February 2026

In hierarchical multi-label classification, a persistent challenge is enabling model predictions to reach deeper levels of the hierarchy for more detailed or fine-grained classifications. This difficulty partly arises from the natural rarity of certain classes (or hierarchical nodes) and the hierarchical constraint that ensures child nodes are almost always less frequent than their parents. To address this, we propose a weighted loss objective for neural networks that combines node-wise imbalance weighting with focal weighting components, the latter leveraging […]

Ver mais

The inability to communicate poses a major challenge to coordination in multi-agent reinforcement learning (MARL). Prior work has explored correlating local policies via shared randomness, sometimes in the form of a correlation device, as a mechanism to assist in decentralized decision-making. In contrast, this work introduces the first framework for training MARL agents to exploit shared quantum entanglement as a coordination resource, which permits a larger class of communication-free correlated policies than shared randomness alone. This is motivated […]

Ver mais

The inability to communicate poses a major challenge to coordination in multi-agent reinforcement learning (MARL). Prior work has explored correlating local policies via shared randomness, sometimes in the form of a correlation device, as a mechanism to assist in decentralized decision-making. In contrast, this work introduces the first framework for training MARL agents to exploit shared quantum entanglement as a coordination resource, which permits a larger class of communication-free correlated policies than shared randomness alone. This is motivated […]

Ver mais

We just finished what I think is one of the larger controlled VLA comparisons on physical robots and wanted to share the results with this community, since the scaling and policy learning findings feel very relevant to RL. The setup: 3 dual-arm platforms (Agibot G1, AgileX, Galaxea R1Pro), 100 manipulation tasks per platform from the GM-100 benchmark, 130 post-training trajectories per task, 15 evaluation trials per task per model. All four models were fine-tuned from their public checkpoints […]

Ver mais

AI-text detectors face a critical robustness challenge: adversarial paraphrasing attacks that preserve semantics while evading detection. We introduce StealthRL, a reinforcement learning framework that stress-tests detector robustness under realistic adversarial conditions. StealthRL trains a paraphrase policy against a multi-detector ensemble using Group Relative Policy Optimization (GRPO) with LoRA adapters on Qwen3-4B, optimizing a composite reward that balances detector evasion with semantic preservation. We evaluate six attack settings (M0-M5) against three detector families (RoBERTa, FastDetectGPT, and Binoculars) at the […]

Ver mais

Regression neural networks (NNs) are most commonly trained by minimizing the mean squared prediction error, which is highly sensitive to outliers and data contamination. Existing robust training methods for regression NNs are often limited in scope and rely primarily on empirical validation, with only a few offering partial theoretical guarantees. In this paper, we propose a new robust learning framework for regression NNs based on the $β$-divergence (also known as the density power divergence) which we call `rRNet’. […]

Ver mais

We study a setting where the goal is to learn a target function f(x) with respect to a target distribution D(x), but training is done on i.i.d. samples from a different training distribution D'(x), labeled by the true target f(x). Such a distribution shift (here in the form of covariate shift) is usually viewed negatively, as hurting or making learning harder, and the traditional distribution shift literature is mostly concerned with limiting or avoiding this negative effect. In […]

Ver mais