arXiv subjects

Xue Feng

Publications and source records attributed to Xue Feng.

At least 19 recordsLinked to original sources

arXiv2026

Magic-free coexisting photonic and phononic moir\'e flat bands

Moir\'e flat bands enhance localization and interactions through suppressed group velocity, but existing approaches largely target a single physical field because distinct excitations generally require different, finely tuned magic configurations. Here we introduce a flat-band mechanism based on strong diffractive hybridization among moir\'e-folded bands. Period-mismatched modulations open distinct coupling channels whose hybridization renormalizes the band dispersion. An effective Hamiltonian shows that increasing the diffractive coupling progressively suppresses the group velocity, driving the system toward a flat-band regime without field-specific magic configurations. This coupling-induced mechanism enables band flattening across distinct physical excitations. We demonstrate this mechanism in a single-layer moir\'e optomechanical crystal, where photonic and phononic flat bands are simultaneously realized, and their localized modes and optomechanical interaction are experimentally observed. Beyond photonic and phononic systems, this mechanism may extend to other wave and quasiparticle platforms, providing a general route to co-localizing and coupling distinct physical fields in moir\'e systems.

physics.optics↗

arXiv2026

NormAct: Benchmarking Embodied Agents' Proactive Compliance with Unspoken Social Norms

Embodied agents driven by multimodal large language models (MLLMs) can often complete everyday tasks from visual observations, but goal achievement does not establish whether they proactively respect unstated social norms. Existing benchmarks assess explicit norm judgments or constrained behavior, but rarely test whether agents infer and apply scene-relevant norms during ordinary tasks. We introduce NormAct, a benchmark of 550 TongSim scenarios in which the same goal permits norm-compliant or norm-violating action sequences. Norm-relevant evidence is embedded in each scenario while the applicable rule is omitted from the goal instruction. By progressively increasing normative guidance while holding the goal and scene fixed, NormAct tests whether compliant behavior emerges autonomously or only after prompting. Across three MLLM planners, goal achievement substantially exceeds norm compliance without guidance (67.4% versus 24.7%), while both broad and rule-specific guidance improve compliance, indicating that planners can often comply when prompted but not reliably on their own. With a fixed planner, general-norm retrieval is less effective than norm-relevant scene descriptions or generated norm cues, suggesting that identifying relevant visual evidence is a greater challenge than accessing general norm knowledge. NormAct therefore supports the development of embodied agents that pursue everyday goals while proactively respecting unstated social norms.

cs.AI↗

arXiv2026

Learning to cooperate with emergent reputation via multi-agent reinforcement learning

Reputation, the aggregation of peer assessments diffused through social networks, is a pivotal mechanism for promoting cooperation in social dilemmas ubiquitous to distributed multi-agent systems comprising agents with limited perception and cognitive capabilities. Exploring efficient reputation systems, comprising reputation assessment rules and reputation-based policies, is a long-standing challenge. Previous work assumes predefined reputation assessment rules or models reputation as an intrinsic reward to learn policies, compromising the methods' ability for generalization and adaptation. To address this, we propose a distributed multi-agent reinforcement learning method $\textbf{COOPER}$ ($\textbf{COOP}$eration with $\textbf{E}$mergent $\textbf{R}$eputation), which jointly learns reputation assessment rules and reputation-based policies entirely from environment rewards. Notably, leveraging the underlying mechanisms of reputation, we deliberately design the constituent modules of $\textbf{COOPER}$ and the data flows among them, overcoming the latency and noise in the feedback signal, caused by the deep entanglement between reputation and policy. Experiments on the donation game and the coin game in grid world environments demonstrate that $\textbf{COOPER}$ effectively adapts to various existing reputation systems and co-players. Furthermore, we observe the co-emergence of reputation norms and cooperation in self-play settings. These results hold robustly across diverse social network topologies, underscoring the generalizability and efficacy of our approach.

cs.GT↗

arXiv2026

Trapping 11,000 Atoms in a Tweezer Array Generated by a Single Metasurface

The scalability of physical qubit numbers is a central challenge toward a universal fault-tolerant quantum computer. The inherent scalability of atom array quantum computers stems from the identical nature of atomic qubits, so the available qubit resource is primarily limited by the number of atoms that can be trapped and controlled. Here, we robustly trap 11,000 individual atoms in a tweezer array, thereby enabling the available qubit resource to reach the tens-of-thousands scale for the first time among all quantum computation platforms. This advance is enabled by a single metasurface, approximately 2 cm in diameter, that generates the entire tweezer array without the need for microscope objectives, thereby maximizing laser-power efficiency. The large aperture ensures a working distance of about 1.5 cm, allowing the metasurface to be placed outside the vacuum cell and avoiding the technical complications of in-vacuum operation. We further characterize the randomly loaded atom array using the statistical theory of percolation phase transitions. This work takes an important first step toward a quantum computer at the 10,000-qubit scale.

quant-ph↗

arXiv2026

Adaptive Punishment for Cooperation in Mixed-Motive Games

Mixed-motive scenarios are ubiquitous in real-world multi-agent interactions, where self-interested agents often defect for immediate rewards, overlooking the potential of altruistic cooperation to improve long-term gains and collective welfare. Peer punishment can deter defection, but as costly second-order altruism, its persistent imposition may undermine the punisher's interests. Existing approaches often struggle to effectively implement punishment to promote cooperation. To balance the efficacy and cost of punishment, we propose Adaptive Punishment for Cooperation (APC), a distributed method that determines punishment intensity based on both a dynamic punishment probability and the severity of defection. This dynamic probability substantially reduces costly and ineffective punishment while also promotes cooperation. To accurately assess defection and its severity, we use a defection awareness module, whose learning is guided by game reward. Theoretical analysis and empirical results show APC performs effectively in iterated public goods game. Empirically, APC also significantly outperforms existing baselines across sequential social dilemmas, learning rational and effective punishment policies that foster cooperation by strategically deterring defection.

cs.MA↗

arXiv2026

Convex Dataset Valuation for Post-Training

Improving LLM performance on downstream tasks sometimes requires leveraging auxiliary datasets during post-training. In practice, however, developers face constraints on compute, labeling, and licensing costs that preclude using all available data, necessitating principled dataset-level selection. These constraints are increasingly shaped by dataset marketplaces, where data acquisition is governed by budgets and negotiation. We study dataset valuation as a subset selection problem during LLM post-training. Our goal is to identify and weight auxiliary datasets so as to maximize target task performance given constrained budgets. We first show that commonly used gradient alignment scores provide a reasonable yet incomplete valuation signal, as they ignore redundancy among datasets. To address this, we propose a scalable convex dataset-level valuation method based on kernel mean matching (KMM) in gradient space, which jointly accounts for alignment with the target task and redundancy across auxiliary datasets. Through extensive experiments across diverse post-training settings and tasks, we show that our approach consistently outperforms existing valuation baselines, achieving stronger performance with low computational overhead. Our results position dataset valuation as a practical decision tool for post-training data selection in market-constrained large language model settings. The code is available at https://github.com/uiuctml/convex_data_valuation.

cs.LG↗

arXiv2026

Modeling Decision-Making with Will for Cooperation in Social Dilemmas

Standard rational actor models often attribute cooperation failures in social dilemmas to insufficient incentives, overlooking the destabilizing effects of continuous utility maximization. To address this, we propose a framework of ``will" defined as a mechanism that persistently pursues goals while ignoring local cost-benefit fluctuations. We formalize the Willed Agents as potential minimizers, distinguishing them from cumulative utility maximization. Dynamical analysis of infinite population demonstrates that willed agents shrink the feasible state space, acting as boundary constraints that accelerate convergence in canonical social dilemmas. Through multi-agent simulations in a spatiotemporal Stag Hunt Game, we show that willed agents function as ``cooperation catalysts", enabling groups to surmount high-risk thresholds where purely utility maximization fails. We find that heterogeneous will strength promotes cooperation, and that agents who autonomously suspend rational re-evaluation can significantly outperform continuous optimizers. These findings suggest that successful cooperation relies on the cognitive capacity to strategically constrain calculation.

cs.MA↗

arXiv2026

Expectation Error Bounds for Transfer Learning in Linear Regression and Linear Neural Networks

In transfer learning, the learner leverages auxiliary data to improve generalization on a main task. However, the precise theoretical understanding of when and how auxiliary data help remains incomplete. We provide new insights on this issue in two canonical linear settings: ordinary least squares regression and under-parameterized linear neural networks. For linear regression, we derive exact closed-form expressions for the expected generalization error with bias-variance decomposition, yielding necessary and sufficient conditions for auxiliary tasks to improve generalization on the main task. We also derive globally optimal task weights as outputs of solvable optimization programs, with consistency guarantees for empirical estimates. For linear neural networks with shared representations of width $q \leq K$, where $K$ is the number of auxiliary tasks, we derive a non-asymptotic expectation bound on the generalization error, yielding the first non-vacuous sufficient condition for beneficial auxiliary learning in this setting, as well as principled directions for task weight curation. We achieve this by proving a new column-wise low-rank perturbation bound for random matrices, which improves upon existing bounds by preserving fine-grained column structures. Our results are verified on synthetic data simulated with controlled parameters.

cs.LG↗

arXiv2026

Feed m Birds with One Scone: Accelerating Multi-task Gradient Balancing via Bi-level Optimization

In machine learning, the goal of multi-task learning (MTL) is to optimize multiple objectives together. Recent works, for example, Multiple Gradient Descent Algorithm (MGDA) and its variants, show promising results with dynamically adjusted weights for different tasks to mitigate conflicts that may potentially degrade the performance on certain tasks. Despite the empirical success of MGDA-type methods, one major limitation of such methods is their computational inefficiency, as they require access to all task gradients. In this paper we introduce MARIGOLD, a unified algorithmic framework for efficiently solving MTL problems. Our method reveals that multi-task gradient balancing methods have a hierarchical structure, in which the model training and the gradient balancing are coupled during the whole optimization process and can be viewed as a bi-level optimization problem. Moreover, we showcase that the bi-level problem can be solved efficiently by leveraging zeroth-order method. Extensive experiments on both public datasets and industrial-scale datasets demonstrate the efficiency and superiority of our method.

cs.LG↗

arXiv2026

Credibility Governance: A Social Mechanism for Collective Self-Correction under Weak Truth Signals

Online platforms increasingly rely on opinion aggregation to allocate real-world attention and resources, yet common signals such as engagement votes or capital-weighted commitments are easy to amplify and often track visibility rather than reliability. This makes collective judgments brittle under weak truth signals, noisy or delayed feedback, early popularity surges, and strategic manipulation. We propose Credibility Governance (CG), a mechanism that reallocates influence by learning which agents and viewpoints consistently track evolving public evidence. CG maintains dynamic credibility scores for both agents and opinions, updates opinion influence via credibility-weighted endorsements, and updates agent credibility based on the long-run performance of the opinions they support, rewarding early and persistent alignment with emerging evidence while filtering short-lived noise. We evaluate CG in POLIS, a socio-physical simulation environment that models coupled belief dynamics and downstream feedback under uncertainty. Across settings with initial majority misalignment, observation noise and contamination, and misinformation shocks, CG outperforms vote-based, stake-weighted, and no-governance baselines, yielding faster recovery to the true state, reduced lock-in and path dependence, and improved robustness under adversarial pressure. Our implementation and experimental scripts are publicly available at https://github.com/Wanying-He/Credibility_Governance.

cs.CY↗

arXiv2026

Learn to Evolve: Self-supervised Neural JKO Operator for Wasserstein Gradient Flow

The Jordan-Kinderlehrer-Otto (JKO) scheme provides a stable variational framework for computing Wasserstein gradient flows, but its practical use is often limited by the high computational cost of repeatedly solving the JKO subproblems. We propose a self-supervised approach for learning a JKO solution operator without requiring numerical solutions of any JKO trajectories. The learned operator maps an input density directly to the minimizer of the corresponding JKO subproblem, and can be iteratively applied to efficiently generate the gradient-flow evolution. A key challenge is that only a number of initial densities are typically available for training. To address this, we introduce a Learn-to-Evolve algorithm that jointly learns the JKO operator and its induced trajectories by alternating between trajectory generation and operator updates. As training progresses, the generated data increasingly approximates true JKO trajectories. Meanwhile, this Learn-to-Evolve strategy serves as a natural form of data augmentation, significantly enhancing the generalization ability of the learned operator. Numerical experiments demonstrate the accuracy, stability, and robustness of the proposed method across various choices of energies and initial conditions.

cs.LG↗

arXiv2025

Arbitrary-order exceptional points in a nanomechanical cavity

Higher-order exceptional points (EPs) govern non-Hermitian system dynamics through their enriched and sharpened spectral topology, yet the intrinsic topological fragility hinders robust experimental realization. Here, we present a scalable architecture that implements arbitrary-order EPs via a recurrent network comprising a single nanomechanical resonator and unlimited virtual resonators. We experimentally realize mechanical EPs up to the seventh order and confirm this architecture's scalability. Moreover, we reveal that the fundamental noise component and the measured signal share the same system coupling channel and thus undergo identical root-response amplification near EPs of arbitrary order, consistent with our signal-to-noise ratio measurements. Our work establishes a general platform for exploring higher-order EP-based phenomena while clarifying the fundamental boundary of non-Hermitian sensitivity enhancement across diverse physical systems.

physics.optics↗

arXiv2025

ValuePilot: A Two-Phase Framework for Value-Driven Decision-Making

Personalized decision-making is essential for human-AI interaction, enabling AI agents to act in alignment with individual users' value preferences. As AI systems expand into real-world applications, adapting to personalized values beyond task completion or collective alignment has become a critical challenge. We address this by proposing a value-driven approach to personalized decision-making. Human values serve as stable, transferable signals that support consistent and generalizable behavior across contexts. Compared to task-oriented paradigms driven by external rewards and incentives, value-driven decision-making enhances interpretability and enables agents to act appropriately even in novel scenarios. We introduce ValuePilot, a two-phase framework consisting of a dataset generation toolkit (DGT) and a decision-making module (DMM). DGT constructs diverse, value-annotated scenarios from a human-LLM collaborative pipeline. DMM learns to evaluate actions based on personal value preferences, enabling context-sensitive, individualized decisions. When evaluated on previously unseen scenarios, DMM outperforms strong LLM baselines, including GPT-5, Claude-Sonnet-4, Gemini-2-flash, and Llama-3.1-70b, in aligning with human action choices. Our results demonstrate that value-driven decision-making is an effective and extensible engineering pathway toward building interpretable, personalized AI agents.

cs.AI↗

arXiv2025

Direct Generation of an Array with 78400 Optical Tweezers Using a Single Metasurface

Scalability remains a major challenge in building practical fault-tolerant quantum computers. Currently, the largest number of qubits achieved across leading quantum platforms ranges from hundreds to thousands. In atom arrays, scalability is primarily constrained by the capacity to generate large numbers of optical tweezers, and conventional techniques using acousto-optic deflectors or spatial light modulators struggle to produce arrays much beyond $\sim 10,000$ tweezers. Moreover, these methods require additional microscope objectives to focus the light into micrometer-sized spots, which further complicates system integration and scalability. Here, we demonstrate the experimental generation of an optical tweezer array containing $280\times 280$ spots using a metasurface, nearly an order of magnitude more than most existing systems. The metasurface leverages a large number of subwavelength phase-control pixels to engineer the wavefront of the incident light, enabling both large-scale tweezer generation and direct focusing into micron-scale spots without the need for a microscope. This result shifts the scalability bottleneck for atom arrays from the tweezer generation hardware to the available laser power. Furthermore, the array shows excellent intensity uniformity exceeding $90\%$, making it suitable for homogeneous single-atom loading and paving the way for trapping arrays of more than $10,000$ atoms in the near future.

cond-mat.quant-gas↗

arXiv2025

Evaluating Generalization Capabilities of LLM-Based Agents in Mixed-Motive Scenarios Using Concordia

Large Language Model (LLM) agents have demonstrated impressive capabilities for social interaction and are increasingly being deployed in situations where they might engage with both human and artificial agents. These interactions represent a critical frontier for LLM-based agents, yet existing evaluation methods fail to measure how well these capabilities generalize to novel social situations. In this paper, we introduce a method for evaluating the ability of LLM-based agents to cooperate in zero-shot, mixed-motive environments using Concordia, a natural language multi-agent simulation environment. Our method measures general cooperative intelligence by testing an agent's ability to identify and exploit opportunities for mutual gain across diverse partners and contexts. We present empirical results from the NeurIPS 2024 Concordia Contest, where agents were evaluated on their ability to achieve mutual gains across a suite of diverse scenarios ranging from negotiation to collective action problems. Our findings reveal significant gaps between current agent capabilities and the robust generalization required for reliable cooperation, particularly in scenarios demanding persuasion and norm enforcement.

cs.AI↗

arXiv2025

On-chip Time-bin to Path Qubit Encoding Converter via Thin Film Lithium Niobate Photonics Chip

The development of quantum internet demands on-chip quantum processor nodes and interconnection between the nodes. Path-encoded photonic qubits are suitable for on-chip quantum information processors, while time-bin encoded ones are good at long-distance communication. It is necessary to develop an on-chip converter between the two encodings to satisfy the needs of the quantum internet. In this work, a quantum photonic circuit is proposed to convert time-bin-encoded photonic qubits to path-encoded ones via a thin-film lithium niobate high-speed optical switch and low-loss matched optical delay lines. The performance of the encoding converter is demonstrated by the experiment of time-bin to path encoding conversion on the fabricated sample chip. The converted path qubits have an average fidelity higher than 97%. The potential of the encoding converter on applications in quantum networks is demonstrated by the experiments of entanglement distribution and quantum key distribution. The results show that the on-chip encoding converter can serve as a foundational component in the future quantum internet, bridging the gap between quantum information transmission and on-chip processing based on photons.

quant-ph↗

arXiv2025

World Models Should Prioritize the Unification of Physical and Social Dynamics

World models, which explicitly learn environmental dynamics to lay the foundation for planning, reasoning, and decision-making, are rapidly advancing in predicting both physical dynamics and aspects of social behavior, yet predominantly in separate silos. This division results in a systemic failure to model the crucial interplay between physical environments and social constructs, rendering current models fundamentally incapable of adequately addressing the true complexity of real-world systems where physical and social realities are inextricably intertwined. This position paper argues that the systematic, bidirectional unification of physical and social predictive capabilities is the next crucial frontier for world model development. We contend that comprehensive world models must holistically integrate objective physical laws with the subjective, evolving, and context-dependent nature of social dynamics. Such unification is paramount for AI to robustly navigate complex real-world challenges and achieve more generalizable intelligence. This paper substantiates this imperative by analyzing core impediments to integration, proposing foundational guiding principles (ACE Principles), and outlining a conceptual framework alongside a research roadmap towards truly holistic world models.

cs.CY↗

arXiv2025

Social World Model-Augmented Mechanism Design Policy Learning

Designing adaptive mechanisms to align individual and collective interests remains a central challenge in artificial social intelligence. Existing methods often struggle with modeling heterogeneous agents possessing persistent latent traits (e.g., skills, preferences) and dealing with complex multi-agent system dynamics. These challenges are compounded by the critical need for high sample efficiency due to costly real-world interactions. World Models, by learning to predict environmental dynamics, offer a promising pathway to enhance mechanism design in heterogeneous and complex systems. In this paper, we introduce a novel method named SWM-AP (Social World Model-Augmented Mechanism Design Policy Learning), which learns a social world model hierarchically modeling agents' behavior to enhance mechanism design. Specifically, the social world model infers agents' traits from their interaction trajectories and learns a trait-based model to predict agents' responses to the deployed mechanisms. The mechanism design policy collects extensive training trajectories by interacting with the social world model, while concurrently inferring agents' traits online during real-world interactions to further boost policy learning efficiency. Experiments in diverse settings (tax policy design, team coordination, and facility location) demonstrate that SWM-AP outperforms established model-based and model-free RL baselines in cumulative rewards and sample efficiency.

cs.CY↗