arXiv subjects

Yan Huang

Publications and source records attributed to Yan Huang.

At least 109 records · Page 6Linked to original sources

arXiv2025

An Optimistic Gradient Tracking Method for Distributed Minimax Optimization

This paper studies the distributed minimax optimization problem over networks. To enhance convergence performance, we propose a distributed optimistic gradient tracking method, termed DOGT, which solves a surrogate function that captures the similarity between local objective functions to approximate a centralized optimistic approach locally. Leveraging a Lyapunov-based analysis, we prove that DOGT achieves linear convergence to the optimal solution for strongly convex-strongly concave objective functions while remaining robust to the heterogeneity among them. Moreover, by integrating an accelerated consensus protocol, the accelerated DOGT (ADOGT) algorithm achieves an optimal convergence rate of $\mathcal{O} \left( κ\log \left( ε^{-1} \right) \right)$ and communication complexity of $\mathcal{O} \left( κ\log \left( ε^{-1} \right) /\sqrt{1-\sqrt{ρ_W}} \right)$ for a suboptimality level of $ε>0$, where $κ$ is the condition number of the objective function and $ρ_W$ is the spectrum gap of the network. Numerical experiments illustrate the effectiveness of the proposed algorithms.

math.OC↗

arXiv2025

CoCoL: A Communication Efficient Decentralized Collaborative Method for Multi-Robot Systems

Collaborative learning enhances the performance and adaptability of multi-robot systems in complex tasks but faces significant challenges due to high communication overhead and data heterogeneity inherent in multi-robot tasks. To this end, we propose CoCoL, a Communication efficient decentralized Collaborative Learning method tailored for multi-robot systems with heterogeneous local datasets. Leveraging a mirror descent framework, CoCoL achieves remarkable communication efficiency with approximate Newton-type updates by capturing the similarity between objective functions of robots, and reduces computational costs through inexact sub-problem solutions. Furthermore, the integration of a gradient tracking scheme ensures its robustness against data heterogeneity. Experimental results on three representative multi robot collaborative learning tasks show the superiority of the proposed CoCoL in significantly reducing both the number of communication rounds and total bandwidth consumption while maintaining state-of-the-art accuracy. These benefits are particularly evident in challenging scenarios involving non-IID (non-independent and identically distributed) data distribution, streaming data, and time-varying network topologies.

cs.RO↗

arXiv2025

Interleaved Transceiver Design for a Continuous- Transmission MIMO-OFDM ISAC System

This paper proposes an interleaved transceiver design method for a multiple-input multiple-output (MIMO) integrated sensing and communication (ISAC) system utilizing orthogonal frequency division multiplexing (OFDM) waveforms. We consider a continuous transmission system and focus on the design of the transmission signal and a receiving filter in the time domain for an interleaved transmission architecture. For communication performance, constructive interference (CI) is integrated into the optimization problem. For radar sensing performance, the integrated mainlobe-to-sidelobe ratio (IMSR) of the beampattern is considered to ensure desirable directivity. Additionally, we tackle the challenges of inter-block interference and eliminate the spurious peaks, which are crucial for accurate target detection. Regarding the hardware implementation aspect, the power of each time sample is constrained to manage the peak-to-average power ratio (PAPR). The design problem is addressed using an alternating optimization (AO) framework, with the subproblem for transmitted waveform design being solved via the successive convex approximation (SCA) method. To further enhance computational efficiency, the alternate direction penalty method (ADPM) is employed to solve the subproblems within the SCA iterations. The convergence of ADPM is established, with convergence of the case of more than two auxiliary variables being established for the first time. Numerical simulations validate the effectiveness of our transceiver design in achieving desirable performance in both radar sensing and communication, with the fast algorithm achieving comparable performance with greater computational efficiency.

eess.SP↗

arXiv2025

IKOD: Mitigating Visual Attention Degradation in Large Vision-Language Models

Recent advancements in Large Vision-Language Models (LVLMs) have demonstrated significant progress across multiple domains. However, these models still face the inherent challenge of integrating vision and language for collaborative inference, which often leads to "hallucinations", outputs that are not grounded in the corresponding images. Many efforts have been made to address these issues, but each comes with its own limitations, such as high computational cost or expensive dataset annotation. Recent research shows that LVLMs exhibit a long-term bias where hallucinations increase as the sequence length grows, yet the underlying cause remains poorly understood. Building on extensive research into attention mechanisms in LVLMs, we analyze the relationship between this long-term bias and visual attention. In our research, we identify a consistent phenomenon in current LVLMs: the model's attention to visual input diminishes as the generated sequence grows, which we hypothesize to be a key factor contributing to observed increasing hallucinations. Based on these insights, we propose Image attention-guided Key-value merging cOllaborative Decoding (IKOD), a collaborative decoding strategy generating more image-focused sequences. This method derives logits from shorter sequences with higher image attention through key-value merging and combines them with those from the original decoding, effectively mitigating attention degradation and suppressing hallucinations while not incurring too much inference cost. Extensive experiments on both hallucination and comprehensive benchmarks demonstrate IKOD's superior effectiveness in mitigating hallucinations and improving comprehensive capacities for LVLMs. Importantly, IKOD requires no additional training or external tools, making it a lightweight and efficient framework applicable to various models.

cs.CV↗

arXiv2025

Approximation properties of the intermediate $β$-expansions

Given $β>1$ and $α\in[0,1)$, let $T_{β, α}(x)=βx+α\pmod 1$. Then under the map $T_{β,α}$ each $x\in[0,1]$ has an \emph{intermediate $β$-expansion} of the form $x=\sum_{i=1}^\infty\frac{c_i-α}{β^i}$ {with each $c_i\in\{0,1,\ldots,\lf β+α\rf\}$}. In this paper we study the approximation properties of $T_{β,α}$ by considering the expected value $M_β(α)$ of the \emph{normalized errors} $(θ_{β,α}^n(x))_{n\geq 1}$, where $$θ_{β,α}^n(x):=β^n\left(x-\sum_{i=1}^n\frac{c_i-α}{β^i}\right),\quad n\in\mathbb{N}.$$ We prove that $M_β(\cdot)$ is continuous on $[0,1)$. As a result, $\mathcal{M_β}:=\{M_β(α):α\in[0,1)\}$ is a closed interval. In particular, if $β$ is a multinacci number, the map $T_{β,α}$ has matching for Lebesgue almost every $α\in[0,1)$, and then $M_β(\cdot)$ is locally linear almost everywhere on $[0,1)$.

math.DS↗

arXiv2025

Recovering Partially Corrupted Objects via Sketch-Guided Bidirectional Feature Interaction

Text-guided diffusion models have achieved remarkable success in object inpainting by providing high-level semantic guidance through text prompts. However, they often lack precise pixel-level spatial control, especially in scenarios involving partially corrupted objects where critical uncorrupted cues remain. To overcome this limitation, sketch-guided methods have been introduced, using either indirect gradient modulation or direct sketch injection to improve structural control. Yet, existing approaches typically establish a one-way mapping from the sketch to the masked regions only, neglecting the contextual information from unmasked object areas. This leads to a disconnection between the sketch and the uncorrupted content, thereby causing sketch-guided inconsistency and structural mismatch. To tackle this challenge, we propose a sketch-guided bidirectional feature interaction framework built upon a pretrained Stable Diffusion model. Our bidirectional interaction features two complementary directions, context-to-sketch and sketch-to-inpainting, that enable fine-grained spatial control for partially corrupted object inpainting. In the context-to-sketch direction, multi-scale latents from uncorrupted object regions are propagated to the sketch branch to generate a visual mask that adapts the sketch features to the visible context and denoising progress. In the sketch-to-inpainting direction, a sketch-conditional affine transformation modulates the influence of sketch guidance based on the learned visual mask, ensuring consistency with uncorrupted object content. This interaction is applied at multiple scales within the encoder of the diffusion U-Net, enabling the model to restore object structures with enhanced spatial fidelity. Extensive experiments on two newly constructed benchmark datasets demonstrate that our approach outperforms state-of-the-art methods.

cs.CV↗

arXiv2025

Choosing Coordinate Forms for Solving ECDLP Using Shor's Algorithm

Shor's algorithm is well-known for its capability to address the elliptic curve discrete logarithm problem (ECDLP) in polynomial time. The enhancement of its quantum resources continues to be a crucial focus of research. Nevertheless, the application of projective coordinates for quantum resource optimization remains an unresolved issue, mainly because the representation of projective coordinates lacks uniqueness without employing modular division operations. Our study reveals that projective coordinates do not provide the same advantages as affine coordinates when utilizing Shor's method to tackle the ECDLP.

cs.CR↗

arXiv2025

MExplore: an entity-based visual analytics approach for medical expertise acquisition

Acquiring medical expertise is a critical component of medical education and professional development. While existing studies focus primarily on constructing medical knowledge bases or developing learning tools based on the structured, private healthcare data, they often lack methods for extracting expertise from unstructured medical texts. These texts constitute a significant portion of medical literature and offer greater flexibility and detail compared to structured data formats. Furthermore, many studies fail to provide explicit analytical and learning pathways in this context. This paper introduces MExplore, an interactive visual analytics system designed to support the acquisition of medical expertise. To address the challenges of the inconsistencies and confidentiality concerns inherent in unstructured medical texts, we propose a workflow that employs a fine-tuned BERT-based model to extract medical entities (MEs) from them. We then present a novel multilevel visual analysis framework that integrates multiple coordinated visualizations, enabling a progressive and interactive exploration of medical knowledge. To assess the effectiveness of MExplore, we conducted three case studies, a user study, and interviews with domain experts. The results indicate that the system significantly enhances the medical expertise acquisition process, providing an effective interactive approach for acquiring and retaining knowledge from medical texts.

cs.HC↗

arXiv2025

The Giant Radio Array for Neutrino Detection (GRAND) Collaboration -- Contributions to the 39th International Cosmic Ray Conference (ICRC 2025)

The Giant Radio Array for Neutrino Detection (GRAND) is an envisioned observatory of ultra-high-energy particles of cosmic origin, with energies in excess of 100 PeV. GRAND uses large surface arrays of antennas to look for the radio emission from extensive air showers that are triggered by the interaction of ultra-high-energy cosmic rays, gamma rays, and neutrinos in the atmosphere or underground. In particular, for ultra-high-energy neutrinos, the future final phase of GRAND aims to be sensitive enough to detect them in spite of their plausibly tiny flux. Three prototype GRAND radio arrays have been in operation since 2023: GRANDProto300, in China, GRAND@Auger, in Argentina, and GRAND@Nançay, in France. Their goals are to field-test the GRAND detection units, understand the radio background to which they are exposed, and develop tools for diagnostic, data gathering, and data analysis. This list of contributions to the 39th International Cosmic Ray Conference (ICRC 2025) presents an overview of GRAND, in its present and future incarnations, and a first look at data collected by GRANDProto300 and GRAND@Auger, including the first cosmic-ray candidates detected by them.

astro-ph.IM↗

arXiv2025

EC-Flow: Enabling Versatile Robotic Manipulation from Action-Unlabeled Videos via Embodiment-Centric Flow

Current language-guided robotic manipulation systems often require low-level action-labeled datasets for imitation learning. While object-centric flow prediction methods mitigate this issue, they remain limited to scenarios involving rigid objects with clear displacement and minimal occlusion. In this work, we present Embodiment-Centric Flow (EC-Flow), a framework that directly learns manipulation from action-unlabeled videos by predicting embodiment-centric flow. Our key insight is that incorporating the embodiment's inherent kinematics significantly enhances generalization to versatile manipulation scenarios, including deformable object handling, occlusions, and non-object-displacement tasks. To connect the EC-Flow with language instructions and object interactions, we further introduce a goal-alignment module by jointly optimizing movement consistency and goal-image prediction. Moreover, translating EC-Flow to executable robot actions only requires a standard robot URDF (Unified Robot Description Format) file to specify kinematic constraints across joints, which makes it easy to use in practice. We validate EC-Flow on both simulation (Meta-World) and real-world tasks, demonstrating its state-of-the-art performance in occluded object handling (62% improvement), deformable object manipulation (45% improvement), and non-object-displacement tasks (80% improvement) than prior state-of-the-art object-centric flow methods. For more information, see our project website at https://ec-flow1.github.io .

cs.RO↗

arXiv2025

PRVQL: Progressive Knowledge-guided Refinement for Robust Egocentric Visual Query Localization

Egocentric visual query localization (EgoVQL) focuses on localizing the target of interest in space and time from first-person videos, given a visual query. Despite recent progressive, existing methods often struggle to handle severe object appearance changes and cluttering background in the video due to lacking sufficient target cues, leading to degradation. Addressing this, we introduce PRVQL, a novel Progressive knowledge-guided Refinement framework for EgoVQL. The core is to continuously exploit target-relevant knowledge directly from videos and utilize it as guidance to refine both query and video features for improving target localization. Our PRVQL contains multiple processing stages. The target knowledge from one stage, comprising appearance and spatial knowledge extracted via two specially designed knowledge learning modules, are utilized as guidance to refine the query and videos features for the next stage, which are used to generate more accurate knowledge for further feature refinement. With such a progressive process, target knowledge in PRVQL can be gradually improved, which, in turn, leads to better refined query and video features for localization in the final stage. Compared to previous methods, our PRVQL, besides the given object cues, enjoys additional crucial target information from a video as guidance to refine features, and hence enhances EgoVQL in complicated scenes. In our experiments on challenging Ego4D, PRVQL achieves state-of-the-art result and largely surpasses other methods, showing its efficacy. Our code, model and results will be released at https://github.com/fb-reps/PRVQL.

cs.CV↗

arXiv2025

DAM: Dynamic Attention Mask for Long-Context Large Language Model Inference Acceleration

Long-context understanding is crucial for many NLP applications, yet transformers struggle with efficiency due to the quadratic complexity of self-attention. Sparse attention methods alleviate this cost but often impose static, predefined masks, failing to capture heterogeneous attention patterns. This results in suboptimal token interactions, limiting adaptability and retrieval accuracy in long-sequence tasks. This work introduces a dynamic sparse attention mechanism that assigns adaptive masks at the attention-map level, preserving heterogeneous patterns across layers and heads. Unlike existing approaches, our method eliminates the need for fine-tuning and predefined mask structures while maintaining computational efficiency. By learning context-aware attention structures, it achieves high alignment with full-attention models, ensuring minimal performance degradation while reducing memory and compute overhead. This approach provides a scalable alternative to full attention, enabling the practical deployment of large-scale Large Language Models (LLMs) without sacrificing retrieval performance. DAM is available at: https://github.com/HanzhiZhang-Ulrica/DAM.

cs.CL↗

arXiv2025

Classification of the real Painlevé I transcendents by zeros and connection problem: an asymptotic study

In this paper, we study the asymptotic behavior and connection problem of Painlevé I (PI) equation through a detailed analysis of the Stokes multipliers associated with its solutions. Focusing on the regime where the derivative at the real zeros of the solution becomes large, we apply the complex WKB method to derive full asymptotic expansions of the Stokes multipliers. These expansions allow us to classify real solutions of PI according to their behavior at the zeros, distinguishing between oscillatory, separatrix, and singular types solutions on the negative real axis. Furthermore, we resolve the connection problem between the large negative asymptotics and the location of positive zeros by establishing full asymptotic expansions of the zero parameters. Our approach enables the construction of a precise phase diagram in the $(r,b)$-plane, where $r$ is the location of a zero and $b$ is the derivative at that point. Numerical simulations are provided to validate the theoretical results. This work extends prior studies on monodromy asymptotics and contributes a comprehensive framework for understanding the global structure of real PI solutions through their local zero data.

math.CA↗

arXiv2025

Cyrus+: A DRL-based Puncturing Solution to URLLC/eMBB Multiplexing in O-RAN

Puncturing is a promising technique in 3GPP to multiplex Enhanced Mobile Broadband (eMBB) and Ultra-Reliable Low Latency Communications (URLLC) traffic on the same 5G New Radio (NR) air interface. The essence of puncturing is to transmit URLLC packets on demand upon their arrival, by preempting the radio resources (or subcarriers) that are already allocated to eMBB traffic. Although it is considered most bandwidth efficient, puncturing URLLC data on eMBB can lead to degradation of eMBB's performance. Most of the state-of-the-art research addressing this problem employ raw eMBB data throughput as performance metric. This is inadequate as, after puncturing, eMBB data may or may not be successfully decoded at its receiver. This paper presents Cyrus+, a deep reinforcement learning (DRL)-based puncturing solution that employs goodput (through feedback from a receiver's decoder), rather than estimated raw throughput, in its design of reward function. Further, Cyrus+ is tailored specifically for the Open RAN (O-RAN) architecture and fully leverages O-RAN's three control loops at different time scales in its design of DRL. In the Non-Real-Time (Non-RT) RAN Intelligent Controller (RIC), Cyrus+ initializes the policy network that will be used in the RT Open Distributed Unit (O-DU). In the Near-RT RIC, Cyrus+ refines the policy based on dynamic network conditions and feedback from the receivers. In the RT O-DU, Cyrus+ generates a puncturing codebook by considering all possible URLLC arrivals. We build a standard-compliant link-level 5G NR simulator to demonstrate the efficacy of Cyrus+. Experimental results show that Cyrus+ outperforms benchmark puncturing algorithms and meets the stringent timing requirement in 5G NR (numerology 3).

cs.NI↗

arXiv2025

Enhancing Marker Scoring Accuracy through Ordinal Confidence Modelling in Educational Assessments

A key ethical challenge in Automated Essay Scoring (AES) is ensuring that scores are only released when they meet high reliability standards. Confidence modelling addresses this by assigning a reliability estimate measure, in the form of a confidence score, to each automated score. In this study, we frame confidence estimation as a classification task: predicting whether an AES-generated score correctly places a candidate in the appropriate CEFR level. While this is a binary decision, we leverage the inherent granularity of the scoring domain in two ways. First, we reformulate the task as an n-ary classification problem using score binning. Second, we introduce a set of novel Kernel Weighted Ordinal Categorical Cross Entropy (KWOCCE) loss functions that incorporate the ordinal structure of CEFR labels. Our best-performing model achieves an F1 score of 0.97, and enables the system to release 47% of scores with 100% CEFR agreement and 99% with at least 95% CEFR agreement -compared to approximately 92% (approx.) CEFR agreement from the standalone AES model where we release all AM predicted scores.

cs.CL↗

arXiv2025

Dyn-D$^2$P: Dynamic Differentially Private Decentralized Learning with Provable Utility Guarantee

Most existing decentralized learning methods with differential privacy (DP) guarantee rely on constant gradient clipping bounds and fixed-level DP Gaussian noises for each node throughout the training process, leading to a significant accuracy degradation compared to non-private counterparts. In this paper, we propose a new Dynamic Differentially Private Decentralized learning approach (termed Dyn-D$^2$P) tailored for general time-varying directed networks. Leveraging the Gaussian DP (GDP) framework for privacy accounting, Dyn-D$^2$P dynamically adjusts gradient clipping bounds and noise levels based on gradient convergence. This proposed dynamic noise strategy enables us to enhance model accuracy while preserving the total privacy budget. Extensive experiments on benchmark datasets demonstrate the superiority of Dyn-D$^2$P over its counterparts employing fixed-level noises, especially under strong privacy guarantees. Furthermore, we provide a provable utility bound for Dyn-D$^2$P that establishes an explicit dependency on network-related parameters, with a scaling factor of $1/\sqrt{n}$ in terms of the number of nodes $n$ up to a bias error term induced by gradient clipping. To our knowledge, this is the first model utility analysis for differentially private decentralized non-convex optimization with dynamic gradient clipping bounds and noise levels.

cs.LG↗

arXiv2025

Orthogonal Factor-Based Biclustering Algorithm (BCBOF) for High-Dimensional Data and Its Application in Stock Trend Prediction

Biclustering is an effective technique in data mining and pattern recognition. Biclustering algorithms based on traditional clustering face two fundamental limitations when processing high-dimensional data: (1) The distance concentration phenomenon in high-dimensional spaces leads to data sparsity, rendering similarity measures ineffective; (2) Mainstream linear dimensionality reduction methods disrupt critical local structural patterns. To apply biclustering to high-dimensional datasets, we propose an orthogonal factor-based biclustering algorithm (BCBOF). First, we constructed orthogonal factors in the vector space of the high-dimensional dataset. Then, we performed clustering using the coordinates of the original data in the orthogonal subspace as clustering targets. Finally, we obtained biclustering results of the original dataset. Since dimensionality reduction was applied before clustering, the proposed algorithm effectively mitigated the data sparsity problem caused by high dimensionality. Additionally, we applied this biclustering algorithm to stock technical indicator combinations and stock price trend prediction. Biclustering results were transformed into fuzzy rules, and we incorporated profit-preserving and stop-loss rules into the rule set, ultimately forming a fuzzy inference system for stock price trend predictions and trading signals. To evaluate the performance of BCBOF, we compared it with existing biclustering methods using multiple evaluation metrics. The results showed that our algorithm outperformed other biclustering techniques. To validate the effectiveness of the fuzzy inference system, we conducted virtual trading experiments using historical data from 10 A-share stocks. The experimental results showed that the generated trading strategies yielded higher returns for investors.

cs.LG↗

arXiv2025

Constraint-Aware Zero-Shot Vision-Language Navigation in Continuous Environments

We address the task of Vision-Language Navigation in Continuous Environments (VLN-CE) under the zero-shot setting. Zero-shot VLN-CE is particularly challenging due to the absence of expert demonstrations for training and minimal environment structural prior to guide navigation. To confront these challenges, we propose a Constraint-Aware Navigator (CA-Nav), which reframes zero-shot VLN-CE as a sequential, constraint-aware sub-instruction completion process. CA-Nav continuously translates sub-instructions into navigation plans using two core modules: the Constraint-Aware Sub-instruction Manager (CSM) and the Constraint-Aware Value Mapper (CVM). CSM defines the completion criteria for decomposed sub-instructions as constraints and tracks navigation progress by switching sub-instructions in a constraint-aware manner. CVM, guided by CSM's constraints, generates a value map on the fly and refines it using superpixel clustering to improve navigation stability. CA-Nav achieves the state-of-the-art performance on two VLN-CE benchmarks, surpassing the previous best method by 12 percent and 13 percent in Success Rate on the validation unseen splits of R2R-CE and RxR-CE, respectively. Moreover, CA-Nav demonstrates its effectiveness in real-world robot deployments across various indoor scenes and instructions.

cs.RO↗