arXiv:2604.03333v1 Announce Type: cross Abstract: Symbolic music generation has made significant progress, yet achieving fine-grained and flexible control over composer style remains challenging. Existing training-based methods for composer style conditioning depend on large labeled datasets. Besides, these methods typically support only single-composer generation at a time, limiting their applicability to more creative or blended scenarios. […]
Governance-Constrained Agentic AI: Blockchain-Enforced Human Oversight for Safety-Critical Wildfire Monitoring
arXiv:2604.04265v1 Announce Type: cross Abstract: The AI-based sensing and autonomous monitoring have become the main components of wildfire early detection, but current systems do not provide adaptive inter-agent coordination, structurally defined human control, and cryptographically verifiable responsibility. Purely autonomous alert dissemination in the context of safety critical disasters poses threats of false alarming, governance failure […]
Safety-Aligned 3D Object Detection: Single-Vehicle, Cooperative, and End-to-End Perspectives
arXiv:2604.03325v1 Announce Type: cross Abstract: Perception plays a central role in connected and autonomous vehicles (CAVs), underpinning not only conventional modular driving stacks, but also cooperative perception systems and recent end-to-end driving models. While deep learning has greatly improved perception performance, its statistical nature makes perfect predictions difficult to attain. Meanwhile, standard training objectives and […]
Toward Epistemic Stability: Engineering Consistent Procedures for Industrial LLM Hallucination Reduction
arXiv:2603.10047v2 Announce Type: replace-cross Abstract: Hallucinations in large language models (LLMs) are outputs that are syntactically coherent but factually incorrect or contextually inconsistent. They are persistent obstacles in high-stakes industrial settings such as engineering design, enterprise resource planning, and IoT telemetry platforms. We present and compare five prompt engineering strategies intended to reduce the variance […]
APPA: Adaptive Preference Pluralistic Alignment for Fair Federated RLHF of LLMs
arXiv:2604.04261v1 Announce Type: cross Abstract: Aligning large language models (LLMs) with diverse human preferences requires pluralistic alignment, where a single model must respect the values of multiple distinct groups simultaneously. In federated reinforcement learning from human feedback (FedRLHF), these groups align a shared policy without centralizing preference data, which makes fair reward aggregation essential. Existing […]
Toward Artificial Intelligence Enabled Earth System Coupling
arXiv:2604.03289v1 Announce Type: cross Abstract: Coupling constitutes a foundational mechanism in the Earth system, regulating the interconnected physical, chemical, and biological processes that link its spheres. This review examines how emerging artificial intelligence (AI) methods create new opportunities to enhance Earth system coupling and address long-standing limitations in multi-component models. Rather than surveying next-generation modelling […]
Downscaling weather forecasts from Low- to High-Resolution with Diffusion Models
arXiv:2604.03303v1 Announce Type: cross Abstract: We introduce a probabilistic diffusion-based method for global atmospheric downscaling implemented within the Anemoi framework. The approach transforms low-resolution ensemble forecasts into high-resolution ensembles by learning the conditional distribution of finer-scale residuals, defined as the difference between the high-resolution fields and the interpolated low-resolution inputs. The system is trained on […]
Projected Autoregression: Autoregressive Language Generation in Continuous State Space
arXiv:2601.04854v3 Announce Type: replace-cross Abstract: Standard autoregressive language models generate text by repeatedly selecting a discrete next token, coupling prediction with irreversible commitment at every step. We show that token selection is not the only viable autoregressive interface. textbfProjected Autoregression replaces token selection with continuous prediction in embedding space followed by discrete projection at commitment […]
UtilityMax Prompting: A Formal Framework for Multi-Objective Large Language Model Optimization
arXiv:2603.11583v3 Announce Type: replace-cross Abstract: The success of a Large Language Model (LLM) task depends heavily on its prompt. Most use-cases specify prompts using natural language, which is inherently ambiguous when multiple objectives must be simultaneously satisfied. In this paper we introduce UtilityMax Prompting, a framework that specifies tasks using formal mathematical language. We reconstruct […]
Mitigating Value Hallucination in Dyna Planning via Multistep Predecessor Models
arXiv:2006.04363v2 Announce Type: replace-cross Abstract: Dyna-style reinforcement learning (RL) agents improve sample efficiency over model-free RL agents by updating the value function with simulated experience generated by an environment model. However, it is often difficult to learn accurate models of environment dynamics, and even small errors may result in failure of Dyna agents. In this […]
Embodied-R1: Reinforced Embodied Reasoning for General Robotic Manipulation
arXiv:2508.13998v2 Announce Type: replace-cross Abstract: Generalization in embodied AI is hindered by the “seeing-to-doing gap,” which stems from data scarcity and embodiment heterogeneity. To address this, we pioneer “pointing” as a unified, embodiment-agnostic intermediate representation, defining four core embodied pointing abilities that bridge high-level vision-language comprehension with low-level action primitives. We introduce Embodied-R1, a 3B […]
SkillX: Automatically Constructing Skill Knowledge Bases for Agents
arXiv:2604.04804v1 Announce Type: cross Abstract: Learning from experience is critical for building capable large language model (LLM) agents, yet prevailing self-evolving paradigms remain inefficient: agents learn in isolation, repeatedly rediscover similar behaviors from limited experience, resulting in redundant exploration and poor generalization. To address this problem, we propose SkillX, a fully automated framework for constructing […]