Searcharxiv⌕ Search

arXiv subjects

Li Guo

Publications and source records attributed to Li Guo.

At least 37 records · Page 2Linked to original sources

Rethinking LLM Watermark Detection in Black-Box Settings: A Non-Intrusive Third-Party Framework

While watermarking serves as a critical mechanism for LLM provenance, existing secret-key schemes tightly couple detection with injection, requiring access to keys or provider-side scheme-specific detectors for verification. This dependency creates a fundamental barrier for real-world governance, as independent auditing becomes impossible without compromising model security or relying on the opaque claims of service providers. To resolve this dilemma, we introduce TTP-Detect, a pioneering black-box framework designed for non-intrusive, third-party watermark verification. By decoupling detection from injection, TTP-Detect reframes verification as a relative hypothesis testing problem. It employs a proxy model to amplify watermark-relevant signals and a suite of complementary relative measurements to assess the alignment of the query text with watermarked distributions. Extensive experiments across representative watermarking schemes, datasets and models demonstrate that TTP-Detect achieves superior detection performance and robustness against diverse attacks.

cs.CR↗

HyperMem: Hypergraph Memory for Long-Term Conversations

Long-term memory is essential for conversational agents to maintain coherence, track persistent tasks, and provide personalized interactions across extended dialogues. However, existing approaches as Retrieval-Augmented Generation (RAG) and graph-based memory mostly rely on pairwise relations, which can hardly capture high-order associations, i.e., joint dependencies among multiple elements, causing fragmented retrieval. To this end, we propose HyperMem, a hypergraph-based hierarchical memory architecture that explicitly models such associations using hyperedges. Particularly, HyperMem structures memory into three levels: topics, episodes, and facts, and groups related episodes and their facts via hyperedges, unifying scattered content into coherent units. Leveraging this structure, we design a hybrid lexical-semantic index and a coarse-to-fine retrieval strategy, supporting accurate and efficient retrieval of high-order associations. Experiments on the LoCoMo benchmark show that HyperMem achieves state-of-the-art performance with 92.73% LLM-as-a-judge accuracy, demonstrating the effectiveness of HyperMem for long-term conversations.

cs.CL↗

Wanderland: Geometrically Grounded Simulation for Open-World Embodied AI

Reproducible closed-loop evaluation remains a major bottleneck in Embodied AI such as visual navigation. A promising path forward is high-fidelity simulation that combines photorealistic sensor rendering with geometrically grounded interaction in complex, open-world urban environments. Although recent video-3DGS methods ease open-world scene capturing, they are still unsuitable for benchmarking due to large visual and geometric sim-to-real gaps. To address these challenges, we introduce Wanderland, a real-to-sim framework that features multi-sensor capture, reliable reconstruction, accurate geometry, and robust view synthesis. Using this pipeline, we curate a diverse dataset of indoor-outdoor urban scenes and systematically demonstrate how image-only pipelines scale poorly, how geometry quality impacts novel view synthesis, and how all of these adversely affect navigation policy learning and evaluation reliability. Beyond serving as a trusted testbed for embodied navigation, Wanderland's rich raw sensor data further allows benchmarking of 3D reconstruction and novel view synthesis models. Our work establishes a new foundation for reproducible research in open-world embodied AI. Project website is at https://ai4ce.github.io/wanderland/.

cs.CV↗

Exons-Detect: Identifying and Amplifying Exonic Tokens via Hidden-State Discrepancy for Robust AI-Generated Text Detection

The rapid advancement of large language models has increasingly blurred the boundary between human-written and AI-generated text, raising societal risks such as misinformation dissemination, authorship ambiguity, and threats to intellectual property rights. These concerns highlight the urgent need for effective and reliable detection methods. While existing training-free approaches often achieve strong performance by aggregating token-level signals into a global score, they typically assume uniform token contributions, making them less robust under short sequences or localized token modifications. To address these limitations, we propose Exons-Detect, a training-free method for AI-generated text detection based on an exon-aware token reweighting perspective. Exons-Detect identifies and amplifies informative exonic tokens by measuring hidden-state discrepancy under a dual-model setting, and computes an interpretable translation score from the resulting importance-weighted token sequence. Empirical evaluations demonstrate that Exons-Detect achieves state-of-the-art detection performance and exhibits strong robustness to adversarial attacks and varying input lengths. In particular, it attains a 2.2\% relative improvement in average AUROC over the strongest prior baseline on DetectRL.

cs.CL↗

General multi-Novikov algebras, multi-differential algebras and their free constructions

Motivated by the recent development of noncommutative Novikov algebras and multi-Novikov algebras from the study of regularity structures of stochastic PDEs, this paper gives a general approach to study various multi-Novikov algebras and multi-differential algebras, with close connection with Poisson algebras. The construction of S. Gelfand of Novikov algebras from differential commutative algebras is generalized to this context. Free noncommuting multi-Novikov algebras are constructed from typed decorated rooted trees and from noncommuting multi-differential polynomials with populated conditions.

math.RA↗

Isomorphism between Hopf algebras for multiple zeta values

The classical quasi-shuffle algebra for multiple zeta values have a well-known Hopf algebra structure. Recently, the shuffle algebra for multiple zeta values are also equipped with a Hopf algebra structure. This paper shows that these two Hopf algebras are isomorphic utilizing quasi-symmetric functions. This Hopf algebra isomorphism is compared with with the well-known isomorphism between the shuffle Hopf algebra and quasi-shuffle Hopf algebra of Hoffman, Newman and Radford.

math.NT↗

Para-differential Rota-Baxter algebras and their free objects by Gröbner-Shirshov bases

The algebraic formulation of the derivation and integration related by the First Fundamental Theorem of Calculus (FFTC) gives rise to the notion of differential Rota-Baxter algebra. The notion has a remarkable list of categorical properties, in terms of the existence of (co)extensions of differential and Rota-Baxter operators, of the lifting of monads and comonads, and of mixed distributive laws. Conversely, using these properties as axioms leads to a class of algebraic structures called para-differential Rota-Baxter algebras. This paper carries out a systematic study of para-differential Rota-Baxter algebras. After their basic properties and examples from Hurwitz series and difference algebras, a Gröbner-Shirshov bases theory is established for para-differential Rota-Baxter algebras. Then an explicit construction of free para-differential Rota-Baxter algebras is obtained.

math.RA↗

SE-EE Tradeoff in Pinching-Antenna Systems: Waveguide Multiplexing or Waveguide Switching?

The spectral and energy efficiency (SE-EE) trade-off in pinching-antenna systems (PASS) is investigated in this paper. In particular, two practical operating protocols, namely waveguide multiplexing (WM) and waveguide switching (WS), are considered. A multi-objective optimization problem (MOOP) is formulated to jointly optimize the baseband and pinching beamforming for maximizing the achievable SE and EE, which is then converted into a single-objective problem via the ε-constraint method. For WM, the problem is decomposed within the alternating-optimization framework, where the baseband beamforming is optimized using the successive convex approximation, and the pinching beamforming is updated through the particle swarm optimization. For WS, due to the time-division transmission and interference-free nature, the pinching beamforming in each time slot is first adjusted to maximize the served user channel gain, followed by the baseband power allocation. Simulation results demonstrate that 1) PASS outperforms conventional antennas by mitigating large-scale path losses; 2) WS leads to a higher maximum achievable EE by activating a single RF chain, whereas WM yields a higher SE upper bound by serving all users concurrently; and 3) increasing the number of users substantially enhances SE under WM, whereas WS shows more pronounced benefits in low-signal-to-noise ratio regimes.

eess.SP↗

Rota-Baxter operators on braces, post-braces and the Yang-Baxter equation

Combining the notions of braces and relative Rota-Baxter operators on groups in connection with the Yang-Baxter equation and a factorization theorem of Lie groups from integrable systems, relative Rota-Baxter operators on braces and post-braces are introduced. A relative Rota-Baxter operator on a brace naturally induces a post-brace, and conversely, every post-brace determines a relative Rota-Baxter operator on its sub-adjacent brace. Furthermore, a post-brace yields two Drinfel'd-isomorphic solutions to the Yang-Baxter equation. As a special case, {\it enhanced} relative Rota-Baxter operators give rise to matched pairs of braces. Focusing on enhanced Rota-Baxter operators on two-sided braces, a corresponding factorization theorem is established. Examples are provided from the two-sided brace associated with the three-dimensional Heisenberg Lie algebra.

math-ph↗

Adjoint motives of modular forms and the Tamagawa number conjecture

Let $f$ be a newform of weight $k\geq 2$, level $N$ with coefficients in a number field $K$, and $A$ the adjoint motive of the motive $M$ associated to $f$. We carefully discuss the construction of the realisations of $M$ and $A$, as well as natural integral structures in these realisations. We then use the method of Taylor and Wiles to verify the $λ$-part of the Tamagawa number conjecture of Bloch and Kato for $L(A,0)$ and $L(A,1)$. Here $λ$ is any prime of $K$ not dividing $Nk!$, and so that the mod $λ$ representation associated to $f$ is absolutely irreducible when restricted to the Galois group over $\mathbb{Q}(\sqrt{(-1)^{(\ell-1)/2}\ell})$ where $λ\mid \ell$. The method also establishes modularity of all lifts of the mod $λ$ representation which are crystalline of Hodge-Tate type $(0,k-1)$.

math.NT↗

Generalized Connes-Kreimer Hopf algebras on decorated rooted forests by weighted cocycles

The Connes-Kreimer Hopf algebra of rooted trees is an operated Hopf algebra whose coproduct satisfies the classical Hochschild 1-cocycle condition. In this paper, we extend the setting from rooted trees to the space $H_{\rm RT}(X,Ω)$ of $(X,Ω)$-rooted trees, in which internal vertices are decorated by a set $Ω$ and leafs are decorated by $X \cup Ω$. We introduce a new coalgebra structure on $H_{\rm RT}(X,Ω)$ whose coproduct satisfies a weighted Hochschild 1-cocycle condition involving multiple operators, thereby generalizing the classical condition. A combinatorial interpretation of this coproduct is also provided. We then endow $H_{\rm RT}(X,Ω)$ with a Hopf algebra structure. Finally, we define weighted $Ω$-cocycle Hopf algebras, characterized by a Hochschild 1-cocycle condition with weights, and show that $H_{\rm RT}(X,Ω)$ is the free object in the category of $Ω$-cocycle Hopf algebras.

math.QA↗

LLM-based Agents Suffer from Hallucinations: A Survey of Taxonomy, Methods, and Directions

Driven by the rapid advancements of Large Language Models (LLMs), LLM-based agents have emerged as powerful intelligent systems capable of human-like cognition, reasoning, and interaction. These agents are increasingly being deployed across diverse real-world applications, including student education, scientific research, and financial analysis. However, despite their remarkable potential, LLM-based agents remain vulnerable to hallucination issues, which can result in erroneous task execution and undermine the reliability of the overall system design. Addressing this critical challenge requires a deep understanding and a systematic consolidation of recent advances on LLM-based agents. To this end, we present the first comprehensive survey of hallucinations in LLM-based agents. By carefully analyzing the complete workflow of agents, we propose a new taxonomy that identifies different types of agent hallucinations occurring at different stages. Furthermore, we conduct an in-depth examination of eighteen triggering causes underlying the emergence of agent hallucinations. Through a detailed review of a large number of existing studies, we summarize approaches for hallucination mitigation and detection, and highlight promising directions for future research. We hope this survey will inspire further efforts toward addressing hallucinations in LLM-based agents, ultimately contributing to the development of more robust and reliable agent systems.

cs.AI↗

A Riemann-type duality of shuffle Hopf algebras related to multiple zeta values

This paper offers a Hopf algebraic interpretation of a functional equation of multiple zeta functions, motivated by the classical symmetry of the Riemann zeta function. Starting from the extended shuffle algebra that encodes multiple zeta values (MZVs) at integer arguments, we show that its subalgebra corresponding to nonpositive arguments carries a natural differential Hopf algebra structure. This Hopf algebra is in graded linear duality with the shuffle Hopf algebra associated to MZVs at positive arguments. The resulting duality, realized through an explicit isomorphism, provides an algebraic analog of the functional equation relating $ζ(s)$ with $ζ(1-s)$ of the Riemann zeta function and unifies the positive and nonpositive sectors of multiple zeta functions within a common Hopf algebraic framework.

math.RA↗

Complementary Information Guided Occupancy Prediction via Multi-Level Representation Fusion

Camera-based occupancy prediction is a mainstream approach for 3D perception in autonomous driving, aiming to infer complete 3D scene geometry and semantics from 2D images. Almost existing methods focus on improving performance through structural modifications, such as lightweight backbones and complex cascaded frameworks, with good yet limited performance. Few studies explore from the perspective of representation fusion, leaving the rich diversity of features in 2D images underutilized. Motivated by this, we propose \textbf{CIGOcc, a two-stage occupancy prediction framework based on multi-level representation fusion. \textbf{CIGOcc extracts segmentation, graphics, and depth features from an input image and introduces a deformable multi-level fusion mechanism to fuse these three multi-level features. Additionally, CIGOcc incorporates knowledge distilled from SAM to further enhance prediction accuracy. Without increasing training costs, CIGOcc achieves state-of-the-art performance on the SemanticKITTI benchmark. The code is provided in the supplementary material and will be released https://github.com/VitaLemonTea1/CIGOcc

cs.CV↗

Multimodal Fusion and Vision-Language Models: A Survey for Robot Vision

Robot vision has greatly benefited from advancements in multimodal fusion techniques and vision-language models (VLMs). We adopt a task-oriented perspective to systematically review the applications and advancements of multimodal fusion methods and VLMs in the field of robot vision. For semantic scene understanding tasks, we categorize fusion approaches into encoder-decoder frameworks, attention-based architectures, and graph neural networks. Meanwhile, we also analyze the architectural characteristics and practical implementations of these fusion strategies in key tasks such as simultaneous localization and mapping (SLAM), 3D object detection, navigation, and manipulation. We compare the evolutionary paths and applicability of VLMs based on large language models (LLMs) with traditional multimodal fusion methods.Additionally, we conduct an in-depth analysis of commonly used datasets, evaluating their applicability and challenges in real-world robotic scenarios. Building on this analysis, we identify key challenges in current research, including cross-modal alignment, efficient fusion, real-time deployment, and domain adaptation. We propose future directions such as self-supervised learning for robust multimodal representations, structured spatial memory and environment modeling to enhance spatial intelligence, and the integration of adversarial robustness and human feedback mechanisms to enable ethically aligned system deployment. Through a comprehensive review, comparative analysis, and forward-looking discussion, we provide a valuable reference for advancing multimodal perception and interaction in robotic vision. A comprehensive list of studies in this survey is available at https://github.com/Xiaofeng-Han-Res/MF-RV.

cs.RO↗

CurriFlow: Curriculum-Guided Depth Fusion with Optical Flow-Based Temporal Alignment for 3D Semantic Scene Completion

Semantic Scene Completion (SSC) aims to infer complete 3D geometry and semantics from monocular images, serving as a crucial capability for camera-based perception in autonomous driving. However, existing SSC methods relying on temporal stacking or depth projection often lack explicit motion reasoning and struggle with occlusions and noisy depth supervision. We propose CurriFlow, a novel semantic occupancy prediction framework that integrates optical flow-based temporal alignment with curriculum-guided depth fusion. CurriFlow employs a multi-level fusion strategy to align segmentation, visual, and depth features across frames using pre-trained optical flow, thereby improving temporal consistency and dynamic object understanding. To enhance geometric robustness, a curriculum learning mechanism progressively transitions from sparse yet accurate LiDAR depth to dense but noisy stereo depth during training, ensuring stable optimization and seamless adaptation to real-world deployment. Furthermore, semantic priors from the Segment Anything Model (SAM) provide category-agnostic supervision, strengthening voxel-level semantic learning and spatial consistency. Experiments on the SemanticKITTI benchmark demonstrate that CurriFlow achieves state-of-the-art performance with a mean IoU of 16.9, validating the effectiveness of our motion-guided and curriculum-aware design for camera-based 3D semantic scene completion.

cs.CV↗

Neural Multivariate Regression: Qualitative Insights from the Unconstrained Feature Model

The Unconstrained Feature Model (UFM) is a mathematical framework that enables closed-form approximations for minimal training loss and related performance measures in deep neural networks (DNNs). This paper leverages the UFM to provide qualitative insights into neural multivariate regression, a critical task in imitation learning, robotics, and reinforcement learning. Specifically, we address two key questions: (1) How do multi-task models compare to multiple single-task models in terms of training performance? (2) Can whitening and normalizing regression targets improve training performance? The UFM theory predicts that multi-task models achieve strictly smaller training MSE than multiple single-task models when the same or stronger regularization is applied to the latter, and our empirical results confirm these findings. Regarding whitening and normalizing regression targets, the UFM theory predicts that they reduce training MSE when the average variance across the target dimensions is less than one, and our empirical results once again confirm these findings. These findings highlight the UFM as a powerful framework for deriving actionable insights into DNN design and data pre-processing strategies.

cs.LG↗

Image Recognition with Online Lightweight Vision Transformer: A Survey

The Transformer architecture has achieved significant success in natural language processing, motivating its adaptation to computer vision tasks. Unlike convolutional neural networks, vision transformers inherently capture long-range dependencies and enable parallel processing, yet lack inductive biases and efficiency benefits, facing significant computational and memory challenges that limit its real-world applicability. This paper surveys various online strategies for generating lightweight vision transformers for image recognition, focusing on three key areas: Efficient Component Design, Dynamic Network, and Knowledge Distillation. We evaluate the relevant exploration for each topic on the ImageNet-1K benchmark, analyzing trade-offs among precision, parameters, throughput, and more to highlight their respective advantages, disadvantages, and flexibility. Finally, we propose future research directions and potential challenges in the lightweighting of vision transformers with the aim of inspiring further exploration and providing practical guidance for the community. Project Page: https://github.com/ajxklo/Lightweight-VIT

cs.CV↗