arXiv subjects

Hongyi Li

Publications and source records attributed to Hongyi Li.

At least 19 recordsLinked to original sources

arXiv2026

PGMT: Perceptive General Motion Tracking for Humanoid Robots

Humanoid motion trackers can reproduce diverse whole-body motions, but their performance degrades on complex terrain where terrain-agnostic references become physically infeasible. We present PGMT, a Perceptive General Motion Tracking pipeline for humanoid robots that learns terrain adaptation from independently selected motion references and terrains. PGMT first learns a general tracking and recovery prior, then incorporates terrain perception through motion-conditioned terrain glimpses that selectively encode regions relevant to the current motion. Terrain-aware tracking relaxation allows necessary deviations from the reference while preserving its motion intent. Zero-shot deployment on a Unitree G1 demonstrates robust terrain-adaptive locomotion and whole-body motion execution over real-world terrain with obstacles up to 37 cm high, while supporting teleoperation, dynamic motion tracking, and fall recovery. PGMT extends general humanoid motion tracking beyond flat ground, providing a unified policy for terrain-adaptive locomotion, diverse whole-body behaviors, and teleoperation in complex environments. Project homepage: https://luyili.github.io/pgmt/

cs.RO↗

arXiv2026

SWAP: Symmetric Equivariant World-Model for Agile Robot Parkour

While latent world models enable the proactive predictions required for extreme parkour, their purely data-driven nature forces them to redundantly encode left-right symmetric interactions as independent patterns. This inflates the learning burden and hinders the capture of geometric regularities, restricting the latent space's efficiency for downstream policies. To address this, we propose SWAP, an end-to-end equivariant symmetric world model. This framework embeds symmetry directly into both the world model and the actor-critic networks. In real-world tests, the robot leaps across a 2.13 m gap and climbs a 1.63 m platform, breaking records for quadruped parkour. Furthermore, the framework exhibits robust geometric generalization to unseen mirrored terrains and exceptional zero-shot transferability across diverse outdoor environments. These results demonstrate that symmetry equivariance is an effective structural prior for pushing the physical boundaries of learned legged locomotion.

cs.RO↗

arXiv2026

TAGA: Terrain-aware Active Gaze Learning for Generalizable Agile Humanoid Locomotion

Agile humanoid locomotion across diverse challenging terrain demands both wide perceptual coverage and precise local geometry understanding. Motivated by the way humans selectively look at relevant terrain during locomotion, we introduce TAGA, a Terrain-aware Active Gaze learning framework for Attention-based humanoid control. By fusing vision, proprioception, and motion commands, our framework guides the model to learn anticipatory cues and actively attend to specific areas of the height scan, selectively using these informative regions for the downstream network. This adaptively increases the information density of observations under tight onboard computational constraints, thus enabling fine-grained perceptive locomotion over larger-scale terrains. We find that such gaze behaviors can naturally emerge through reinforcement learning alone, without requiring additional supervision or explicit guidance, significantly improve training efficiency. As a result, the trained policy demonstrates robust and generalizable locomotion in simulation and on hardware, including reliable terrain-aware foothold selection, elevated-platform traversal, competitive sparse-foothold traversal, and the largest reported real-world gap traversal distance of 1.2m among perceptive humanoid locomotion systems, while maintaining stability under severe perceptual disturbances and environmental interference.

cs.RO↗

arXiv2026

2.4 GHz Flip-flop Device within Nonequilibrium Superconducting Diode

Superconducting diode effect exhibits asymmetric critical supercurrent and has profound implications for condensed matter physics. The technical appeals of such superconducting diodes are their ultrahigh on-off ratio and diode efficiency for superconducting electronics owing to the dissipationless supercurrent therein. However, realizing superconducting diode operation at high working frequency, which is a key requirement for practical applications, remains elusive and challenging. Here, we demonstrate a polarity-controllable superconducting diode with non-equilibrium Josephson junction and its edge-triggered flip-flop operation at a high frequency up to 2.4 GHz, within a van der Waals superconductor 2M-WS$_2$. By simply tuning the thickness of superconducting 2M-WS$_2$ nanoflakes to engineer inversion asymmetry in the junction, we achieve a high diode efficiency of 67% and an on-off ratio exceeding 10$^5$. Importantly, the pulse width and duty cycle of output pulse signals in such superconducting diode flip-flop devices can be controlled in a broadband frequency range crossing 12 orders of magnitude. Theoretical analysis reveals that the non-equilibrium dynamic nature of supercurrent in these Josephson junctions enables such a high diode operating frequency and the polarity control of supercurrent. The 2.4 GHz non-equilibrium Josephson diode developed here provides a promising platform for advanced superconducting logic circuits and broadband telecommunication applications.

cond-mat.supr-con↗

arXiv2026

Hinge Regression Trees and HRT-Boost: Newton-Optimized Oblique Learning for Compact Tabular Models

Learning high-quality oblique decision trees remains a significant challenge due to the discrete and non-convex nature of split optimization. We present the Hinge Regression Tree (HRT) framework, which reframes each oblique split as a nonlinear least-squares problem over two linear predictors whose max/min envelope induces ReLU-like representation capacity. We show that the resulting node-level optimization can be interpreted as a damped Newton method, and we establish the monotonic decrease of the node objective for its backtracking line-search variant. We establish, theoretically, that HRT is a universal approximator with an explicit $O(\delta^2)$ approximation rate. Building upon this base learner, we propose HRT-Boost, a mathematically synergistic ensemble extension that couples node-level Newton updates with stage-wise functional gradient descent. We show that this ensemble construction admits a stage-wise empirical risk reduction guarantee under the squared loss. Empirical evaluations on synthetic and real-world benchmarks show that HRT is highly competitive with established single-tree baselines, and HRT-Boost compares favorably with strong ensemble baselines and often yields substantially more compact models. The code is publicly available at https://github.com/Hongyi-Li-sz/HRT-Boost.

cs.LG↗

arXiv2026

Joint sparse coding and temporal dynamics support context reconfiguration

Adaptive behavior requires the brain to transition between distinct contexts while maintaining representations of prior experience. The ability to reconfigure neural representations without erasing previously acquired knowledge is central to learning in dynamic environments, yet the neural mechanisms that support this balance remain unclear. Understanding these mechanisms is also critical for addressing catastrophic forgetting in artificial systems designed for lifelong learning. Here, we identify joint sparse coding and temporal dynamics in both the mouse medial prefrontal cortex (mPFC) and computational networks as mechanisms that help preserve prior representations during context transitions. Specifically, sparsity in context-dependent representations reduces cross-context interference, whereas temporal dynamics within the network activity further enhance context separability across time. Strikingly, networks endowed with both properties, such as spiking neural networks, exhibit improved retention during lifelong learning without auxiliary heuristics. These findings establish joint sparse coding and temporal dynamics as a core mechanism supporting flexible context reconfiguration in lifelong learning and, through their activity constraining nature, as an energy-efficient architectural principle for stable adaptation. Together, they provide a mechanistic framework for understanding how the brain preserves prior knowledge while flexibly adapting to new contexts.

q-bio.NC↗

arXiv2026

Day-Ahead Offering for Virtual Power Plants: A Stochastic Linear Programming Reformulation and Projected Subgradient Method

Virtual power plants (VPPs) are an emerging paradigm that aggregates distributed energy resources (DERs) for coordinated participation in power systems, including bidding as a single dispatchable entity in the wholesale market. In this paper, we address a critical operational challenge for VPPs: the day-ahead offering problem under highly intermittent and uncertain DER outputs and market prices. The day-ahead offering problem determines the price-quantity pairs submitted by VPPs while balancing profit opportunities against operational uncertainties. First, we formulate the problem as a scenario-based two-stage stochastic adaptive robust optimization problem, where the uncertainty of the locational marginal prices follows a Markov process and DER uncertainty is characterized by static uncertainty sets. Then, motivated by the outer approximation principle of the column-and-constraint generation (CC&G) algorithm, we propose a novel inner approximation-based projected subgradient method. By exploiting the problem structure, we propose two novel approaches to improve computational tractability. First, we show that under mild modeling assumptions, the robust second-stage problem can be equivalently reformulated as a linear program (LP) with a nested resource allocation structure that is amenable to an efficient greedy algorithm. Furthermore, motivated by the computational efficiency of solving the reformulated primal second-stage problem and the isotonic structure of the first-stage feasible region, we propose an efficient projected subgradient algorithm to solve the overall stochastic LP problem. Extensive computational experiments using real-world data demonstrate that the overall projected subgradient descent method achieves about two orders of magnitude speedup over CC&G while maintaining solution quality.

math.OC↗

arXiv2026

Expert Streaming: Accelerating Low-Batch MoE Inference via Multi-chiplet Architecture and Dynamic Expert Trajectory Scheduling

Mixture-of-Experts is a promising approach for edge AI with low-batch inference. Yet, on-device deployments often face limited on-chip memory and severe workload imbalance; the prevalent use of offloading further incurs off-chip memory access bottlenecks. Moreover, MoE sparsity and dynamic gating shift distributed strategies toward much finer granularity and introduce runtime scheduling considerations. Recently, high die-to-die bandwidth chiplet interconnects have created new opportunities for multi-chiplet systems to address workload imbalance and offloading bottlenecks with fine-grained scheduling. In this paper, we propose Fully Sharded Expert Data Parallelism, a parallelization paradigm specifically architected for low-batch MoE inference on multi-chiplet accelerators. FSE-DP attains adaptive computation-communication overlap and balanced load by orchestrating fine-grained, complementary expert streams along dynamic trajectories across high-bandwidth D2D links. The attendant dataflow complexity is tamed by a minimal, hardware-amenable set of virtualization rules and a lightweight scheduling algorithm. Our approach achieves 1.22 to 2.00 times speedup over state-of-the-art baselines and saves up to 78.8 percent on-chip memory.

cs.AR↗

arXiv2026

Loosely-Structured Software: Engineering Context, Structure, and Evolution Entropy in Runtime-Rewired Multi-Agent Systems

As LLM-based multi-agent systems (MAS) become more autonomous, their free-form interactions increasingly dominate system behavior. However, scaling the number of agents often amplifies context pressure, coordination errors, and system drift. It is well known that building robust MAS requires more than prompt tuning or increased model intelligence. It necessitates engineering discipline focused on architecture to manage complexity under uncertainty. We characterize agentic software by a core property: \emph{runtime generation and evolution under uncertainty}. Drawing upon and extending software engineering experience, especially object-oriented programming, this paper introduces \emph{Loosely-Structured Software (LSS)}, a new class of software systems that shifts the engineering focus from constructing deterministic logic to managing the runtime entropy generated by View-constructed programming, semantic-driven self-organization, and endogenous evolution. To make this entropy governable, we introduce design principles under a three-layer engineering framework: \emph{View/Context Engineering} to manage the execution environment and maintain task-relevant Views, \emph{Structure Engineering} to organize dynamic binding over artifacts and agents, and \emph{Evolution Engineering} to govern the lifecycle of self-rewriting artifacts. Building on this framework, we develop LSS design patterns as semantic control blocks that stabilize fluid, inference-mediated interactions while preserving agent adaptability. Together, these abstractions improve the \emph{designability}, \emph{scalability}, and \emph{evolvability} of agentic infrastructure. We provide basic experimental validation of key mechanisms, demonstrating the effectiveness of LSS.

cs.SE↗

arXiv2026

Hinge Regression Tree: A Newton Method for Oblique Regression Tree Splitting

Oblique decision trees combine the transparency of trees with the power of multivariate decision boundaries, but learning high-quality oblique splits is NP-hard, and practical methods still rely on slow search or theory-free heuristics. We present the Hinge Regression Tree (HRT), which reframes each split as a non-linear least-squares problem over two linear predictors whose max/min envelope induces ReLU-like expressive power. The resulting alternating fitting procedure is exactly equivalent to a damped Newton (Gauss-Newton) method within fixed partitions. We analyze this node-level optimization and, for a backtracking line-search variant, prove that the local objective decreases monotonically and converges; in practice, both fixed and adaptive damping yield fast, stable convergence and can be combined with optional ridge regularization. We further prove that HRT's model class is a universal approximator with an explicit $O(\delta^2)$ approximation rate, and show on synthetic and real-world benchmarks that it matches or outperforms single-tree baselines with more compact structures.

cs.LG↗

arXiv2026

Distributed Model Predictive Control for Energy and Comfort Optimization in Large Buildings Using Piecewise Affine Approximation

The control of large buildings encounters challenges in computational efficiency due to their size and nonlinear components. To address these issues, this paper proposes a Piecewise Affine (PWA)-based distributed scheme for Model Predictive Control (MPC) that optimizes energy and comfort through PWA-based quadratic programming. We utilize the Alternating Direction Method of Multipliers (ADMM) for effective decomposition and apply the PWA technique to handle the nonlinear components. To solve the resulting large-scale nonconvex problems, the paper introduces a convex ADMM algorithm that transforms the nonconvex problem into a series of smaller convex problems, significantly enhancing computational efficiency. Furthermore, we demonstrate that the convex ADMM algorithm converges to a local optimum of the original problem. A case study involving 36 zones validates the effectiveness of the proposed method. Our proposed method reduces execution time by 86\% compared to the centralized version.

math.OC↗

arXiv2026

Classification of Invariant Subalgebras in a class of factors with property (T)

Let $n\geq 2$ and $G_n=\mathbb{Z}^n\rtimes SL_n(\mathbb{Z})$. We classify all $G_n$-invariant von Neumann subalgebras in $L(G_n)$. For $n=2$, this gives an alternative proof of the previous result of Jiang-Liu. For $n\geq 3$, this gives the first class of property (T) groups without the invariant subalgebras rigidity property but invariant subalgebras in the corresponding group factors can still be classified. As a corollary, $L(G_n)$ admits a unique maximal Haagerup $G_n$-invariant von Neumann subalgebra.

math.OA↗

arXiv2026

Rotation-Robust Regression with Convolutional Model Trees

We study rotation-robust learning for image inputs using Convolutional Model Trees (CMTs) [1], whose split and leaf coefficients can be structured on the image grid and transformed geometrically at deployment time. In a controlled MNIST setting with a rotation-invariant regression target, we introduce three geometry-aware inductive biases for split directions -- convolutional smoothing, a tilt dominance constraint, and importance-based pruning -- and quantify their impact on robustness under in-plane rotations. We further evaluate a deployment-time orientation search that selects a discrete rotation maximizing a forest-level confidence proxy without updating model parameters. Orientation search improves robustness under severe rotations but can be harmful near the canonical orientation when confidence is misaligned with correctness. Finally, we observe consistent trends on MNIST digit recognition implemented as one-vs-rest regression, highlighting both the promise and limitations of confidence-based orientation selection for model-tree ensembles.

cs.CV↗

arXiv2025

START: Traversing Sparse Footholds with Terrain Reconstruction

Traversing terrains with sparse footholds like legged animals presents a promising yet challenging task for quadruped robots, as it requires precise environmental perception and agile control to secure safe foot placement while maintaining dynamic stability. Model-based hierarchical controllers excel in laboratory settings, but suffer from limited generalization and overly conservative behaviors. End-to-end learning-based approaches unlock greater flexibility and adaptability, but existing state-of-the-art methods either rely on heightmaps that introduce noise and complex, costly pipelines, or implicitly infer terrain features from egocentric depth images, often missing accurate critical geometric cues and leading to inefficient learning and rigid gaits. To overcome these limitations, we propose START, a single-stage learning framework that enables agile, stable locomotion on highly sparse and randomized footholds. START leverages only low-cost onboard vision and proprioception to accurately reconstruct local terrain heightmap, providing an explicit intermediate representation to convey essential features relevant to sparse foothold regions. This supports comprehensive environmental understanding and precise terrain assessment, reducing exploration cost and accelerating skill acquisition. Experimental results demonstrate that START achieves zero-shot transfer across diverse real-world scenarios, showcasing superior adaptability, precise foothold placement, and robust locomotion.

cs.RO↗

arXiv2025

Optimizing DER Aggregate Flexibility via Network Reconfiguration

The aggregate flexibility region of distributed energy resources (DERs) quantifies the aggregate power shaping capabilities of DERs. It characterizes the distribution network's potential for wholesale market participation and grid service provision at the transmission level. To enhance flexibility and fully exploit the potential of DERs, this paper proposes a method to optimize the aggregate flexibility region through distribution network reconfiguration. First, we formulate the ellipsoidal aggregate flexibility region characterization problem as a two-stage adaptive robust optimization problem and derive an exact convex reformulation with a large number of second-order cone constraints. By exploiting the problem structure, we propose a scalable Benders decomposition algorithm with provable finite convergence to the optimal solution. Finally, we propose an optimal reconfiguration problem for aggregate flexibility region optimization and solve it using the custom Benders decomposition. Numerical simulations on the IEEE 123-bus test feeder demonstrate that, compared to existing approaches, substantial improvements in the aggregate flexibility region can be achieved over multiple scenarios with the optimized topology.

eess.SY↗

arXiv2025

Convolutional Model Trees

A method for creating a forest of model trees to fit samples of a function defined on images is described in several steps: down-sampling the images, determining a tree's hyperplanes, applying convolutions to the hyperplanes to handle small distortions of training images, and creating forests of model trees to increase accuracy and achieve a smooth fit. A 1-to-1 correspondence among pixels of images, coefficients of hyperplanes and coefficients of leaf functions offers the possibility of dealing with larger distortions such as arbitrary rotations or changes of perspective. A theoretical method for smoothing forest outputs to produce a continuously differentiable approximation is described. Within that framework, a training procedure is proved to converge.

cs.LG↗

arXiv2025

DER Day-Ahead Offering: A Neural Network Column-and-Constraint Generation Approach

In the day-ahead energy market, the offering strategy of distributed energy resource (DER) aggregators must be submitted before the uncertainty realization in the form of price-quantity pairs. This work addresses the day-ahead offering problem through a two-stage adaptive robust stochastic optimization model, wherein the first-stage price-quantity pairs and second-stage operational commitment decisions are made before and after DER uncertainty is realized, respectively. Uncertainty in day-ahead price is addressed using a stochastic programming-based approach, while uncertainty of DER generation is handled through robust optimization. To address the max-min structure of the second-stage problem, a neural network-accelerated column-and-constraint generation method is developed. A dedicated neural network is trained to approximate the value function, while optimality is maintained by the design of the network architecture. Numerical studies indicate that the proposed method yields high-quality solutions and is up to 100 times faster than Gurobi and 33 times faster than classical column-and-constraint generation on the same 1028-node synthetic distribution network.

eess.SY↗

arXiv2025

StyleBreak: Revealing Alignment Vulnerabilities in Large Audio-Language Models via Style-Aware Audio Jailbreak

Large Audio-language Models (LAMs) have recently enabled powerful speech-based interactions by coupling audio encoders with Large Language Models (LLMs). However, the security of LAMs under adversarial attacks remains underexplored, especially through audio jailbreaks that craft malicious audio prompts to bypass alignment. Existing efforts primarily rely on converting text-based attacks into speech or applying shallow signal-level perturbations, overlooking the impact of human speech's expressive variations on LAM alignment robustness. To address this gap, we propose StyleBreak, a novel style-aware audio jailbreak framework that systematically investigates how diverse human speech attributes affect LAM alignment robustness. Specifically, StyleBreak employs a two-stage style-aware transformation pipeline that perturbs both textual content and audio to control linguistic, paralinguistic, and extralinguistic attributes. Furthermore, we develop a query-adaptive policy network that automatically searches for adversarial styles to enhance the efficiency of LAM jailbreak exploration. Extensive evaluations demonstrate that LAMs exhibit critical vulnerabilities when exposed to diverse human speech attributes. Moreover, StyleBreak achieves substantial improvements in attack effectiveness and efficiency across multiple attack paradigms, highlighting the urgent need for more robust alignment in LAMs.

cs.SD↗