arXiv subjects

Yunzhe Wang

Publications and source records attributed to Yunzhe Wang.

11 recordsLinked to original sources

arXiv2026

GraphAllocBench: A Flexible Benchmark for Preference-Conditioned Multi-Objective Policy Learning

Preference-Conditioned Policy Learning (PCPL) in Multi-Objective Reinforcement Learning (MORL) approximates diverse Pareto-optimal solutions by conditioning a single policy on user-specified preferences, enabling run-time adaptation to arbitrary trade-offs without retraining. However, existing PCPL benchmarks are largely restricted to toy tasks and fixed environments, limiting their realism and scalability. To address this gap, we introduce GraphAllocBench, a flexible benchmark built on CityPlannerEnv, a novel graph-based resource allocation sandbox inspired by city management. GraphAllocBench provides a rich suite of problems with customizable objective functions, varying preference conditions, complex Pareto Fronts, and high-dimensional scalability. We further propose two supplementary metrics -- Proportion of Non-Dominated Solutions (PNDS) and Ordering Score (OS) -- that capture prediction reliability and preference consistency while complementing the widely used hypervolume metric. Through experiments with several state-of-the-art PCPL algorithms and our own MLP and graph-aware PCPL-PPO baseline, we show that GraphAllocBench exposes distinct failure modes that hypervolume alone does not capture but our supplementary metrics reveal, while motivating graph-based approaches such as Graph Neural Networks (GNNs) for scaling to complex, high-dimensional allocation tasks. By letting users freely vary objectives, preferences, and allocation rules, GraphAllocBench serves as a versatile and extensible testbed for advancing PCPL.

cs.LG↗

arXiv2026

SongBench: A Fine-Grained Multi-Aspect Benchmark for Song Quality Assessment

Recent advancements in Text-to-Song generation have enabled realistic musical content production, yet existing evaluation benchmarks lack the professional granularity to capture multi-dimensional aesthetic nuances. In this paper, we propose SongBench, a specialized framework for fine-grained song assessment across seven key dimensions: Vocal, Instrument, Melody, Structure, Arrangement, Mixing, and Musicality. Utilizing this framework, we construct an expert-annotated database comprising 11,717 samples from state-of-the-art models, labeled by music professionals. Extensive experimental results demonstrate that SongBench achieves high correlation with expert ratings. By revealing fine-grained performance gaps in current state-of-the-art models, SongBench serves as a diagnostic benchmark to steer the development toward more professional and musically coherent song generation.

eess.AS↗

arXiv2026

GameplayQA: A Benchmarking Framework for Decision-Dense POV-Synced Multi-Video Understanding of 3D Virtual Agents

Multimodal LLMs are increasingly deployed as perceptual backbones for autonomous agents in 3D environments, from robotics to virtual worlds. These applications require agents to perceive rapid state changes, attribute actions to the correct entities, and reason about concurrent multi-agent behaviors from a first-person perspective, capabilities that existing benchmarks do not adequately evaluate. We introduce GameplayQA, a framework for evaluating agentic-centric perception and reasoning through video understanding. Specifically, we densely annotate multiplayer 3D gameplay videos at 1.22 labels/second, with time-synced, concurrent captions of states, actions, and events structured around a triadic system of Self, Other Agents, and the World, a natural decomposition for multi-agent environments. From these annotations, we refined 2.4K diagnostic QA pairs organized into three levels of cognitive complexity, accompanied by a structured distractor taxonomy that enables fine-grained analysis of where models hallucinate. Evaluation of frontier MLLMs reveals a substantial gap from human performance, with common failures in temporal and cross-video grounding, agent-role attribution, and handling the decision density of the game. We hope GameplayQA stimulates future research at the intersection of embodied AI, agentic perception, and world modeling.

cs.CL↗

arXiv2025

Individualized Cognitive Simulation in Large Language Models: Evaluating Different Cognitive Representation Methods

Individualized cognitive simulation (ICS) aims to build computational models that approximate the thought processes of specific individuals. While large language models (LLMs) convincingly mimic surface-level human behavior such as role-play, their ability to simulate deeper individualized cognitive processes remains poorly understood. To address this gap, we introduce a novel task that evaluates different cognitive representation methods in ICS. We construct a dataset from recently published novels (later than the release date of the tested LLMs) and propose an 11-condition cognitive evaluation framework to benchmark seven off-the-shelf LLMs in the context of authorial style emulation. We hypothesize that effective cognitive representations can help LLMs generate storytelling that better mirrors the original author. Thus, we test different cognitive representations, e.g., linguistic features, concept mappings, and profile-based information. Results show that combining conceptual and linguistic features is particularly effective in ICS, outperforming static profile-based cues in overall evaluation. Importantly, LLMs are more effective at mimicking linguistic style than narrative structure, underscoring their limits in deeper cognitive simulation. These findings provide a foundation for developing AI systems that adapt to individual ways of thinking and expression, advancing more personalized and human-aligned creative technologies.

cs.AI↗

arXiv2025

X-Ego: Acquiring Team-Level Tactical Situational Awareness via Cross-Egocentric Contrastive Video Representation Learning

Human team tactics emerge from each player's individual perspective and their ability to anticipate, interpret, and adapt to teammates' intentions. While advances in video understanding have improved the modeling of team interactions in sports, most existing work relies on third-person broadcast views and overlooks the synchronous, egocentric nature of multi-agent learning. We introduce X-Ego-CS, a benchmark dataset consisting of 124 hours of gameplay footage from 45 professional-level matches of the popular e-sports game Counter-Strike 2, designed to facilitate research on multi-agent decision-making in complex 3D environments. X-Ego-CS provides cross-egocentric video streams that synchronously capture all players' first-person perspectives along with state-action trajectories. Building on this resource, we propose Cross-Ego Contrastive Learning (CECL), which aligns teammates' egocentric visual streams to foster team-level tactical situational awareness from an individual's perspective. We evaluate CECL on a teammate-opponent location prediction task, demonstrating its effectiveness in enhancing an agent's ability to infer both teammate and opponent positions from a single first-person view using state-of-the-art video encoders. Together, X-Ego-CS and CECL establish a foundation for cross-egocentric multi-agent benchmarking in esports. More broadly, our work positions gameplay understanding as a testbed for multi-agent modeling and tactical learning, with implications for spatiotemporal reasoning and human-AI teaming in both virtual and real-world domains. Code and dataset are available at https://github.com/HATS-ICT/x-ego.

cs.CV↗

arXiv2025

A Data-Driven Discretized CS:GO Simulation Environment to Facilitate Strategic Multi-Agent Planning Research

Modern simulation environments for complex multi-agent interactions must balance high-fidelity detail with computational efficiency. We present DECOY, a novel multi-agent simulator that abstracts strategic, long-horizon planning in 3D terrains into high-level discretized simulation while preserving low-level environmental fidelity. Using Counter-Strike: Global Offensive (CS:GO) as a testbed, our framework accurately simulates gameplay using only movement decisions as tactical positioning -- without explicitly modeling low-level mechanics such as aiming and shooting. Central to our approach is a waypoint system that simplifies and discretizes continuous states and actions, paired with neural predictive and generative models trained on real CS:GO tournament data to reconstruct event outcomes. Extensive evaluations show that replays generated from human data in DECOY closely match those observed in the original game. Our publicly available simulation environment provides a valuable tool for advancing research in strategic multi-agent planning and behavior generation.

cs.AI↗

arXiv2025

Implicit Behavioral Alignment of Language Agents in High-Stakes Crowd Simulations

Language-driven generative agents have enabled large-scale social simulations with transformative uses, from interpersonal training to aiding global policy-making. However, recent studies indicate that generative agent behaviors often deviate from expert expectations and real-world data--a phenomenon we term the Behavior-Realism Gap. To address this, we introduce a theoretical framework called Persona-Environment Behavioral Alignment (PEBA), formulated as a distribution matching problem grounded in Lewin's behavior equation stating that behavior is a function of the person and their environment. Leveraging PEBA, we propose PersonaEvolve (PEvo), an LLM-based optimization algorithm that iteratively refines agent personas, implicitly aligning their collective behaviors with realistic expert benchmarks within a specified environmental context. We validate PEvo in an active shooter incident simulation we developed, achieving an 84% average reduction in distributional divergence compared to no steering and a 34% improvement over explicit instruction baselines. Results also show PEvo-refined personas generalize to novel, related simulation scenarios. Our method greatly enhances behavioral realism and reliability in high-stakes social simulations. More broadly, the PEBA-PEvo framework provides a principled approach to developing trustworthy LLM-driven social simulations.

cs.CL↗

arXiv2025

BREATH: A Bio-Radar Embodied Agent for Tonal and Human-Aware Diffusion Music Generation

We present a multimodal system for personalized music generation that integrates physiological sensing, LLM-based reasoning, and controllable audio synthesis. A millimeter-wave radar sensor non-invasively captures heart rate and respiration rate. These physiological signals, combined with environmental state, are interpreted by a reasoning agent to infer symbolic musical descriptors, such as tempo, mood intensity, and traditional Chinese pentatonic modes, which are then expressed as structured prompts to guide a diffusion-based audio model in synthesizing expressive melodies. The system emphasizes cultural grounding through tonal embeddings and enables adaptive, embodied music interaction. To evaluate the system, we adopt a research-creation methodology combining case studies, expert feedback, and targeted control experiments. Results show that physiological variations can modulate musical features in meaningful ways, and tonal conditioning enhances alignment with intended modal characteristics. Expert users reported that the system affords intuitive, culturally resonant musical responses and highlighted its potential for therapeutic and interactive applications. This work demonstrates a novel bio-musical feedback loop linking radar-based sensing, prompt reasoning, and generative audio modeling.

cs.HC↗

arXiv2025

Abstracting Geo-specific Terrains to Scale Up Reinforcement Learning

Multi-agent reinforcement learning (MARL) is increasingly ubiquitous in training dynamic and adaptive synthetic characters for interactive simulations on geo-specific terrains. Frameworks such as Unity's ML-Agents help to make such reinforcement learning experiments more accessible to the simulation community. Military training simulations also benefit from advances in MARL, but they have immense computational requirements due to their complex, continuous, stochastic, partially observable, non-stationary, and doctrine-based nature. Furthermore, these simulations require geo-specific terrains, further exacerbating the computational resources problem. In our research, we leverage Unity's waypoints to automatically generate multi-layered representation abstractions of the geo-specific terrains to scale up reinforcement learning while still allowing the transfer of learned policies between different representations. Our early exploratory results on a novel MARL scenario, where each side has differing objectives, indicate that waypoint-based navigation enables faster and more efficient learning while producing trajectories similar to those taken by expert human players in CSGO gaming environments. This research points out the potential of waypoint-based navigation for reducing the computational costs of developing and training MARL models for military training simulations, where geo-specific terrains and differing objectives are crucial.

cs.LG↗

arXiv2024

Reconfigurable Robot Identification from Motion Data

Integrating Large Language Models (VLMs) and Vision-Language Models (VLMs) with robotic systems enables robots to process and understand complex natural language instructions and visual information. However, a fundamental challenge remains: for robots to fully capitalize on these advancements, they must have a deep understanding of their physical embodiment. The gap between AI models cognitive capabilities and the understanding of physical embodiment leads to the following question: Can a robot autonomously understand and adapt to its physical form and functionalities through interaction with its environment? This question underscores the transition towards developing self-modeling robots without reliance on external sensory or pre-programmed knowledge about their structure. Here, we propose a meta self modeling that can deduce robot morphology through proprioception (the internal sense of position and movement). Our study introduces a 12 DoF reconfigurable legged robot, accompanied by a diverse dataset of 200k unique configurations, to systematically investigate the relationship between robotic motion and robot morphology. Utilizing a deep neural network model comprising a robot signature encoder and a configuration decoder, we demonstrate the capability of our system to accurately predict robot configurations from proprioceptive signals. This research contributes to the field of robotic self-modeling, aiming to enhance understanding of their physical embodiment and adaptability in real world scenarios.

cs.RO↗

arXiv2020

Rapid Generation of Optimal Generalized Monkhorst-Pack Grids

Computational modeling of the properties of crystalline materials has become an increasingly important aspect of materials research, consuming hundreds of millions of CPU-hours at scientific computing centres around the world each year, if not more. A routine operation in such calculations is the evaluation of integrals over the Brillouin zone. We have previously demonstrated that performing such integrals using generalized Monkhorst-Pack k-point grids can roughly double the speed of these calculations relative to the widely-used traditional Monkhorst-Pack grids, and such grids can be rapidly generated by querying a free, internet-accessible database of pre-generated grids. To facilitate the widespread use of generalized k-point grids, we present new algorithms that allow rapid generation of optimized generalized Monkhorst-Pack grids on the fly, an open-source library to facilitate their integration into external software packages, and an open-source implementation of the database tool that can be used offline. We also present benchmarks of the speed of our algorithms on structures randomly selected from the Inorganic Crystal Structure Database. For grids that correspond to a real-space supercell with at least 50 angstroms between lattice points, which is sufficient to converge density functional theory calculations within 1 meV/atom for nearly all materials, our algorithm finds optimized grids in an average of 0.19 seconds on a single processing core. For 100 angstroms between real-space lattice points, our algorithm finds optimal grids in less than 5 seconds on average.

physics.comp-ph↗