Procedural Content Generation for 3D game levels faces challenges in balancing spatial coherence, navigational functionality, and adaptable gameplay progression across multi-floor environments. This paper introduces a novel framework for generating such levels, centered on the offline, LLM-assisted construction of reusable databases for architectural components (facilities and room templates) and gameplay mechanic elements. Our multi-phase pipeline assembles levels by: (1) selecting and arranging instances from the Room Database to form a multi-floor global structure with an inherent topological order; (2) optimizing the internal layout of facilities for each room based on predefined constraints from the Facility Database; and (3) integrating progression-based gameplay mechanics by placing components from a Mechanics Database according to their topological and spatial rules. A subsequent two-phase repair system ensures navigability. This approach combines modular, database-driven design with constraint-based optimization, allowing for systematic control over level structure and the adaptable pacing of gameplay elements. Initial experiments validate the framework's ability in generating diverse, navigable 3D environments and its capability to simulate distinct gameplay pacing strategies through simple parameterization. This research advances PCG by presenting a scalable, database-centric foundation for the automated generation of complex 3D levels with configurable gameplay progression.

Advancing AI systems in scientific domains like physics, materials science, and engineering calls for reasoning over complex, multi-physics phenomena while respecting governing principles. Although Large Language Models (LLMs) and existing preference optimization techniques perform well on standard benchmarks, they often struggle to differentiate between physically valid and invalid reasoning. This shortcoming becomes critical in high-stakes applications like metal joining, where seemingly plausible yet physically incorrect recommendations can lead to defects, material waste, equipment damage, and serious safety risks. To address this challenge, we introduce PKG-DPO, a novel framework that integrates Physics Knowledge Graphs (PKGs) with Direct Preference Optimization (DPO) to enforce physical validity in AI-generated outputs. PKG-DPO comprises three key components A) hierarchical physics knowledge graph that encodes cross-domain relationships, conservation laws, and thermodynamic principles. B) A physics reasoning engine that leverages structured knowledge to improve discrimination between physically consistent and inconsistent responses. C) A physics-grounded evaluation suite designed to assess compliance with domain-specific constraints. PKG-DPO achieves 17% fewer constraint violations and an 11% higher Physics Score compared to KG-DPO (knowledge graph-based DPO). Additionally, PKG-DPO demonstrates a 12\% higher relevant parameter accuracy and a 7% higher quality alignment in reasoning accuracy. While our primary focus is on metal joining, the framework is broadly applicable to other multi-scale, physics-driven domains, offering a principled approach to embedding scientific constraints into preference learning.

The Profiled V ehicle Routing Problem (PVRP) extends the classical VRP by incorporating vehicle-client-specific preferences and constraints, reflecting real-world requirements such as zone restrictions and service-level preferences. While recent reinforcement-learning solvers have shown promising performance, they require retraining for each new profile distribution, suffer from poor representation ability, and struggle to generalize to out-of-distribution instances. In this paper, we address these limitations by introducing U nified Solver for Profiled R outing (USPR), a novel framework that natively handles arbitrary profile types. USPR introduces on three key innovations: (i) Profile Embeddings (PE) to encode any combination of profile types; (ii) Multi-Head Profiled Attention (MHP A), an attention mechanism that models rich interactions between vehicles and clients; (iii) Profile-aware Score Reshaping (PSR), which dynamically adjusts decoder logits using profile scores to improve generalization. Empirical results on diverse PVRP benchmarks demonstrate that USPR achieves state-of-the-art results among learning-based methods while offering significant gains in flexibility and computational efficiency. We make our source code publicly available to foster future research.

We address the problem of data scarcity in harmful text classification for guardrailing applications and introduce GRAID (Geometric and Reflective AI-Driven Data Augmentation), a novel pipeline that leverages Large Language Models (LLMs) for dataset augmentation. GRAID consists of two stages: (i) generation of geometrically controlled examples using a constrained LLM, and (ii) augmentation through a multi-agentic reflective process that promotes stylistic diversity and uncovers edge cases. This combination enables both reliable coverage of the input space and nuanced exploration of harmful content. Using two benchmark data sets, we demonstrate that augmenting a harmful text classification dataset with GRAID leads to significant improvements in downstream guardrail model performance.

Enabling neural networks to learn complex logical constraints and fulfill symbolic reasoning is a critical challenge. Bridging this gap often requires guiding the neural network's output distribution to move closer to the symbolic constraints. While diffusion models have shown remarkable generative capability across various domains, we employ the powerful architecture to perform neuro-symbolic learning and solve logical puzzles. Our diffusion-based pipeline adopts a two-stage training strategy: the first stage focuses on cultivating basic reasoning abilities, while the second emphasizes systematic learning of logical constraints. To impose hard constraints on neural outputs in the second stage, we formulate the diffusion reasoner as a Markov decision process and innovatively fine-tune it with an improved proximal policy optimization algorithm. We utilize a rule-based reward signal derived from the logical consistency of neural outputs and adopt a flexible strategy to optimize the diffusion reasoner's policy. We evaluate our methodology on some classical symbolic reasoning benchmarks, including Sudoku, Maze, pathfinding and preference learning. Experimental results demonstrate that our approach achieves outstanding accuracy and logical consistency among neural networks.

The success of generative modeling in continuous domains has led to a surge of interest in generating discrete data such as molecules, source code, and graphs.

Since the constraints are independent of the target labels, our framework easily generalizes to semi-supervised setting.

Neural Information Processing Systems http://nips.cc/

Imitating tool manipulation from human videos offers an intuitive approach to teaching robots, while also providing a promising and scalable alternative to labor-intensive teleoperation data collection for visuomotor policy learning. While humans can mimic tool manipulation behavior by observing others perform a task just once and effortlessly transfer the skill to diverse tools for functionally equivalent tasks, current robots struggle to achieve this level of generalization. A key challenge lies in establishing function-level correspondences, considering the significant geometric variations among functionally similar tools, referred to as intra-function variations. To address this challenge, we propose MimicFunc, a framework that establishes functional correspondences with function frame, a function-centric local coordinate frame constructed with keypoint-based abstraction, for imitating tool manipulation skills. Experiments demonstrate that MimicFunc effectively enables the robot to generalize the skill from a single RGB-D human video to manipulating novel tools for functionally equivalent tasks. Furthermore, leveraging MimicFunc's one-shot generalization capability, the generated rollouts can be used to train visuomotor policies without requiring labor-intensive teleoperation data collection for novel objects. Our code and video are available at https://sites.google.com/view/mimicfunc.

A motion of a mechanism is a curve in its configuration space (c-space). Singularities of the c-space are kinematic singularities of the mechanism. Any mobility analysis of a particular mechanism amounts to investigating the c-space geometry at a given configuration. A higher-order analysis is necessary to determine the finite mobility. To this end, past research lead to approaches using higher-order time derivatives of loop closure constraints assuming (implicitly) that all possible motions are smooth. This continuity assumption limits the generality of these methods. In this paper an approach to the higher-order local mobility analysis of lower pair multi-loop linkages is presented. This is based on a higher-order Taylor series expansion of the geometric constraint mapping, for which a recursive algebraic expression in terms of joint screws is presented. An exhaustive local analysis includes analysis of the set of constraint singularities (configurations where the constraint Jacobian has certain corank). A local approximation of the set of configurations with certain rank is presented, along with an explicit expression for the differentials of Jacobian minors in terms of instantaneous joint screws. The c-space and the set of points of certain corank are therewith locally approximated by an algebraic variety determined algebraically from the mechanism's screw system. Results are shown for a simple planar 4-bar linkage, which exhibits a bifurcation singularity, and for a planar three-loop linkage exhibiting a cusp in c-space. The latter cannot be treated by the higher-order local analysis methods proposed in the literature.