success in sim and faceplants […]

Ver mais

Hey, I’m working on a RL project with a coach/trainer module, and I regularly brainstorm with AI chatbots (Claude, ChatGPT, Gemini) to analyze decision quality, debug training issues, and find improvements. The problem: this back-and-forth is very time-consuming, and I’m looking to optimize it. A few questions: 1. Which chatbot do you find most effective for RL-specific brainstorming (policy issues, reward design, training instabilities…)? 2. Any prompting strategies or workflows that save you time? Looking for feedback from […]

Ver mais

Higher education institutions have historically relied on retrospective reporting to understand enrollment trends and student outcomes. Admissions offices scrutinized last year’s yield rates; registrars tracked semester-to-semester retention; academic affairs teams compiled graduation statistics after the fact. While these practices produced useful summaries, they offered no predictive leverage. By the time a pattern became visible in the static data, the window for meaningful intervention had almost always slammed shut. The current pivot toward predictive modeling isn’t just a technical […]

Ver mais

arXiv:2601.12266v1 Announce Type: new Abstract: We study the problem of scheduling delay-sensitive jobs over spot and on-demand cloud instances to minimize average cost while meeting an average delay constraint. Jobs arrive as a general stochastic process, and incur different costs based on the instance type. This work provides the first analytical treatment of this problem using tools from queuing theory, stochastic processes, and optimization. We derive cost expressions for general policies, prove queue length one is optimal for […]

Ver mais

Custom Diffusion Models (CDMs) have gained significant attention due to their remarkable ability to personalize generative processes. However, existing CDMs suffer from catastrophic forgetting when continuously learning new concepts. Most prior works attempt to mitigate this issue under the sequential learning setting with a fixed order of concept inflow and neglect inter-concept interactions. In this paper, we propose a novel framework – Forget Less by Learning Together (FL2T) – that enables concurrent and order-agnostic concept learning while addressing […]

Ver mais

Precision medicine aims to tailor therapeutic decisions to individual patient characteristics. This objective is commonly formalized through dynamic treatment regimes, which use statistical and machine learning methods to derive sequential decision rules adapted to evolving clinical information. In most existing formulations, these approaches produce a single optimal treatment at each stage, leading to a unique decision sequence. However, in many clinical settings, several treatment options may yield similar expected outcomes, and focusing on a single optimal policy may […]

Ver mais

arXiv:2603.03311v1 Announce Type: new Abstract: This paper documents the architecture, development practices, and preserved artifacts of the Logovista English–Japanese machine translation system, a large, explicitly rule-based MT system that was developed and sold commercially from the early 1990s through at least 2012. The system combined hand-authored grammatical rules, a large central dictionary encoding syntactic and semantic constraints, and chart-based parsing with weighted interpretation scoring to manage extensive structural ambiguity. The account emphasizes how the system was extended and […]

Ver mais