arXiv subjects

Yao Lyu

Publications and source records attributed to Yao Lyu.

At least 19 recordsLinked to original sources

arXiv2026

Momentum as Residual-Driven Multiplier Correction for Deep Learning Optimization

Momentum-based optimizers are widely used in modern deep learning, yet the relations among momentum recursion, update geometry, and acceleration remain only partially understood. We develop an $\textbf{A}$DMM-$\textbf{I}$nspired $\textbf{M}$omentum (AIM) framework based on residual-penalty variable splitting, which interprets momentum as a multiplier-like correction driven by the splitting residual. AIM recovers the exponential moving average of gradients from an ADMM-style multiplier update and separates two mechanisms that are usually intertwined in practical optimizers: the residual penalty determines the update geometry, whereas the approximation of the objective-related subproblem determines the acceleration form. Building on AIM, we propose $\textbf{R}$elativistic $\textbf{A}$daptive gradient $\textbf{D}$escent with $\textbf{A}$ccelerated $\textbf{R}$esidual (RADAR), which combines relativistic adaptive geometry, decoupled residual correction, and second-order momentum filtering to improve the update direction and momentum estimation. We establish stochastic convergence through a variance-perturbed Lyapunov drift analysis. Experiments on supervised vision learning, language modeling, and reinforcement learning show that RADAR achieves consistent improvements over strong adaptive optimizer baselines.

cs.LG↗

arXiv2026

Distributional Soft Bellman Operator under the Cram\'er Geometry

Distributional soft policy iteration (DSPI) provides an important framework for combining distributional reinforcement learning (DRL) with maximum-entropy control, in which the policy evaluation step is governed by a distributional soft Bellman operator acting on entropy-regularised returns. Theoretical analysis of such an evaluation step requires a probability metric under which Bellman updates can be controlled, typically by showing that the operator contracts the distance between any two candidate return-distribution estimates. In this paper, we focus on the Cram\'er geometry, a cumulative distribution function (CDF)-based metric with an $L^2$ structure, and study whether the fixed-policy distributional soft Bellman operator has this contraction property and hence a unique fixed point under this metric. Working directly on an admissible CDF field domain, we formulate the CDF-level distributional soft Bellman operator, prove that it is a $\sqrt{\gamma}$-contraction, and obtain the corresponding unique fixed point together with convergent iterative policy evaluation. The CDF formulation also shows that this finite-Cram\'er-domain property follows from a uniform first-moment condition on the combined one-step reward entropy shift, rather than from separate uniform boundedness assumptions on the reward and entropy terms. We then transport the same evaluation problem to the spectral domain by conjugation, obtaining an equivalent Hilbert-space representation of the same decision process. Taken together, these results identify the Cram\'er-geometric Bellman fixed point associated with the policy-evaluation step of DSPI, providing a reference point for studying approximate critics, evaluation error, and critic-loss design in DSPI-style algorithms.

cs.LG↗

arXiv2026

Co-Designing Community-Centered AI Education for Adults: A Midwestern Case Study

Artificial Intelligence (AI) education is increasingly important, yet adults outside higher education receive less attention. We report a case study of an AI education session with 54 adults (48 in-person and 6 virtual) in a predominantly African American community on the east side of a major Midwestern city. We ask: "What does AI education for adults outside formal educational systems look like in practice?" and "What does this AI education session reveal about AI literacy at the community level?" Through a co-designed session developed with community partners, we found that concerns about AI persisted but shifted to specific, locally grounded questions about AI design and deployment. We also discuss AI literacy from a community capacity perspective and argue for AI literacy frameworks grounded in local community contexts that strengthen community capacity.

cs.HC↗

arXiv2026

Factor-Aware Mixture-of-Experts with Pretrained Encoder for Combinatorial Generalization

The integration of pretrained encoders with diffusion policies has become a dominant paradigm for visual robotic manipulation. However, it still struggles to generalize across complex environments with varying factors such as lighting and surface textures. To address this, we propose FAME, a framework that integrates a factor-aware mixture-of-experts (MoE) with a pretrained encoder to enhance generalization to environmental variations. FAME follows a three-stage training process: (1) policy warmup, where a diffusion policy is trained on standard-environment data with a frozen encoder; (2) factor-specific adapter training, where lightweight adapters inserted between the frozen encoder and the temporarily frozen policy are trained on customized datasets, each targeting a distinct environmental variation; and (3) joint fine-tuning, where a central router and the warmed policy are trained on mixed data to handle multiple factors jointly. FAME is ``factor-aware'' because the central router softly weights frozen factor-specific adapters as a dense MoE, enabling combinatorial generalization across multiple factors. Evaluations on the Meta-World benchmark show that FAME outperforms diffusion policy baselines by 34%. We further validate FAME in a real-world pick-and-place task using a compact model trained on newly collected data, where FAME achieves a 35% improvement in generalization under real-world variations.

cs.RO↗

arXiv2026

M3imic: Learning a Versatile Whole-Body Controller for Multimodal Motion Mimicking

Building a general-purpose whole-body controller is essential for enabling diverse motion capabilities in humanoid robots across a wide range of downstream tasks, including locomotion and loco-manipulation. Different tasks rely on distinct motion reference modalities: locomotion primarily depends on coordinated robot joint trajectories, whereas manipulation requires precise end-effector trajectory tracking. Existing methods often overlook the representational mismatch between dense robot joint angles and sparse end-effector poses. To address this, we propose Multi-Modal Mimic (M3imic), a versatile multi-modal whole-body control framework that unifies heterogeneous motion reference modalities, including robot joint angles, human pose trajectories, and end-effector poses, using modality-specific encoders to map them into a shared latent space. Leveraging large-scale reinforcement learning in the simulator, we train a single policy that achieves sim-to-real transfer across multiple motion reference modalities without modality-specific retraining. Extensive simulation and real-world experiments on the Unitree G1 robot are conducted to evaluate the proposed framework. In simulation, the policy achieves a peak success rate of 98.42\% on an unseen test dataset, demonstrating its exceptional generalization capability. The code is available at https://github.com/Renforce-Dynamics/MultiModalWBC

cs.RO↗

arXiv2026

FUSE: A Framework for Unified State Estimation in Vehicular and Robotic SLAM Systems

Tightly coupled SLAM formulations under mixed-rate sensing often bind temporal processing, local geometric association, estimator formulation, and map-update policy into method-specific designs. Such binding makes it difficult to vary one design choice without re-engineering the rest of the state-estimation process. This paper presents FUSE, a framework for unified state estimation in vehicular and robotic SLAM systems. FUSE organizes the state-estimation interface around observation ingestion, propagation, update, and state query, and uses this interface to separate temporal processing, residual-ready local geometric association, estimator formulation, and map-update policy. A LiDAR--IMU instantiation is developed to examine the framework under mixed-rate sensing and directional degeneracy, where high-rate inertial propagation, LiDAR-triggered geometric update, residual screening, and degeneracy-aware correction operate through the same interface boundaries. On a 418~m loop-corridor sequence, the instantiation reports a 1.626 m end-to-end trajectory error, corresponding to a 7.9% relative error reduction compared with Faster-LIO, the lowest-error baseline on this sequence. The results support FUSE as a framework for organizing state-estimation design choices and show how the evaluated instantiation regularizes updates along weakly observable directions.

cs.RO↗

arXiv2026

Natural Gradient Bayesian Filtering: Geometry-Aware Filter for Dynamical Systems

Bayesian filtering is a cornerstone of state estimation in complex systems such as aerospace systems, yet exact solutions are available only for linear Gaussian models. In practice,nonlinear systems are handled through tractable approximations,with Gaussian filters such as the extended and unscented Kalman filters being among the most widely used methods. This tutorial revisits Gaussian filtering from an information-geometric perspective, viewing the prediction and measurement update steps as inference procedures over state distributions. Within this framework, we introduce a geometry-aware Gaussian filtering approach that leverages natural gradient descent on the statistical manifold of Gaussian distributions. The resulting Natural Gradient Gaussian Approximation (NANO) filter iteratively refines the posterior mean and covariance while respecting the intrinsic geometry of the Gaussian family and preserving the positive definiteness of the covariance matrix. We further highlight fundamental connections to the classical Kalman filtering, showing that a single natural-gradient step exactly recovers the Kalman measurement update in the linear-Gaussian case. The practical implications of the proposed framework are illustrated through case studies in representative nonlinear estimation problems,including satellite attitude estimation, simultaneous localization and mapping, and state estimation for robotic systems including quadruped and humanoid robots.

cs.RO↗

arXiv2026

Augmented Lagrangian Multiplier Network for State-wise Safety in Reinforcement Learning

Safety is a primary challenge in real-world reinforcement learning (RL). Formulating safety requirements as state-wise constraints has become a prominent paradigm. Handling state-wise constraints with the Lagrangian method requires a distinct multiplier for every state, necessitating neural networks to approximate them as a multiplier network. However, applying standard dual gradient ascent to multiplier networks induces severe training oscillations. This is because the inherent instability of dual ascent is exacerbated by network generalization -- local overshoots and delayed updates propagate to adjacent states, further amplifying policy fluctuations. Existing stabilization techniques are designed for scalar multipliers, which are inadequate for state-dependent multiplier networks. To address this challenge, we propose an augmented Lagrangian multiplier network (ALaM) framework for stable learning of state-wise multipliers. ALaM consists of two key components. First, a quadratic penalty is introduced into the augmented Lagrangian to compensate for delayed multiplier updates and establish the local convexity near the optimum, thereby mitigating policy oscillations. Second, the multiplier network is trained via supervised regression toward a dual target, which stabilizes training and promotes convergence. Theoretically, we show that ALaM guarantees multiplier convergence and thus recovers the optimal policy of the constrained problem. Building on this framework, we integrate soft actor-critic (SAC) with ALaM to develop the SAC-ALaM algorithm. Experiments demonstrate that SAC-ALaM outperforms state-of-the-art safe RL baselines in both safety and return, while also stabilizing training dynamics and learning well-calibrated multipliers for risk identification.

cs.LG↗

arXiv2026

Natural Gradient Gaussian Approximation Filter on Lie Groups for Robot State Estimation

Accurate state estimation for robotic systems evolving on Lie group manifolds, such as legged robots, is a prerequisite for achieving agile control. However, this task is challenged by nonlinear observation models defined on curved manifolds, where existing filters rely on local linearization in the tangent space to handle such nonlinearity, leading to accumulated estimation errors. To address this limitation, we reformulate manifold filtering as a parameter optimization problem over a Gaussian-distributed increment variable, thereby avoiding linearization. Under this formulation, the increment can be mapped to the Lie group through the exponential operator, where it acts multiplicatively on the prior estimate to yield the posterior state. We further propose a natural gradient optimization scheme for solving this problem, whose iteration process leverages the Fisher information matrix of the increment variable to account for the curvature of the tangent space. This results in an iterative algorithm named the Natural Gradient Gaussian Approximation on Lie Groups (NANO-L) filter. Leveraging the perturbation model in Lie derivative, we prove that for the invariant observation model widely adopted in robotic localization tasks, the covariance update in NANO-L admits an exact closed-form solution, eliminating the need for iterative updates thus improving computational efficiency. Hardware experiments on a Unitree GO2 legged robot operating across different terrains demonstrate that NANO-L achieves approximately 40% lower estimation error than commonly used filters at a comparable computational cost.

cs.RO↗

arXiv2026

A Spectral Revisit of the Distributional Bellman Operator under the Cramér Metric

Distributional reinforcement learning (DRL) studies the evolution of full return distributions under Bellman updates rather than focusing on expected values. A classical result is that the distributional Bellman operator is contractive under the Cramér metric, which corresponds to an $L^2$ geometry on differences of cumulative distribution functions (CDFs). While this contraction ensures stability of policy evaluation, existing analyses remain largely metric, focusing on contraction properties without elucidating the structural action of the Bellman update on distributions. In this work, we analyse distributional Bellman dynamics directly at the level of CDFs, treating the Cramér geometry as the intrinsic analytical setting. At this level, the Bellman update acts affinely on CDFs and linearly on differences between CDFs, and its contraction property yields a uniform bound on this linear action. Building on this intrinsic formulation, we construct a family of regularised spectral Hilbert representations that realise the CDF-level geometry by exact conjugation, without modifying the underlying Bellman dynamics. The regularisation affects only the geometry and vanishes in the zero-regularisation limit, recovering the native Cramér metric. This framework clarifies the operator structure underlying distributional Bellman updates and provides a foundation for further functional and operator-theoretic analyses in DRL.

cs.LG↗

arXiv2026

Monetizing Generative AI: YouTubers' Collective Knowledge on Earning from Generative AI Content

Generative Artificial Intelligence (GenAI) is reshaping creative labor by enabling the rapid production of text, images, and videos. On YouTube, creators are developing new ways to leverage these tools and share knowledge about how to pursue income through such strategies. However, little is known about what GenAI knowledge has been collectively constructed around monetizing GenAI as a community practice of acting both with and against algorithmically mediated platforms. We analyze 377 YouTube videos in which creators publicly promote workflows, revenue claims, and monetization strategies for GenAI-enabled content. Our analysis identifies ten shared use cases that frame AI-supported income opportunities, and examines how this GenAI knowledge repository embodies a collective effort to leverage platform infrastructures for monetization -- including advertising, direct sales, affiliate marketing, and revenue-sharing models. We further surface structural tensions in AI-mediated creative labor, including unverifiable income claims, content misappropriation, synthetic engagement practices, and shifting authorship norms. We conceptualize creators' collective understanding and adoption of GenAI in the context of monetizing creative labor, with implications for the design of creator-centered GenAI technologies and responsible platform policy.

cs.HC↗

arXiv2026

Real-Time Generative Policy via Langevin-Guided Flow Matching for Autonomous Driving

Reinforcement learning (RL) is a fundamental methodology in autonomous driving systems, where generative policies exhibit considerable potential by leveraging their ability to model complex distributions to enhance exploration. However, their inherent high inference latency severely impedes their deployment in real-time decision-making and control. To address this issue, we propose diffusion actor-critic with entropy regulator via flow matching (DACER-F) by introducing flow matching into online RL, enabling the generation of competitive actions in a single inference step. By leveraging Langevin dynamics and gradients of the Q-function, DACER-F dynamically optimizes actions from experience replay toward a target distribution that balances high Q-value information with exploratory behavior. The flow policy is then trained to efficiently learn a mapping from a simple prior distribution to this dynamic target. In complex multi-lane and intersection simulations, DACER-F outperforms baselines diffusion actor-critic with entropy regulator (DACER) and distributional soft actor-critic (DSAC), while maintaining an ultra-low inference latency. DACER-F further demonstrates its scalability on standard RL benchmark DeepMind Control Suite (DMC), achieving a score of 775.8 in the humanoid-stand task and surpassing prior methods. Collectively, these results establish DACER-F as a high-performance and computationally efficient RL algorithm.

cs.LG↗

arXiv2026

"My Brother Is a School Principal, Earns About $80,000 Per Year... But When the Kids See Me, 'Wow, Uncle, You Have 1500 Followers on TikTok!'": A Study of Blind TikTokers' Alternative Professional Development Experiences

One's profession is an essential part of modern life. Traditionally, professional development has been criticized for excluding people with disabilities. People with visual impairments, for example, face disproportionately low employment rates, highlighting persistent gaps in professional opportunities. Recently, there has been growing research on social media platforms as spaces for more equitable career development approaches. In this paper, we present an interview study on the professional development experiences of 60 people with visual impairments on TikTok (also known as "BlindTokers"). We report BlindTokers' goals, strategies, and challenges, supported by detailed examples and in-depth analysis. Based on the findings, we identify that BlindTokers' practices reveal an alternative professional development approach that is more flexible, inclusive, personalized, and diversified than traditional models. Our study also extends professional development research by foregrounding emerging digital skills and proposing design implications to foster more equitable and inclusive professional opportunities.

cs.HC↗

arXiv2026

"I'm Constantly Getting Comments Like, 'Oh, You're Blind. You're Like the Only Woman That I Stand a Chance With.'": A Study of Blind TikTokers' Intersectional Experiences of Gender and Sexuality

Social media platforms are important venues for identity expression, and the Human-Computer Interaction community has been paying growing attention to how marginalized groups express their identities on these platforms. Joining the emerging literature on intersectional experiences, we study blind TikTokers ("BlindTokers") who are also women and/or LGBTQ+. Using interview data from \rev{41} participants, we identify their intersectional experiences as mediated by TikTok's socio-technical affordances. We argue that BlindTokers' intersectional marginalization is infrastructural: TikTok's classification and moderation features interact with social norms in ways that push them aside and distort how they are treated on the platform. We use this infrastructure perspective to understand what these experiences are, how they were formed, and how they become harmful. We further recognize participants' infrastructuring work to address these problems. This study guides future social media design with accessible creator tools, inclusive identity options, and context-aware moderation developed in partnership with communities.

cs.HC↗

arXiv2025

"I thought it was my mistake, but it's really the design'': A Critical Examination of the Accessibility of User-Enacted Moderation Tools on Facebook and X

As social media platforms increasingly promote the use of user-enacted moderation tools (e.g., reporting, blocking, content filters) to address online harms, it becomes crucially important that such controls are usable for everyone. We evaluate the accessibility of these moderation tools on two mainstream platforms -- Facebook and X -- through interviews and task-based walkthroughs with 15 individuals with vision impairments. Adapting the lens of \emph{administrative burden of safety work}, we identify three interleaved costs that users with vision loss incur while interacting with moderation tools: \emph{learning costs} (understanding what controls do and where they live), \emph{compliance costs} (executing multi-step procedures under screen reader and low-vision conditions), and \emph{psychological costs} (experiencing uncertainty, stress, and diminished agency). Our analysis bridges the fields of content moderation and accessibility in HCI research and contributes (1) a cross-platform catalog of accessibility and usability breakdowns affecting safety tools; and (2) design recommendations for reducing this burden.

cs.HC↗

arXiv2025

Jump-Start Reinforcement Learning with Self-Evolving Priors for Extreme Monopedal Locomotion

Reinforcement learning (RL) has shown great potential in enabling quadruped robots to perform agile locomotion. However, directly training policies to simultaneously handle dual extreme challenges, i.e., extreme underactuation and extreme terrains, as in monopedal hopping tasks, remains highly challenging due to unstable early-stage interactions and unreliable reward feedback. To address this, we propose JumpER (jump-start reinforcement learning via self-evolving priors), an RL training framework that structures policy learning into multiple stages of increasing complexity. By dynamically generating self-evolving priors through iterative bootstrapping of previously learned policies, JumpER progressively refines and enhances guidance, thereby stabilizing exploration and policy optimization without relying on external expert priors or handcrafted reward shaping. Specifically, when integrated with a structured three-stage curriculum that incrementally evolves action modality, observation space, and task objective, JumpER enables quadruped robots to achieve robust monopedal hopping on unpredictable terrains for the first time. Remarkably, the resulting policy effectively handles challenging scenarios that traditional methods struggle to conquer, including wide gaps up to 60 cm, irregularly spaced stairs, and stepping stones with distances varying from 15 cm to 35 cm. JumpER thus provides a principled and scalable approach for addressing locomotion tasks under the dual challenges of extreme underactuation and extreme terrains.

cs.RO↗

arXiv2025

A Systematic Literature Review of Infrastructure Studies in SIGCHI

Infrastructure is an indispensable part of human life. Over the past decades, the Human-Computer Interaction (HCI) community has paid increasing attention to human interactions with infrastructure. In this paper, we conducted a systematic literature review on infrastructure studies in SIGCHI, one of the most influential communities in HCI. We collected a total of 190 primary studies, covering works published between 2006 and 2024. Most of these studies are inspired by Susan Leigh Star's notion of infrastructure. We identify three major themes in infrastructure studies: growing infrastructure, appropriating infrastructure, and coping with infrastructure. Our review highlights a prevailing trend in SIGCHI's infrastructure research: a focus on informal infrastructural activities across various sociotechnical contexts. In particular, we examine studies that problematize infrastructure and alert the HCI community to its potentially harmful aspects.

cs.HC↗

arXiv2025

Conversational Agents for Older Adults' Health: A Systematic Literature Review

There has been vast literature that studies Conversational Agents (CAs) in facilitating older adults' health. The vast and diverse studies warrants a comprehensive review that concludes the main findings and proposes research directions for future studies, while few literature review did it from human-computer interaction (HCI) perspective. In this study, we present a survey of existing studies on CAs for older adults' health. Through a systematic review of 72 papers, this work reviewed previously studied older adults' characteristics and analyzed participants' experiences and expectations of CAs for health. We found that (1) Past research has an increasing interest on chatbots and voice assistants and applied CA as multiple roles in older adults' health. (2) Older adults mainly showed low acceptance CAs for health due to various reasons, such as unstable effects, harm to independence, and privacy concerns. (3) Older adults expect CAs to be able to support multiple functions, to communicate using natural language, to be personalized, and to allow users full control. We also discuss the implications based on the findings.

cs.HC↗