Policy optimisation, reward modelling and RLHF — how models are trained by feedback rather than by labels.
arXiv:2607. 19367v1 Announce Type: new Abstract: Calibration is the primary criterion for evaluating LLM confidence, but it is insufficient: it admits trivially incoherent estimators, depends on the evaluation distribution, and does not test the extent to which the estimation can be interpreted as a consistent, underlying probability function.
arXiv:2607. 19712v1 Announce Type: new Abstract: In RLHF pipelines, reward scoring blocks policy updates.
arXiv:2602. 18109v3 Announce Type: replace Abstract: Real-time schedulers must reason about tight deadlines under strict compute budgets.
arXiv:2607. 19354v1 Announce Type: new Abstract: Spreadsheet applications are used by hundreds of millions worldwide, yet writing formulas remains a significant barrier.
arXiv:2607. 19628v1 Announce Type: new Abstract: In this work we investigate reinforcement learning (RL) as a framework for the robust control of parametrized dynamical systems in presence of measurements and model uncertainties.
arXiv:2510. 10057v2 Announce Type: replace Abstract: The three-dimensional bin packing problem (3D-BPP) is widely applied in logistics and warehousing.
arXiv:2510. 18348v2 Announce Type: replace-cross Abstract: State-of-the-art perceptive Reinforcement Learning controllers for legged robots typically either (i) impose oscillator-or IK-based gait priors that constrain the action space, bias policy optimization, and limit adaptability across robot morphologies, or (ii) operate "blind," making them unable to anticipate hind-leg terrain and brittle to observation noise.
arXiv:2607. 20090v1 Announce Type: cross Abstract: Retrieval-augmented large language models frequently face contexts that interleave useful evidence with misleading statements or instruction-like content.
arXiv:2607. 20399v1 Announce Type: cross Abstract: Full-sized humanoid robot capabilities have grown exponentially in recent years, aiming towards general-purpose deployment in human environments.
arXiv:2607. 19616v1 Announce Type: new Abstract: Knowledge graphs (KGs) are widely used to inject prior knowledge into reinforcement learning (RL), yet the literature is dominated by single-domain, positive-result method papers, so we lack a systematic account of when KG structure helps an agent, when it is neutral, and when it hurts.
arXiv:2607. 19935v1 Announce Type: new Abstract: Large metal-organic framework (MOF) databases support simulation, screening, and machine learning through crystallographic information files (CIFs).
arXiv:2607. 20152v1 Announce Type: cross Abstract: Active Inference (AIF) frames adaptive behavior as the minimization of expected free energy (EFE), combining epistemic and pragmatic objectives within a single variational principle.
arXiv:2607. 20166v1 Announce Type: cross Abstract: Large Audio Language models (LALMs) have made rapid progress on acoustic understanding, yet they still struggle with fine-grained audio reasoning (e.
arXiv:2607. 20010v1 Announce Type: new Abstract: In this paper, we present a generalized temporal-difference (TD) reinforcement learning framework based on the theory of conditional expectations.
arXiv:2604. 14180v2 Announce Type: replace-cross Abstract: We train a 318M-parameter Transformer language model from scratch on a curated corpus of 1.
arXiv:2607. 19854v1 Announce Type: new Abstract: We study horizon-free regret minimization for finite-horizon time-homogeneous tabular Markov decision processes with $S$ states, $A$ actions, horizon $H$, and per-trajectory total reward bounded by $1$.
arXiv:2607. 17572v2 Announce Type: replace Abstract: Group Relative Policy Optimization (GRPO) is a powerful reinforcement learning algorithm for aligning generative models with human preferences.
arXiv:2607. 19389v1 Announce Type: cross Abstract: As AI-driven Decision Makers (ADMs) influence our socioeconomic reality, their roles in both enhancing efficiency and amplifying the social biases have drawn attention.
arXiv:2607. 20253v1 Announce Type: cross Abstract: In this report, we present a unified song generation framework capable of producing high-quality full-length music from lyrics, text descriptions, and musical attributes.
arXiv:2607. 18365v1 Announce Type: cross Abstract: Reinforcement learning (RL) for legged robots is advancing locomotion, demonstrating its ability to adapt to new and challenging terrain.