arXiv subjects

Siying Wang

Publications and source records attributed to Siying Wang.

12 recordsLinked to original sources

arXiv2026

Evolving Cache Schedules for Fast Diffusion Policy Inference

Diffusion policies achieve strong visuomotor control by iteratively denoising action chunks, but repeated denoising makes real-time deployment computationally demanding. Cache-based methods reduce inference cost by reusing intermediate activations, but existing training-free schedules typically allocate computation uniformly across blocks, ignoring heterogeneous redundancy across blocks and leading to a suboptimal performance-efficiency trade-off. To bridge this gap, we introduce Evolving Cache Schedules (EVO), a training-free acceleration framework that globally schedules cache refreshes via evolutionary search. EVO represents each candidate as a complete schedule over the block-timestep lattice. Thus, redundant transformer computations during iterative denoising can be skipped through cache reuse while preserving closed-loop rollout performance. To make the search practical, EVO introduces redundancy-aware initialization, which seeds the population with promising schedules, and target-conditioned early stopping, which verifies and terminates once a desired performance target is reached. The offline-optimized schedule can be directly plugged into pretrained diffusion policies without retraining. Extensive manipulation benchmarks show that EVO preserves near-full performance while substantially reducing computation, achieving up to 8.05x action-generation speedup and reducing FLOPs from 15.77G to as low as 1.96G. Source code is available at https://github.com/pillom/EVO.

cs.CV↗

arXiv2026

GraSP: Graph-Structured Skill Compositions for LLM Agents

Skill ecosystems for LLM agents have matured rapidly, yet recent benchmarks show that providing agents with more skills does not monotonically improve performance -- focused sets of 2-3 skills outperform comprehensive documentation, and excessive skills actually hurt. The bottleneck has shifted from skill availability to skill orchestration: agents need not more skills, but a structural mechanism to select, compose, and execute them with explicit causal dependencies. We propose GraSP, the first executable skill graph architecture that introduces a compilation layer between skill retrieval and execution. GraSP transforms flat skill sets into typed directed acyclic graphs (DAGs) with precondition-effect edges, executes them with node-level verification, and performs locality-bounded repair through five typed operators -- reducing replanning from O(N) to O(d^h). Across ALFWorld, ScienceWorld, WebShop, and InterCode with eight LLM backbones, GraSP outperforms ReAct, Reflexion, ExpeL, and flat skill baselines in every configuration, improving reward by up to +19 points over the strongest baseline while cutting environment steps by up to 41%. GraSP's advantage grows with task complexity and is robust to both skill over-retrieval and quality degradation, confirming that structured orchestration -- not larger skill libraries -- is the key to reliable agent execution.

cs.CL↗

arXiv2026

AD-Bench: A Real-World, Trajectory-Aware Advertising Analytics Benchmark for LLM Agents

While Large Language Model (LLM) agents have made remarkable progress on complex reasoning, evaluating them in real-world environments remains an open problem. Existing benchmarks are largely confined to idealized simulations and fail to capture specialized domains such as advertising and marketing analytics, where tasks require multi-round interaction with professional tools and where ground-truth answers quickly become obsolete as data and platform rules evolve. To address this, we propose AD-Bench, a benchmark built from real user marketing-analysis requests on a production advertising platform. AD-Bench introduces two key designs: (i) a dynamic ground-truth pipeline that replays expert tool-call trajectories to regenerate answers consistent with the current environment, mitigating answer obsolescence; and (ii) a trajectory-aware evaluation that jointly measures end-to-end answer correctness (Pass@k) and trajectory coverage. Requests are stratified into three difficulty levels (L1-L3) to probe multi-round, multi-tool collaboration. Experiments show that the best model, Claude-Opus-4.7, attains Pass@1 = 76.9% and Pass@3 = 80.4% with 82.7% trajectory coverage overall, yet drops sharply on L3 to Pass@1 = 61.4% and Pass@3 = 65.1%, revealing that even state-of-the-art agents have substantial gaps in complex advertising analytics.

cs.CL↗

arXiv2025

Auto-US: An Ultrasound Video Diagnosis Agent Using Video Classification Framework and LLMs

AI-assisted ultrasound video diagnosis presents new opportunities to enhance the efficiency and accuracy of medical imaging analysis. However, existing research remains limited in terms of dataset diversity, diagnostic performance, and clinical applicability. In this study, we propose \textbf{Auto-US}, an intelligent diagnosis agent that integrates ultrasound video data with clinical diagnostic text. To support this, we constructed \textbf{CUV Dataset} of 495 ultrasound videos spanning five categories and three organs, aggregated from multiple open-access sources. We developed \textbf{CTU-Net}, which achieves state-of-the-art performance in ultrasound video classification, reaching an accuracy of 86.73\% Furthermore, by incorporating large language models, Auto-US is capable of generating clinically meaningful diagnostic suggestions. The final diagnostic scores for each case exceeded 3 out of 5 and were validated by professional clinicians. These results demonstrate the effectiveness and clinical potential of Auto-US in real-world ultrasound applications. Code and data are available at: https://github.com/Bean-Young/Auto-US.

cs.CV↗

arXiv2025

Representation Discrepancy Bridging Method for Remote Sensing Image-Text Retrieval

Remote Sensing Image-Text Retrieval (RSITR) plays a critical role in geographic information interpretation, disaster monitoring, and urban planning by establishing semantic associations between image and textual descriptions. Existing Parameter-Efficient Fine-Tuning (PEFT) methods for Vision-and-Language Pre-training (VLP) models typically adopt symmetric adapter structures for exploring cross-modal correlations. However, the strong discriminative nature of text modality may dominate the optimization process and inhibits image representation learning. The nonnegligible imbalanced cross-modal optimization remains a bottleneck to enhancing the model performance. To address this issue, this study proposes a Representation Discrepancy Bridging (RDB) method for the RSITR task. On the one hand, a Cross-Modal Asymmetric Adapter (CMAA) is designed to enable modality-specific optimization and improve feature alignment. The CMAA comprises a Visual Enhancement Adapter (VEA) and a Text Semantic Adapter (TSA). VEA mines fine-grained image features by Differential Attention (DA) mechanism, while TSA identifies key textual semantics through Hierarchical Attention (HA) mechanism. On the other hand, this study extends the traditional single-task retrieval framework to a dual-task optimization framework and develops a Dual-Task Consistency Loss (DTCL). The DTCL improves cross-modal alignment robustness through an adaptive weighted combination of cross-modal, classification, and exponential moving average consistency constraints. Experiments on RSICD and RSITMD datasets show that the proposed RDB method achieves a 6%-11% improvement in mR metrics compared to state-of-the-art PEFT methods and a 1.15%-2% improvement over the full fine-tuned GeoRSCLIP model.

cs.CV↗

arXiv2025

Heterogeneous Value Decomposition Policy Fusion for Multi-Agent Cooperation

Value decomposition (VD) has become one of the most prominent solutions in cooperative multi-agent reinforcement learning. Most existing methods generally explore how to factorize the joint value and minimize the discrepancies between agent observations and characteristics of environmental states. However, direct decomposition may result in limited representation or difficulty in optimization. Orthogonal to designing a new factorization scheme, in this paper, we propose Heterogeneous Policy Fusion (HPF) to integrate the strengths of various VD methods. We construct a composite policy set to select policies for interaction adaptively. Specifically, this adaptive mechanism allows agents' trajectories to benefit from diverse policy transitions while incorporating the advantages of each factorization method. Additionally, HPF introduces a constraint between these heterogeneous policies to rectify the misleading update caused by the unexpected exploratory or suboptimal non-cooperation. Experimental results on cooperative tasks show HPF's superior performance over multiple baselines, proving its effectiveness and ease of implementation.

cs.MA↗

arXiv2025

Double Distillation Network for Multi-Agent Reinforcement Learning

Multi-agent reinforcement learning typically employs a centralized training-decentralized execution (CTDE) framework to alleviate the non-stationarity in environment. However, the partial observability during execution may lead to cumulative gap errors gathered by agents, impairing the training of effective collaborative policies. To overcome this challenge, we introduce the Double Distillation Network (DDN), which incorporates two distillation modules aimed at enhancing robust coordination and facilitating the collaboration process under constrained information. The external distillation module uses a global guiding network and a local policy network, employing distillation to reconcile the gap between global training and local execution. In addition, the internal distillation module introduces intrinsic rewards, drawn from state information, to enhance the exploration capabilities of agents. Extensive experiments demonstrate that DDN significantly improves performance across multiple scenarios.

cs.MA↗

arXiv2025

Optimistic {\epsilon}-Greedy Exploration for Cooperative Multi-Agent Reinforcement Learning

The Centralized Training with Decentralized Execution (CTDE) paradigm is widely used in cooperative multi-agent reinforcement learning. However, conventional methods based on CTDE can suffer from value underestimation and converge to suboptimal solutions. While such underestimation is typically attributed to the representational limitations of monotonic structures, we provide a novel perspective by demonstrating that the insufficient sampling of optimal joint actions during exploration is also a critical factor. To address this problem, we propose Optimistic $\epsilon$-Greedy Exploration. Our method introduces optimistic action-value networks that serve as decoupled exploration indicators, which we theoretically prove to converge in probability to the maximum achievable returns. By sampling actions from these distributions with a probability of $\epsilon$, we effectively increase the selection frequency of high-return joint actions. Experimental results in various environments reveal that our strategy effectively prevents the algorithm from falling into suboptimal solutions and significantly improves final returns, win rates, and convergence speeds compared to other enhanced algorithms. Our code has been open-sourced at https://github.com/qxqxtxdy/OptimisticExploration.

cs.MA↗

arXiv2022

Sender-controlled measurement-device-independent multiparty quantum communication

Multiparty quantum communication is an important branch of quantum networks. It enables private information transmission with information-theoretic security among legitimate parties. We propose a sender-controlled measurement-device-independent multiparty quantum communication protocol. The sender Alice divides a private message into several parts and delivers them to different receivers for secret sharing with imperfect measurement devices and untrusted ancillary nodes. Furthermore, Alice acts as an active controller and checks the security of quantum channels and the reliability of each receiver before she encodes her private message for secret sharing, which makes the protocol convenient for multiparity quantum communication.

quant-ph↗

arXiv2019

Multiple Partitions Aligned Clustering

Multi-view clustering is an important yet challenging task due to the difficulty of integrating the information from multiple representations. Most existing multi-view clustering methods explore the heterogeneous information in the space where the data points lie. Such common practice may cause significant information loss because of unavoidable noise or inconsistency among views. Since different views admit the same cluster structure, the natural space should be all partitions. Orthogonal to existing techniques, in this paper, we propose to leverage the multi-view information by fusing partitions. Specifically, we align each partition to form a consensus cluster indicator matrix through a distinct rotation matrix. Moreover, a weight is assigned for each view to account for the clustering capacity differences of views. Finally, the basic partitions, weights, and consensus clustering are jointly learned in a unified framework. We demonstrate the effectiveness of our approach on several real datasets, where significant improvement is found over other state-of-the-art multi-view clustering methods.

cs.LG↗

arXiv2016

Robust Joint Alignment of Multiple Versions of a Piece of Music

Large music content libraries often comprise multiple versions of a piece of music. To establish a link between different versions, automatic music alignment methods map each position in one version to a corresponding position in another version. Due to the leeway in interpreting a piece, any two versions can differ significantly, for example, in terms of local tempo, articulation, or playing style. For a given pair of versions, these differences can be significant such that even state-of-the-art methods fail to identify a correct alignment. In this paper, we present a novel method that increases the robustness for difficult to align cases. Instead of aligning only pairs of versions as done in previous methods, our method aligns multiple versions in a joint manner. This way, the alignment can be computed by comparing each version not only with one but with several versions, which stabilizes the comparison and leads to an increase in alignment robustness. Using recordings from the Mazurka Project, the alignment error for our proposed method was 14% lower on average compared to a state-of-the-art method, with significantly less outliers (standard deviation 53% lower).

cs.SD↗

arXiv2006

Fluorescence blinking statistics from single CdSe nanorods

We report fluorescence blinking statistics measured from single CdSe nanorods (NRs) of seven different sizes with aspect ratio ranging from 3 to 11. This study included core/shell CdSe/ZnSe NRs and core NRs with two different surface ligands producing different degrees of surface passivation. We compare the findings for NRs to our measurements of blinking statistics from spherical CdSe core and CdSe/ZnS core/shell nanocrystals (NCs). We find that for both NRs and spherical NCs, the off-time probability distributions are well described by a power law, while the on-time probability distributions are best described by a truncated power law. The measured crossover time is indistinguishable within experimental uncertainty for core and core/shell NRs, and for core NRs with different ligands, indicating that surface passivation does not affect the blinking statistics significantly. We find that at fixed excitation intensity, the inverse crossover time increases approximately linearly with increasing NR aspect ratio; for a given sample, the inverse crossover time increases very gradually with increasing excitation intensity. The measured per-particle absorption cross section for all samples indicates that the change in NR absorption cross-section with sample size can account for some but not all of the differences in crossover time. This suggests that the degree of quantum confinement may be partially responsible for the aspect ratio dependence of the crossover time.

cond-mat.mtrl-sci↗