Searcharxiv⌕ Search

arXiv subjects

Zhihao Wang

Publications and source records attributed to Zhihao Wang.

At least 55 records · Page 3Linked to original sources
arXiv2025

Towards a Playground to Democratize Experimentation and Benchmarking of AI Agents for Network Troubleshooting

Recent research has demonstrated the effectiveness of Artificial Intelligence (AI), and more specifically, Large Language Models (LLMs), in supporting network configuration synthesis and automating network diagnosis tasks, among others. In this preliminary work, we restrict our focus to the application of AI agents to network troubleshooting and elaborate on the need for a standardized, reproducible, and open benchmarking platform, where to build and evaluate AI agents with low operational effort.

cs.NI↗
arXiv2025

A Novel ViDAR Device With Visual Inertial Encoder Odometry and Reinforcement Learning-Based Active SLAM Method

In the field of multi-sensor fusion for simultaneous localization and mapping (SLAM), monocular cameras and IMUs are widely used to build simple and effective visual-inertial systems. However, limited research has explored the integration of motor-encoder devices to enhance SLAM performance. By incorporating such devices, it is possible to significantly improve active capability and field of view (FOV) with minimal additional cost and structural complexity. This paper proposes a novel visual-inertial-encoder tightly coupled odometry (VIEO) based on a ViDAR (Video Detection and Ranging) device. A ViDAR calibration method is introduced to ensure accurate initialization for VIEO. In addition, a platform motion decoupled active SLAM method based on deep reinforcement learning (DRL) is proposed. Experimental data demonstrate that the proposed ViDAR and the VIEO algorithm significantly increase cross-frame co-visibility relationships compared to its corresponding visual-inertial odometry (VIO) algorithm, improving state estimation accuracy. Additionally, the DRL-based active SLAM algorithm, with the ability to decouple from platform motion, can increase the diversity weight of the feature points and further enhance the VIEO algorithm's performance. The proposed methodology sheds fresh insights into both the updated platform design and decoupled approach of active SLAM systems in complex environments.

cs.RO↗
arXiv2025

Scaling of symmetry-restricted quantum circuits

The intrinsic symmetries of physical systems have been employed to reduce the number of degrees of freedom of systems, thereby simplifying computations. In this work, we investigate the properties of $\mathcal{M}SU(2^N)$, $\mathcal{M}$-invariant subspaces of the special unitary Lie group $SU(2^N)$ acting on $N$ qubits, for some $\mathcal{M}\subseteq M_{2^N}(\mathbb{C})$. We demonstrate that for certain choices of $\mathcal{M}$, the subset $\mathcal{M}SU(2^N)$ inherits many topological and group properties from $SU(2^N)$. We then present a combinatorial method for computing the dimension of such subspaces when $\mathcal{M}$ is a representation of a permutation group acting on qubits $(GSU(2^N))$, or a Hamiltonian $(H^{(N)}SU(2^N))$. The Kronecker product of $\mathfrak{su}(2)$ matrices is employed to construct the Lie algebras associated with different permutation-invariant groups $GSU(2^N)$. Numerical results on the number of dimensions support the the developed theory.

quant-ph↗
arXiv2025

Efficient Robotic Policy Learning via Latent Space Backward Planning

Current robotic planning methods often rely on predicting multi-frame images with full pixel details. While this fine-grained approach can serve as a generic world model, it introduces two significant challenges for downstream policy learning: substantial computational costs that hinder real-time deployment, and accumulated inaccuracies that can mislead action extraction. Planning with coarse-grained subgoals partially alleviates efficiency issues. However, their forward planning schemes can still result in off-task predictions due to accumulation errors, leading to misalignment with long-term goals. This raises a critical question: Can robotic planning be both efficient and accurate enough for real-time control in long-horizon, multi-stage tasks? To address this, we propose a Latent Space Backward Planning scheme (LBP), which begins by grounding the task into final latent goals, followed by recursively predicting intermediate subgoals closer to the current state. The grounded final goal enables backward subgoal planning to always remain aware of task completion, facilitating on-task prediction along the entire planning horizon. The subgoal-conditioned policy incorporates a learnable token to summarize the subgoal sequences and determines how each subgoal guides action extraction. Through extensive simulation and real-robot long-horizon experiments, we show that LBP outperforms existing fine-grained and forward planning methods, achieving SOTA performance. Project Page: https://lbp-authors.github.io

cs.RO↗
arXiv2025

Frobenius homomorphisms for stated ${\rm SL}_n$-skein modules

The stated ${\rm SL}_n$-skein algebra $\mathscr{S}_{\hat{q}}(\mathfrak{S})$ of a surface $\mathfrak{S}$ is a quantization of the ${\rm SL}_n$-character variety, and is spanned over $\mathbb{Z}[\hat{q}^{\pm 1}]$ by framed tangles in $\mathfrak{S} \times (-1,1)$. If $\hat{q}$ is evaluated at a root of unity $\hatω$ with the order of $\hatω^{4n^2}$ being $N$, then for $\hatη = \hatω^{N^2}$, the Frobenius homomorphism $Φ: \mathscr{S}_{\hatη}(\mathfrak{S}) \to \mathscr{S}_{\hatω}(\mathfrak{S})$ is a surface generalization of the well-known Frobenius homomorphism between quantum groups. We show that the image under $Φ$ of a framed oriented knot $α$ is given by threading along $α$ of the reduced power elementary polynomial, which is an ${\rm SL}_n$-analog of the Chebyshev polynomial $T_N$. This generalizes Bonahon and Wong's result for $n=2$, and confirms a conjecture of Bonahon and Higgins. Our proof uses representation theory of quantum groups and its skein theoretic interpretation, and does not require heavy computations. We also extend our result to marked 3-manifolds.

math.GT↗
arXiv2025

TVDiag: A Task-oriented and View-invariant Failure Diagnosis Framework with Multimodal Data

Microservice-based systems often suffer from reliability issues due to their intricate interactions and expanding scale. With the rapid growth of observability techniques, various methods have been proposed to achieve failure diagnosis, including root cause localization and failure type identification, by leveraging diverse monitoring data such as logs, metrics, or traces. However, traditional failure diagnosis methods that use single-modal data can hardly cover all failure scenarios due to the restricted information. Several failure diagnosis methods have been recently proposed to integrate multimodal data based on deep learning. These methods, however, tend to combine modalities indiscriminately and treat them equally in failure diagnosis, ignoring the relationship between specific modalities and different diagnostic tasks. This oversight hinders the effective utilization of the unique advantages offered by each modality. To address the limitation, we propose \textit{TVDiag}, a multimodal failure diagnosis framework for locating culprit microservice instances and identifying their failure types (e.g., Net-packets Corruption) in microservice-based systems. \textit{TVDiag} employs task-oriented learning to enhance the potential advantages of each modality and establishes cross-modal associations based on contrastive learning to extract view-invariant failure information. Furthermore, we develop a graph-level data augmentation strategy that randomly inactivates the observability of some normal microservice instances during training to mitigate the shortage of training data. Experimental results show that \textit{TVDiag} outperforms state-of-the-art methods in multimodal failure diagnosis, achieving at least a 55.94\% higher $HR@1$ accuracy and over a 4.08\% increase in F1-score across two datasets.

cs.SE↗
arXiv2025

Stated $SL_n$-skein modules, roots of unity, and TQFT

For a pb surface $Σ$, two positive integers $m,n$ with $m\mid n$, and two invertible elements $v,ε$ in a commutative domain $R$ with $ε^{2m} = 1$, we construct an $R$-linear isomorphism between the stated $SL_n$-skein algebras $S_n(Σ,v)$ and $S_n(Σ,εv)$, which restricts to an algebraic ismorphism between subalgebras of $S_n(Σ,v)$ and $S_n(Σ,εv)$. Using this linear isomorphism, we prove the splitting map $Θ_{c}:S_n(Σ,v)\rightarrow S_n(\text{Cut}_c(Σ),v)$ for the pb surface $Σ$ and the ideal arc $c$ is injective when $v^{2m} = 1$ and $m\mid n$. We generalize Barrett's work to the $SL_n$-skein space and stated $SL_n$-skein space. As an application, we prove the splitting map for the marked 3-manifolds is always injective when the quantum parameter $v=-1$. Let $(M,\mathcal{N})$ be a connected marked 3-manifold with $\mathcal{N}\neq\emptyset$, and let $(M,\mathcal{N}')$ be obtained from $(M,\mathcal{N})$ by adding one extra marking. When $v^4 =1$, we prove the $R$-linear map from $S_n(M,\mathcal{N},v)$ to $S_n(M,\mathcal{N}',v)$ induced by the embedding $(M,\mathcal{N})\rightarrow (M,\mathcal{N}')$ is injective and $S_n(M.\mathcal{N}',v) = S_n(M,\mathcal{N},v)\otimes_{R}O_{q_v}(SL_n)$, where $O_{q_v}(SL_n)$ is the quantization of the regular function ring of $SL_n$. This shows the splitting map for $S_n(M,\mathcal{N},v)$ is always injective. We formulate the stated $SL_n$-TQFT theory, which generalizes the Costantino and Lê's stated $SL_2$-TQFT theory.

math.QA↗
arXiv2025

POINT: a web-based platform for pharmacological investigation enhanced by multi-omics networks and knowledge graphs

Network pharmacology (NP) explores pharmacological mechanisms through biological networks. Multi-omics data enable multi-layer network construction under diverse conditions, requiring integration into NP analyses. We developed POINT, a novel NP platform enhanced by multi-omics biological networks, advanced algorithms, and knowledge graphs (KGs) featuring network-based and KG-based analytical functions. In the network-based analysis, users can perform NP studies flexibly using 1,158 multi-omics biological networks encompassing proteins, transcription factors, and non-coding RNAs across diverse cell line-, tissue- and disease-specific conditions. Network-based analysis-including random walk with restart (RWR), GSEA, and diffusion profile (DP) similarity algorithms-supports tasks such as target prediction, functional enrichment, and drug screening. We merged networks from experimental sources to generate a pre-integrated multi-layer human network for evaluation. RWR demonstrated superior performance with a 33.1% average ranking improvement over the second-best algorithm, PageRank, in identifying known targets across 2,002 drugs. Additionally, multi-layer networks significantly improve the ability to identify FDA-approved drug-disease pairs compared to the single-layer network. For KG-based analysis, we compiled three high-quality KGs to construct POINT KG, which cross-references over 90% of network-based predictions. We illustrated the platform's capabilities through two case studies. POINT bridges the gap between multi-omics networks and drug discovery; it is freely accessible at http://point.gene.ac/.

q-bio.MN↗
arXiv2025

Universal Actions for Enhanced Embodied Foundation Models

Training on diverse, internet-scale data is a key factor in the success of recent large foundation models. Yet, using the same recipe for building embodied agents has faced noticeable difficulties. Despite the availability of many crowd-sourced embodied datasets, their action spaces often exhibit significant heterogeneity due to distinct physical embodiment and control interfaces for different robots, causing substantial challenges in developing embodied foundation models using cross-domain data. In this paper, we introduce UniAct, a new embodied foundation modeling framework operating in a Universal Action Space. Our learned universal actions capture the generic atomic behaviors across diverse robots by exploiting their shared structural features, and enable enhanced cross-domain data utilization and cross-embodiment generalizations by eliminating the notorious heterogeneity. The universal actions can be efficiently translated back to heterogeneous actionable commands by simply adding embodiment-specific details, from which fast adaptation to new robots becomes simple and straightforward. Our 0.5B instantiation of UniAct outperforms 14X larger SOTA embodied foundation models in extensive evaluations on various real-world and simulation robots, showcasing exceptional cross-embodiment control and adaptation capability, highlighting the crucial benefit of adopting universal actions. Project page: https://github.com/2toinf/UniAct

cs.RO↗
arXiv2024

The Unicity Theorem and the center of the ${\rm SL}_3$-skein algebra

The ${\rm SL}_3$-skein algebra $\mathscr{S}_{\bar{q}}(\mathfrak{S})$ of a punctured oriented surface $\mathfrak{S}$ is a quantum deformation of the coordinate algebra of the ${\rm SL}_3$-character variety of $\mathfrak{S}$. When $\bar{q}$ is a root of unity, we prove the Unicity Theorem for representations of $\mathscr{S}_{\bar{q}}(\mathfrak{S})$, in particular the existence and uniqueness of a generic irreducible representation. Furthermore, we show that the center of $\mathscr{S}_{\bar{q}}(\frak{S})$ is generated by the peripheral skeins around punctures and the central elements contained in the image of the Frobenius homomorphism for $\mathscr{S}_{\bar{q}}(\frak{S})$, a surface generalization of Frobenius homomorphisms of quantum groups related to ${\rm SL}_3$. We compute the rank of $\mathscr{S}_{\bar{q}}(\mathfrak{S})$ over its center, hence the dimension of the generic irreducible representation.

math.QA↗
arXiv2024

A Learning Rate Path Switching Training Paradigm for Version Updates of Large Language Models

Due to the continuous emergence of new data, version updates have become an indispensable requirement for Large Language Models (LLMs). The training paradigms for version updates of LLMs include pre-training from scratch (PTFS) and continual pre-training (CPT). Preliminary experiments demonstrate that PTFS achieves better pre-training performance, while CPT has lower training cost. Moreover, their performance and training cost gaps widen progressively with version updates. To investigate the underlying reasons for this phenomenon, we analyze the effect of learning rate adjustments during the two stages of CPT: preparing an initialization checkpoint and continual pre-training based on this checkpoint. We find that a large learning rate in the first stage and a complete learning rate decay process in the second stage are crucial for version updates of LLMs. Hence, we propose a learning rate path switching training paradigm. Our paradigm comprises one main path, where we pre-train a LLM with the maximal learning rate, and multiple branching paths, each of which corresponds to an update of the LLM with newly-added training data. Extensive experiments demonstrate the effectiveness and generalization of our paradigm. Particularly, when training four versions of LLMs, our paradigm reduces the total training cost to 58% compared to PTFS, while maintaining comparable pre-training performance.

cs.CL↗
arXiv2024

Robo-MUTUAL: Robotic Multimodal Task Specification via Unimodal Learning

Multimodal task specification is essential for enhanced robotic performance, where \textit{Cross-modality Alignment} enables the robot to holistically understand complex task instructions. Directly annotating multimodal instructions for model training proves impractical, due to the sparsity of paired multimodal data. In this study, we demonstrate that by leveraging unimodal instructions abundant in real data, we can effectively teach robots to learn multimodal task specifications. First, we endow the robot with strong \textit{Cross-modality Alignment} capabilities, by pretraining a robotic multimodal encoder using extensive out-of-domain data. Then, we employ two Collapse and Corrupt operations to further bridge the remaining modality gap in the learned multimodal representation. This approach projects different modalities of identical task goal as interchangeable representations, thus enabling accurate robotic operations within a well-aligned multimodal latent space. Evaluation across more than 130 tasks and 4000 evaluations on both simulated LIBERO benchmark and real robot platforms showcases the superior capabilities of our proposed framework, demonstrating significant advantage in overcoming data constraints in robotic learning. Website: zh1hao.wang/Robo_MUTUAL

cs.RO↗
arXiv2024

Kauffman bracket intertwiners and the volume conjecture

The volume conjecture relates the quantum invariant and the hyperbolic geometry. Bonahon-Wong-Yang introduced a new version of the volume conjecture by using the intertwiners between two isomorphic irreducible representations of the skein algebra. The intertwiners are built from surface diffeomorphisms; they formulated the volume conjecture when diffeomorphisms are pseudo-Anosov. In this paper, we explicitly calculate all the intertwiners for the closed torus using an algebraic embedding from the skein algebra of the closed torus to a quantum torus, and show the limit superior related to the trace of these intertwiners is zero. Moreover, we consider the periodic diffeomorphisms for surfaces with negative Euler characteristic, and conjecture the corresponding limit is zero because the simplicial volume of the mapping tori for periodic diffeomorphisms is zero. For the once punctured torus, we make precise calculations for intertwiners and prove our conjecture.

math.AT↗
arXiv2024

Representation-reduced stated skein modules and algebras

For any marked three manifold $(M,\mathcal N)$ and any quantum parameter $q^{\frac{1}{2}}$ (a nonzero complex number), we use $\mathscr{S}_{q^{1/2}}(M,\mathcal{N})$ to denote the stated skein module of $(M,\mathcal{N})$. When $q^{\frac{1}{2}}$ is a root of unity of odd order, the commutative algebra $\mathscr{S}_1(M,\mathcal{N})$ acts on $\mathscr{S}_{q^{1/2}}(M,\mathcal{N})$. For any maximal ideal $ρ$ of $\mathscr{S}_1(M,\mathcal{N})$, define $\mathscr{S}_{q^{1/2}}(M,\mathcal{N})_ρ = \mathscr{S}_{q^{1/2}}(M,\mathcal{N})\otimes _{\mathscr{S}_1(M,\mathcal{N})} (\mathscr{S}_1(M,\mathcal{N})/ρ)$. We prove the splitting map for $\mathscr{S}_{q^{1/2}}(M,\mathcal{N})$ respects the $\mathscr{S}_1(M,\mathcal{N})$-module structure, so it reduces to the splitting map for $\mathscr{S}_{q^{1/2}}(M,\mathcal{N})_ρ$. We prove the splitting map for $\mathscr{S}_{q^{1/2}}(M,\mathcal{N})_ρ$ is injective if there exists at least one component of $\mathcal{N}$ such that this component and the boundary of the splitting disk belong to the same component of $\partial M$. We also prove the representation-reduced stated skein module of the marked handlebody is an irreducible Azumaya representation of the stated skein algebra of its boundary. Let $M$ be an oriented connected closed three manifold. For any positive integer $k$, we use $M_{k}$ to denote the marked three manifold obtained from $M$ by removing $k$ open three dimensional balls and adding one marking to each newly created sphere boundary component. We prove $\text{dim}_{\mathbb{C}}\mathscr{S}_{q^{1/2}}( M_{k})_ρ = 1$ for any maximal ideal $ρ$ of $\mathscr{S}_1(M_k)$.

math.QA↗
arXiv2024

On the Information Redundancy in Non-Autoregressive Translation

Token repetition is a typical form of multi-modal problem in fully non-autoregressive translation (NAT). In this work, we revisit the multi-modal problem in recently proposed NAT models. Our study reveals that these advanced models have introduced other types of information redundancy errors, which cannot be measured by the conventional metric - the continuous repetition ratio. By manually annotating the NAT outputs, we identify two types of information redundancy errors that correspond well to lexical and reordering multi-modality problems. Since human annotation is time-consuming and labor-intensive, we propose automatic metrics to evaluate the two types of redundant errors. Our metrics allow future studies to evaluate new methods and gain a more comprehensive understanding of their effectiveness.

cs.CL↗
arXiv2024

When are Foundation Models Effective? Understanding the Suitability for Pixel-Level Classification Using Multispectral Imagery

Foundation models, i.e., very large deep learning models, have demonstrated impressive performances in various language and vision tasks that are otherwise difficult to reach using smaller-size models. The major success of GPT-type of language models is particularly exciting and raises expectations on the potential of foundation models in other domains including satellite remote sensing. In this context, great efforts have been made to build foundation models to test their capabilities in broader applications, and examples include Prithvi by NASA-IBM, Segment-Anything-Model, ViT, etc. This leads to an important question: Are foundation models always a suitable choice for different remote sensing tasks, and when or when not? This work aims to enhance the understanding of the status and suitability of foundation models for pixel-level classification using multispectral imagery at moderate resolution, through comparisons with traditional machine learning (ML) and regular-size deep learning models. Interestingly, the results reveal that in many scenarios traditional ML models still have similar or better performance compared to foundation models, especially for tasks where texture is less useful for classification. On the other hand, deep learning models did show more promising results for tasks where labels partially depend on texture (e.g., burn scar), while the difference in performance between foundation models and deep learning models is not obvious. The results conform with our analysis: The suitability of foundation models depend on the alignment between the self-supervised learning tasks and the real downstream tasks, and the typical masked autoencoder paradigm is not necessarily suitable for many remote sensing problems.

cs.CV↗
arXiv2024

Existence Is Chaos: Enhancing 3D Human Motion Prediction with Uncertainty Consideration

Human motion prediction is consisting in forecasting future body poses from historically observed sequences. It is a longstanding challenge due to motion's complex dynamics and uncertainty. Existing methods focus on building up complicated neural networks to model the motion dynamics. The predicted results are required to be strictly similar to the training samples with L2 loss in current training pipeline. However, little attention has been paid to the uncertainty property which is crucial to the prediction task. We argue that the recorded motion in training data could be an observation of possible future, rather than a predetermined result. In addition, existing works calculate the predicted error on each future frame equally during training, while recent work indicated that different frames could play different roles. In this work, a novel computationally efficient encoder-decoder model with uncertainty consideration is proposed, which could learn proper characteristics for future frames by a dynamic function. Experimental results on benchmark datasets demonstrate that our uncertainty consideration approach has obvious advantages both in quantity and quality. Moreover, the proposed method could produce motion sequences with much better quality that avoids the intractable shaking artefacts. We believe our work could provide a novel perspective to consider the uncertainty quality for the general motion prediction task and encourage the studies in this field. The code will be available in https://github.com/Motionpre/Adaptive-Salient-Loss-SAGGB.

cs.CV↗