arXiv:2509.24789v3 Announce Type: replace-cross Abstract: The evaluation of time series forecasting models is hindered by a critical lack of high-quality benchmarks, leading to a potential illusion of progress. Existing datasets suffer from issues ranging from pre-training data contamination in the age of LLMs to the temporal and description leakage prevalent in early multimodal designs. To address this, we formalize the core principles of high-fidelity benchmarking, focusing on data sourcing integrity, leak-free and causally sound design, and structural clarity. […]

Ver mais

arXiv:2603.24333v1 Announce Type: cross Abstract: Recently, Forr’e (arXiv:2104.11547, 2021) introduced transitional conditional independence, a notion of conditional independence that provides a unified framework for both random and non-stochastic variables. The original paper establishes a strong global Markov property connecting transitional conditional independencies with suitable graphical separation criteria for directed mixed graphs with input nodes (iDMGs), together with a version of causal calculus for iDMGs in a general measure-theoretic setting. These notes aim to further illustrate the motivations behind […]

Ver mais

We study off-policy reinforcement learning for controlling continuous-time Markov diffusion processes with discrete-time observations and actions. We consider model-free algorithms with function approximation that learn value and advantage functions directly from data, without unrealistic structural assumptions on the dynamics. Leveraging the ellipticity of the diffusions, we establish a new class of Hilbert-space positive definiteness and boundedness properties for the Bellman operators. Based on these properties, we propose the Sobolev-prox fitted $q$-learning algorithm, which learns value and advantage functions […]

Ver mais

Recent progress in reinforcement learning with verifiable rewards (RLVR) shows that small, specialized language models (SLMs) can exhibit structured reasoning without relying on large monolithic LLMs. We introduce soft hidden-state collaboration, where multiple heterogeneous frozen SLM experts are integrated through their internal representations via a trainable attention interface. Experiments on Reasoning Gym and GSM8K show that this latent integration is competitive with strong single-model RLVR baselines. Ablations further reveal a dual mechanism of expert utilization: for simpler arithmetic […]

Ver mais

Adversarial imitation learning (AIL) achieves high-quality imitation by mitigating compounding errors in behavioral cloning (BC), but often exhibits training instability due to adversarial optimization. To avoid this issue, a class of non-adversarial Q-based imitation learning (IL) methods, represented by IQ-Learn, has emerged and is widely believed to outperform BC by leveraging online environment interactions. However, this paper revisits IQ-Learn and demonstrates that it provably reduces to BC and suffers from an imitation gap lower bound with quadratic dependence […]

Ver mais

How are you, hacker? 🪐Want to know what’s trending right now?: The Techbeat by HackerNoon has got you covered with fresh content from our trending stories of the day! Set email preference here. ## The Best Medical Speech Recognition Software and APIs in 2026 By @assemblyai [ 11 Min read ] Compare the best medical speech recognition tools in 2026—APIs and software that cut documentation time, reduce burnout, and improve workflows. Read More. How to Break Your PostgreSQL […]

Ver mais

The global crypto market has faced a very difficult season recently. Over the last five months, the total market value has dropped by a staggering $2 trillion. Many famous coins have lost half of their value, leaving investors looking for safety. However, even in a down market, there are always outliers that defy the trend. While the giants are falling, a new project has managed to climb 300% during its development stage. This performance is catching the eye […]

Ver mais

arXiv:2603.07921v1 Announce Type: new Abstract: Robust Markov Decision Processes (MDPs) address environmental shift through distributionally robust optimization (DRO) by finding an optimal worst-case policy within an uncertainty set of transition kernels. However, standard DRO approaches require enlarging the uncertainty set under large shifts, which leads to overly conservative and pessimistic policies. In this paper, we propose a framework for transfer under environment shift that derives a robust target-domain policy via estimate-centered uncertainty sets, constructed through constrained estimation that […]

Ver mais

arXiv:2603.06901v1 Announce Type: new Abstract: As machine learning (ML) systems increasingly shape access to credit, jobs, and other opportunities, the fairness of algorithmic decisions has become a central concern. Yet it remains unclear when enforcing fairness constraints in these systems genuinely improves outcomes for affected groups or instead leads to “leveling down,” making one or both groups worse off. We address this question in a unified, population-level (Bayes) framework for binary classification under prevalent group fairness notions. Our […]

Ver mais