arXiv subjects

Shuyuan Zhang

Publications and source records attributed to Shuyuan Zhang.

At least 19 recordsLinked to original sources

arXiv2026

From Connectivity to Rewards: Dense Reward Learning with Directed State Graphs

The integration of graphs with Goal-Conditioned Hierarchical Reinforcement Learning (GCHRL) has received increasing attention, as graphs naturally encode task hierarchies for effective subgoal sampling. However, existing methods often overlook intrinsic connectivity information, failing to fully leverage the underlying topology for efficient learning. Most graph-based GCHRL methods use the graph as a stochastic sampling tool rather than as an environmental model that encodes connectivity and state-accessibility information. This limitation is particularly acute in quasimetric environments, where the inherent asymmetry of state transitions poses a fundamental challenge to stable policy learning and robust path planning. In this paper, we address these problems by introducing a state connectivity model designed to predict pairwise state connectivity strength in asymmetric environments. We transform these connectivity strengths into scalar auxiliary dense rewards, providing continuous guidance across multiple hierarchical levels. We demonstrate that our proposed framework, Graph-Guided Quasimetric Dense Reward (G2QDR), can theoretically be integrated into any existing GCHRL architecture, and the state connectivity model is efficiently implemented via a neural network trained on a directed state graph generated during exploration. Empirical results across a wide range of sparse reward environments indicate that, in general, G2QDR can enhance the performance of baseline GCHRL approaches with acceptable computational overhead.

cs.LG↗

arXiv2026

Automated Synthesis of Lyapunov Functions for Multi-Agent Systems under Jointly Connected Topology

This article investigates the consensus tracking problem of multi-agent systems under jointly connected topology through automated synthesis of Lyapunov functions. Based on the proposed distributed nonlinear control protocol, several consensus criteria for first-order multi-agent systems are established and certified by the construction and synthesis of more general polynomial Lyapunov functions. By employing sum-of-squares decomposition for multivariate polynomials, we can efficiently synthesize polynomial Lyapunov functions to achieve consensus verification in polynomial time, although the widely used quadratic Lyapunov functions do not exist. Moreover, polynomial coupling functions for our proposed protocol are concomitantly generated. Furthermore, the distributed nonlinear control protocol is extended to deal with second-order multi-agent systems, while ensuring second-order consensus verification. Finally, an example is presented to demonstrate the efficacy of our method.

math.OC↗

arXiv2026

On Tikhonov Regularization for Direct and Indirect Data-Driven LQR Control

In recent years, the so-called `direct data-driven control' has been a topic of intense research, and it is expected that it will become prominent in future complex dynamical systems control. Within this framework, regularization not only implicitly enforces system identification, but also plays a crucial role in ensuring reliable closed-loop behavior. To further enhance the performance of data-driven controllers, we propose a new regularization method for direct data-driven LQR control of unknown LTI systems, based on a regularized covariance parameterization. Unlike existing data-driven techniques, the proposed method remains effective in handling ill-conditioned cases, such as when the data matrix has a large condition number. Then, we demonstrate that our method is equivalent to the indirect certainty-equivalence LQR combined with Tikhonov regularization. Furthermore, we extend our method to the design of controllers for unknown nonlinear systems using Koopman linear embedding. Finally, the simulation results validate the effectiveness and advantages of the proposed regularization method.

math.OC↗

arXiv2026

Co-Evolution of Policy and Internal Reward for Language Agents

Large language model (LLM) agents learn by interacting with environments, but long-horizon training remains fundamentally bottlenecked by sparse and delayed rewards. Existing methods typically address this challenge through post-hoc credit assignment or external reward models, which provide limited guidance at inference time and often separate reward improvement from policy improvement. We propose Self-Guide, a self-generated internal reward for language agents that supports both inference-time guidance and training-time supervision. Specifically, the agent uses Self-Guide as a short self-guidance signal to steer the next action during inference, and converts the same signal into step-level internal reward for denser policy optimization during training. This creates a co-evolving loop: better policy produces better guidance, and better guidance further improves policy as internal reward. Across three agent benchmarks, inference-time self-guidance already yields clear gains, while jointly evolving policy and internal reward with GRPO brings further improvements (8\%) over baselines trained solely with environment reward. Overall, our results suggest that language agents can improve not only by collecting more experience, but also by learning to generate and refine their own internal reward during acting and learning.

cs.LG↗

arXiv2026

PAct: Part-Decomposed Single-View Articulated Object Generation

Articulated objects are central to interactive 3D applications, including embodied AI, robotics, and VR/AR, where functional part decomposition and kinematic motion are essential. Yet producing high-fidelity articulated assets remains difficult to scale because it requires reliable part decomposition and kinematic rigging. Existing approaches largely fall into two paradigms: optimization-based reconstruction or distillation, which can be accurate but often takes tens of minutes to hours per instance, and inference-time methods that rely on template or part retrieval, producing plausible results that may not match the specific structure and appearance in the input observation. We introduce a part-centric generative framework for articulated object creation that synthesizes part geometry, composition, and articulation under explicit part-aware conditioning. Our representation models an object as a set of movable parts, each encoded by latent tokens augmented with part identity and articulation cues. Conditioned on a single image, the model generates articulated 3D assets that preserve instance-level correspondence while maintaining valid part structure and motion. The resulting approach avoids per-instance optimization, enables fast feed-forward inference, and supports controllable assembly and articulation, which are important for embodied interaction. Experiments on common articulated categories (e.g., drawers and doors) show improved input consistency, part accuracy, and articulation plausibility over optimization-based and retrieval-driven baselines, while substantially reducing inference time.

cs.CV↗

arXiv2026

Convex Model Predictive Control for Safe Output Consensus of Nonlinear Multi-Agent Systems

Nonlinear dynamics and safety constraints typically result in a nonlinear programming problem when applying model predictive control to achieve safe output consensus. To avoid the heavy computational burden of solving a nonlinear programming problem directly, this paper proposes a novel Convex Model Predictive Control (CMPC) approach based on a Sequential Quadratic Programming (SQP) scheme. The core of our method lies in transforming the nonlinear constraints into linear forms: we linearize the system dynamics and convexify the discrete-time high-order control barrier functions using a proposed tangent-line projection method. Consequently, the original problem is reduced to a quadratic program that can be iteratively solved within the SQP scheme at each time step of CMPC. Furthermore, we provide the formal guarantee of the convergence of the SQP scheme, and subsequently guarantee the recursive feasibility and stability of CMPC. Simulations on multi-agent systems with unicycle dynamics demonstrate a 35-52 times reduction in computation time compared with baseline methods, confirming the suitability of the proposed approach for real-time safe output consensus control.

eess.SY↗

arXiv2025

Towards better dense rewards in Reinforcement Learning Applications

Finding meaningful and accurate dense rewards is a fundamental task in the field of reinforcement learning (RL) that enables agents to explore environments more efficiently. In traditional RL settings, agents learn optimal policies through interactions with an environment guided by reward signals. However, when these signals are sparse, delayed, or poorly aligned with the intended task objectives, agents often struggle to learn effectively. Dense reward functions, which provide informative feedback at every step or state transition, offer a potential solution by shaping agent behavior and accelerating learning. Despite their benefits, poorly crafted reward functions can lead to unintended behaviors, reward hacking, or inefficient exploration. This problem is particularly acute in complex or high-dimensional environments where handcrafted rewards are difficult to specify and validate. To address this, recent research has explored a variety of approaches, including inverse reinforcement learning, reward modeling from human preferences, and self-supervised learning of intrinsic rewards. While these methods offer promising directions, they often involve trade-offs between generality, scalability, and alignment with human intent. This proposal explores several approaches to dealing with these unsolved problems and enhancing the effectiveness and reliability of dense reward construction in different RL applications.

cs.AI↗

arXiv2025

TCC-Bench: Benchmarking the Traditional Chinese Culture Understanding Capabilities of MLLMs

Recent progress in Multimodal Large Language Models (MLLMs) have significantly enhanced the ability of artificial intelligence systems to understand and generate multimodal content. However, these models often exhibit limited effectiveness when applied to non-Western cultural contexts, which raises concerns about their wider applicability. To address this limitation, we propose the Traditional Chinese Culture understanding Benchmark (TCC-Bench), a bilingual (i.e., Chinese and English) Visual Question Answering (VQA) benchmark specifically designed for assessing the understanding of traditional Chinese culture by MLLMs. TCC-Bench comprises culturally rich and visually diverse data, incorporating images from museum artifacts, everyday life scenes, comics, and other culturally significant contexts. We adopt a semi-automated pipeline that utilizes GPT-4o in text-only mode to generate candidate questions, followed by human curation to ensure data quality and avoid potential data leakage. The benchmark also avoids language bias by preventing direct disclosure of cultural concepts within question texts. Experimental evaluations across a wide range of MLLMs demonstrate that current models still face significant challenges when reasoning about culturally grounded visual content. The results highlight the need for further research in developing culturally inclusive and context-aware multimodal systems. The code and data can be found at: https://tcc-bench.github.io/.

cs.MM↗

arXiv2025

AI4X Roadmap: Artificial Intelligence for the advancement of scientific pursuit and its future directions

Artificial intelligence and machine learning are reshaping how we approach scientific discovery, not by replacing established methods but by extending what researchers can probe, predict, and design. In this roadmap we provide a forward-looking view of AI-enabled science across biology, chemistry, climate science, mathematics, materials science, physics, self-driving laboratories and unconventional computing. Several shared themes emerge: the need for diverse and trustworthy data, transferable electronic-structure and interatomic models, AI systems integrated into end-to-end scientific workflows that connect simulations to experiments and generative systems grounded in synthesisability rather than purely idealised phases. Across domains, we highlight how large foundation models, active learning and self-driving laboratories can close loops between prediction and validation while maintaining reproducibility and physical interpretability. Taken together, these perspectives outline where AI-enabled science stands today, identify bottlenecks in data, methods and infrastructure, and chart concrete directions for building AI systems that are not only more powerful but also more transparent and capable of accelerating discovery in complex real-world environments.

physics.soc-ph↗

arXiv2025

Incorporating Spatial Information into Goal-Conditioned Hierarchical Reinforcement Learning via Graph Representations

The integration of graphs with Goal-conditioned Hierarchical Reinforcement Learning (GCHRL) has recently gained attention, as intermediate goals (subgoals) can be effectively sampled from graphs that naturally represent the overall task structure in most RL tasks. However, existing approaches typically rely on domain-specific knowledge to construct these graphs, limiting their applicability to new tasks. Other graph-based approaches create graphs dynamically during exploration but struggle to fully utilize them, because they have problems passing the information in the graphs to newly visited states. Additionally, current GCHRL methods face challenges such as sample inefficiency and poor subgoal representation. This paper proposes a solution to these issues by developing a graph encoder-decoder to evaluate unseen states. Our proposed method, Graph-Guided sub-Goal representation Generation RL (G4RL), can be incorporated into any existing GCHRL method when operating in environments with primarily symmetric and reversible transitions to enhance performance across this class of problems. We show that the graph encoder-decoder can be effectively implemented using a network trained on the state graph generated during exploration. Empirical results indicate that leveraging high and low-level intrinsic rewards from the graph encoder-decoder significantly enhances the performance of state-of-the-art GCHRL approaches with an extra small computational cost in dense and sparse reward environments.

cs.LG↗

arXiv2025

ShapeCraft: LLM Agents for Structured, Textured and Interactive 3D Modeling

3D generation from natural language offers significant potential to reduce expert manual modeling efforts and enhance accessibility to 3D assets. However, existing methods often yield unstructured meshes and exhibit poor interactivity, making them impractical for artistic workflows. To address these limitations, we represent 3D assets as shape programs and introduce ShapeCraft, a novel multi-agent framework for text-to-3D generation. At its core, we propose a Graph-based Procedural Shape (GPS) representation that decomposes complex natural language into a structured graph of sub-tasks, thereby facilitating accurate LLM comprehension and interpretation of spatial relationships and semantic shape details. Specifically, LLM agents hierarchically parse user input to initialize GPS, then iteratively refine procedural modeling and painting to produce structured, textured, and interactive 3D assets. Qualitative and quantitative experiments demonstrate ShapeCraft's superior performance in generating geometrically accurate and semantically rich 3D assets compared to existing LLM-based agents. We further show the versatility of ShapeCraft through examples of animated and user-customized editing, highlighting its potential for broader interactive applications.

cs.CV↗

arXiv2025

Resonant diffraction and photoemission inconsistent with altermagnetism in epitaxial RuO$_2$ films

Excitement about the magnetic and electronic properties of RuO$_2$ is growing, fueled by reports of antiferromagnetism, strain-induced superconductivity, and its recent classification as a member of a newly proposed magnetic class, altermagnets, with RuO$_2$ widely regarded as the paradigmatic example. Nevertheless, the magnetic ground state of RuO$_2$ remains contentious, as several recent experiments report no evidence of magnetic order. To address this discrepancy, we performed resonant elastic scattering measurements on a series of epitaxial RuO$_2$ thin films grown on the (100)-plane of TiO$_2$ substrates across a range of strain states. Leveraging full polarization control and azimuthal scans of the structurally forbidden 100 Bragg reflection, we systematically tested for signatures of colinear antiferromagnetic order. We found that the resonant elastic scattering signal in RuO$_2$ thin films likely originates from anisotropic charge scattering, not long-range antiferromagnetic order. Using angle-resolved photoemission spectroscopy we uncover a band structure without altermagnetic band splitting that is consistent with a nonmagnetic phase. Similarly, anisotropic magnetoresistance results show no evidence of magnetism. The combination of three independent measurements suggests the absence of altermagnetism in RuO$_2$.

cond-mat.mtrl-sci↗

arXiv2025

A Highly Scalable LLM Clusters with Optical Interconnect

Recent years have witnessed the adoption of optical circuit switch (OCS) technology. How to design the physical topology, defined by the physical wiring between electrical switching equipments and the OCS, is fundamental to designing efficient OCS-based clusters. We identify three features to evaluate the quality of a physical topology design: logical topology compatibility, cluster scalability, and topology engineering polynomial-solvability. However, none of existing physical topologies has achieved these three features simultaneously. This paper explores designing an optimal physical topology that simultaneously maximizes all. We begin by analyzing the importance of these features in OCS-based cluster and examine the limitations of current designs. Leveraging a proposed \emph{Symmetric Integer Matrix Decomposition Theorem}, we outline a general approach for designing optimal physical topologies and introduce \textbf{Cross Wiring} as a concrete instantiation. The feasibility and advantages of Cross Wiring are verified through a 128-NPU testbed and large-scale real-trace-based simulations.

cs.NI↗

arXiv2025

Distributed Safety-Critical MPC for Multi-Agent Formation Control and Obstacle Avoidance

For nonlinear multi-agent systems with high relative degrees, achieving formation control and obstacle avoidance in a distributed manner remains a significant challenge. To address this issue, we propose a novel distributed safety-critical model predictive control (DSMPC) algorithm that incorporates discrete-time high-order control barrier functions (DHCBFs) to enforce safety constraints, alongside discrete-time control Lyapunov functions (DCLFs) to establish terminal constraints. To facilitate distributed implementation, we develop estimated neighbor states for formulating DHCBFs and DCLFs, while also devising a bound constraint to limit estimation errors and ensure convergence. Additionally, we provide theoretical guarantees regarding the feasibility and stability of the proposed DSMPC algorithm based on a mild assumption. The effectiveness of the proposed method is evidenced by the simulation results, demonstrating improved performance and reduced computation time compared to existing approaches.

eess.SY↗

arXiv2025

Towards Effective MLLM Jailbreaking Through Balanced On-Topicness and OOD-Intensity

Multimodal large language models (MLLMs) are widely used in vision-language reasoning tasks. However, their vulnerability to adversarial prompts remains a serious concern, as safety mechanisms often fail to prevent the generation of harmful outputs. Although recent jailbreak strategies report high success rates, many responses classified as "successful" are actually benign, vague, or unrelated to the intended malicious goal. This mismatch suggests that current evaluation standards may overestimate the effectiveness of such attacks. To address this issue, we introduce a four-axis evaluation framework that considers input on-topicness, input out-of-distribution (OOD) intensity, output harmfulness, and output refusal rate. This framework identifies truly effective jailbreaks. In a substantial empirical study, we reveal a structural trade-off: highly on-topic prompts are frequently blocked by safety filters, whereas those that are too OOD often evade detection but fail to produce harmful content. However, prompts that balance relevance and novelty are more likely to evade filters and trigger dangerous output. Building on this insight, we develop a recursive rewriting strategy called Balanced Structural Decomposition (BSD). The approach restructures malicious prompts into semantically aligned sub-tasks, while introducing subtle OOD signals and visual cues that make the inputs harder to detect. BSD was tested across 13 commercial and open-source MLLMs, where it consistently led to higher attack success rates, more harmful outputs, and fewer refusals. Compared to previous methods, it improves success rates by $67\%$ and harmfulness by $21\%$, revealing a previously underappreciated weakness in current multimodal safety systems.

cs.CV↗

arXiv2025

SCAR: Shapley Credit Assignment for More Efficient RLHF

Reinforcement Learning from Human Feedback (RLHF) is a widely used technique for aligning Large Language Models (LLMs) with human preferences, yet it often suffers from sparse reward signals, making effective credit assignment challenging. In typical setups, the reward model provides a single scalar score for an entire generated sequence, offering little insight into which token or span-level decisions were responsible for the outcome. To address this, we propose Shapley Credit Assignment Rewards (SCAR), a novel method that leverages Shapley values in cooperative game theory. SCAR distributes the total sequence-level reward among constituent tokens or text spans based on their principled marginal contributions. This creates dense reward signals, crucially, without necessitating the training of auxiliary critique models or recourse to fine-grained human annotations at intermediate generation stages. Unlike prior dense reward methods, SCAR offers a game-theoretic foundation for fair credit attribution. Theoretically, we demonstrate that SCAR preserves the original optimal policy, and empirically, across diverse tasks including sentiment control, text summarization, and instruction tuning, we show that SCAR converges significantly faster and achieves higher final reward scores compared to standard RLHF and attention-based dense reward baselines. Our findings suggest that SCAR provides a more effective and theoretically sound method for credit assignment in RLHF, leading to more efficient alignment of LLMs.

cs.AI↗

arXiv2025

Region of Synchronization Estimation for Complex Networks via SOS Programming

In this article, we explore the problem of the region of synchronization (ROS) for complex networks with nonlinear dynamics. Given a pair of state- and target- sets, our goal is to estimate the ROS such that the trajectories originating within it reach the target set (i.e., synchronization manifold), without leaving the state set before the first hitting time. In order to do so, an exponential guidance-barrier function is proposed to construct the ROS along the synchronization manifold, and the corresponding sufficient conditions for estimating the ROS are developed. The resulting conditions lead to a sum-of-squares programming problem, thereby affording a polynomial-time solvability. Furthermore, when the synchronization manifold reduces to an equilibrium point, our method not only estimates a larger ROS compared to existing results but also allows the ROS to take more general shapes. Finally, we present two numerical examples to demonstrate the effectiveness of the theoretical results.

math.OC↗

arXiv2025

Improving efficiency and stability for perovskite solar cell with diethylene glycol dimethacrylate modification

The humidity resistance is the key challenges that hinder the commercial application of perovskite solar cells (PSCs). Herein, we propose an ultra-thin acrylate polymer (diethylene glycol dimethacrylate, DGDMA) into perovskite films to investigate the influence of polymerized networks on stability. The monomer molecules containing acrylate and carbonyl groups were selected, and the effects of the polymerized were quantified with different concentration. The experimental results show that, when the concentration of DGDMA is 1 mg/ml, the PCE increases from 18.06% to 21.82%, which is optimum. The monomer molecules with carbonyl groups polymerize, they can chelate with uncoordinated Pb2+ in perovskite films to improve the film quality, reduce the surface defect density to decrease non-radiative recombination, and also significantly enhance the humidity stability of PSCs.

cond-mat.mtrl-sci↗