January 2026

Limited access to medical infrastructure forces elderly and vulnerable patients to rely on home-based care, often leading to neglect and poor adherence to therapeutic exercises such as yoga or physiotherapy. To address this gap, we propose a low-cost and automated human activity recognition (HAR) framework based on wearable inertial sensors and machine learning. Activity data, including walking, walking upstairs, walking downstairs, sitting, standing, and lying, were collected using accelerometer and gyroscope measurements. Four classical classifiers, Logistic Regression, Random […]

Ver mais

Hey everyone! My company is releasing ARES (Agentic Research and Evaluation Suite) today: https://github.com/withmartian/ares We’re hoping ARES can be a new Gym style environment for long horizon coding tasks, with a couple opinionated design decisions: – async, so it can parallelize easily and to large workloads – treats LLMRequests as environment observations and LLMResponses as actions, so we can treat the underlying LLM as the policy instead of a full agent orchestrator – integrates with Harbor (harborframework.com) on […]

Ver mais

{“document”:[{“e”:”par”,”c”:[{“e”:”text”,”t”:”Recent advances in reinforcement learning for code generation have made robust environments essential to prevent reward hacking. As LLMs increasingly serve as evaluators in code-based RL, their ability to detect reward hacking remains understudied. In this paper, we propose a novel taxonomy of reward exploits spanning across 54 categories and introduce TRACE (Testing Reward Anomalies in Code Environments), a synthetically curated and human-verified benchmark containing 517 testing trajectories. Unlike prior work that evaluates reward hack detection in isolated […]

Ver mais

I am training AI players for a chess-like game which has 3 distinct factions (i.e. different piece sets) and is played on a 9×9 board. The three factions are called Axiom (A), Blades (B), and Clockwork (C). With help from ChatGPT, I have managed to create 6 different AI models, one for each match up (AvA, AvB, AvC, BvB, BvC and CvC), under an Alpha Zero style approach. The structure used (which I broadly understand but largely relied […]

Ver mais

Multi-objective optimization aims to solve problems with competing objectives, often with only black-box access to a problem and a limited budget of measurements. In many applications, historical data from related optimization tasks is available, creating an opportunity for meta-learning to accelerate the optimization. Bayesian optimization, as a promising technique for black-box optimization, has been extended to meta-learning and multi-objective optimization independently, but methods that simultaneously address both settings – meta-learned priors for multi-objective Bayesian optimization – remain largely […]

Ver mais

Reinforcement learning (RL) with combinatorial action spaces remains challenging because feasible action sets are exponentially large and governed by complex feasibility constraints, making direct policy parameterization impractical. Existing approaches embed task-specific value functions into constrained optimization programs or learn deterministic structured policies, sacrificing generality and policy expressiveness. We propose a solver-induced emph{latent spherical flow policy} that brings the expressiveness of modern generative policies to combinatorial RL while guaranteeing feasibility by design. Our method, LSFlow, learns a emph{stochastic} policy […]

Ver mais

Simulating the long-time evolution of Hamiltonian systems is limited by the small timesteps required for stable numerical integration. To overcome this constraint, we introduce a framework to learn Hamiltonian Flow Maps by predicting the mean phase-space evolution over a chosen time span, enabling stable large-timestep updates far beyond the stability limits of classical integrators. To this end, we impose a Mean Flow consistency condition for time-averaged Hamiltonian dynamics. Unlike prior approaches, this allows training on independent phase-space samples […]

Ver mais

Simulating the long-time evolution of Hamiltonian systems is limited by the small timesteps required for stable numerical integration. To overcome this constraint, we introduce a framework to learn Hamiltonian Flow Maps by predicting the mean phase-space evolution over a chosen time span $Δt$, enabling stable large-timestep updates far beyond the stability limits of classical integrators. To this end, we impose a Mean Flow consistency condition for time-averaged Hamiltonian dynamics. Unlike prior approaches, this allows training on independent phase-space […]

Ver mais