Policy optimisation, reward modelling and RLHF — how models are trained by feedback rather than by labels.
arXiv:2512. 14991v2 Announce Type: replace Abstract: We study reinforcement learning for controlled diffusion processes with unbounded continuous state spaces, bounded continuous actions, and polynomially growing rewards: settings that arise naturally in finance, economics, and operations research.
arXiv:2607. 04517v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models are commonly treated as end-to-end action policies conditioned on natural-language task descriptions.
arXiv:2607. 04315v1 Announce Type: cross Abstract: This paper studies the problem of identifying the treatment that maximizes the expected natural direct potential outcome (NDPO), which captures the potential outcome of an intervention while excluding the pathway transmitted through a mediator that researchers may wish to remove from evaluation.
arXiv:2408. 09112v2 Announce Type: replace Abstract: Reinforcement learning policies parametrized by deep neural networks have achieved strong performance for continuous control, yet even small input perturbations may lead to unpredictable behavior.
arXiv:2607. 04119v1 Announce Type: cross Abstract: Reconstructing Computer-Aided Design (CAD) modeling sequences from images is crucial for preserving design intent and supporting parametric editing.
arXiv:2607. 03748v1 Announce Type: new Abstract: Unified multi-modal models (UMMs) have shown promising interleaved text-image reasoning capabilities, yet effectively optimizing such multi-turn generation via reinforcement learning (RL) remains an open challenge.
arXiv:2605. 26012v2 Announce Type: replace-cross Abstract: Deep reinforcement learning (RL) agents commonly rely on high-dimensional neural representations, despite growing evidence that task-relevant value and policy structure may be intrinsically low-dimensional.
arXiv:2506. 16995v4 Announce Type: replace Abstract: Proficient game agents with diverse play styles enrich the gaming experience and enhance the replay value of games.
arXiv:2607. 02891v1 Announce Type: new Abstract: Many online decision-making problems involve both round-specific feasible actions and drifting reward models: eligible ad impressions, feasible prices, and available treatments can change over time, while user preferences, demand curves, and patient responses may evolve.
arXiv:2605. 03135v2 Announce Type: replace Abstract: Standard classification treats all errors equally, but in applications such as content moderation and medical screening, mistakes on clear-cut cases are more costly than errors on ambiguous ones.
arXiv:2512. 15765v3 Announce Type: replace Abstract: Data valuation is a natural framework for understanding which preference datasets matter most when aligning a Large Language Model (LLM) using multiple sources.
arXiv:2607. 03928v1 Announce Type: cross Abstract: Accent normalization (AN) seeks to convert non-native (L2) accented speech into standard (L1) speech while preserving speaker identity.
arXiv:2509. 23960v2 Announce Type: replace-cross Abstract: Co-optimizing safety and performance in large-scale multi-agent systems remains a fundamental challenge.
arXiv:2607. 04091v1 Announce Type: new Abstract: Graph Neural Networks (GNNs) have achieved remarkable performance in graph representation learning, yet their inherent vulnerability to adversarial attacks poses severe security risks.
arXiv:2604. 19139v3 Announce Type: replace-cross Abstract: As Large Language Models (LLMs) continue to evolve through alignment techniques such as Reinforcement Learning from Human Feedback (RLHF) and Constitutional AI, a growing and increasingly conspicuous phenomenon has emerged: the proliferation of verbal tics--repetitive, formulaic linguistic patterns that pervade model outputs.
arXiv:2607. 04681v1 Announce Type: cross Abstract: Embodied Chain-of-Thought has emerged as a promising mechanism to enhance robot decision-making and interpretability in black-box Vision-Language Action (VLA) models.
arXiv:2509. 11259v2 Announce Type: replace-cross Abstract: Recent advancements in machine learning have largely been driven by foundation models (FMs) trained on large, diverse datasets, enabling them to generalize effectively to new, related tasks.
arXiv:2607. 05064v1 Announce Type: new Abstract: Reinforcement learning in real world environments often suffers from severe performance degradation due to delayed feedback.
arXiv:2510. 01460v4 Announce Type: replace-cross Abstract: Offline-to-online reinforcement learning (RL) has emerged as a practical paradigm that leverages offline datasets for pretraining and online interactions for fine-tuning.
arXiv:2607. 05394v1 Announce Type: cross Abstract: Reinforcement learning with verifiable rewards (RLVR) is a powerful recipe for improving language-model reasoning, but it is expensive to repeat on every new strong model because the target model must generate many rollouts during training.