arXiv subjects

Sanglu Lu

Publications and source records attributed to Sanglu Lu.

At least 19 recordsLinked to original sources

arXiv2026

SignLlama: Enhancing Gloss-free Sign Language Translation by Prioritizing Visual Features for LLMs

Large Language Models (LLMs) have achieved remarkable success across a wide range of tasks. However, fine-tuning LLMs for Gloss-Free Sign Language Translation (GFSLT) remains a challenge. In this paper, we investigate how to effectively adapt LLMs to the GFSLT task. We show that there are two key issues that need to be solved: (1) the inherent distributional gap between visual feature inputs and text feature inputs makes it difficult for LLMs to interpret visual inputs; and (2) existing approaches typically concatenate visual and textual features in an autoregressive framework, which leads to the model overemphasizing textual inputs and deprioritizing visual cues, as LLMs are pretrained predominantly on text-centric data. To address the first challenge, we propose a simple yet effective method named Filtered Pseudo-Gloss CTC Pretraining, which leverages filtered pseudo-gloss sequences generated from text sequences to supervise the training of the visual backbone. To tackle the second issue, we introduce a Visual-Prioritized Distillation training strategy. Specifically, we define a visual-only prediction path in which text inputs are masked, and the model is required to generate the target sequence relying solely on visual inputs. To guide this path, the outputs from the standard visual-textual prediction are then distilled into the visual-only prediction path, encouraging the model to prioritize visual features. Comprehensive experiments and qualitative analyses demonstrate the effectiveness of the proposed model. The proposed SignLlama achieves very competitive performance on multiple datasets for GFSLT tasks, without using any extra modalities or external sign language datasets for pretraining.

cs.CV↗

arXiv2026

Sign Language Question Answering: A New Task, Benchmark, and Baseline for Sign Language Understanding

Recent advances in sign language (SL) understanding (SLU) have led to remarkable progress in tasks such as continuous SL recognition and SL translation. However, these tasks are designed with predefined objectives, requiring models to learn a fixed mapping from sign videos to glosses or spoken-language sentences. As a result, they provide only a limited assessment of whether a model truly understands the semantic content of SL videos. To address this limitation, \textbf{we first propose a new task, Sign Language Question Answering (SLQA)}, which evaluates SL understanding by requiring models to answer arbitrary natural language questions about SL videos. Unlike previous SLU tasks, SLQA provides a more flexible and comprehensive evaluation framework that assesses multiple reasoning capabilities beyond recognition and translation. To facilitate this task, \textbf{we further construct two SignQA benchmarks} based on PHOENIX14T and CSL-Daily by automatically generating question-answer pairs from existing gloss and sentence annotations using carefully designed templates. The resulting datasets cover five complementary question categories, including position reasoning, structural reasoning, visual search, gloss recognition, and translation understanding. \textbf{Finally, we propose a simple yet effective baseline model} equipped with a Question-Conditioned Modulated Temporal Downsampling module and an in-domain knowledge transfer strategy, enabling effective knowledge transfer from existing SLU tasks while enhancing question-aware temporal feature modeling. Extensive experiments demonstrate that our baseline consistently outperforms representative vision-language models across all question categories, establishing a strong benchmark for future research on SLQA. Datasets are available at:{https://huggingface.co/datasets/hulala/SignQA-2026}.

cs.AI↗

arXiv2026

MemPoison: Uncovering Persistent Memory Threats and Structural Blind Spots in LLM Agents

Persistent external memory enhances agent continuity but introduces persistent security vulnerabilities: adversarial content can be injected via standard interaction channels, retained across turns, and later distort downstream behavior. To address this challenge, we propose MemPoison, a comprehensive benchmark and analysis framework featuring 1227 hand-validated cases across four attack types, three injection channels, and three representative memory substrates, evaluated on seven open-weight and three closed-weight model families. We introduce a three-tier taxonomy: (L1) direct single-record corruption, (L2) compositional multi-record corruption and (L3) context-triggered dormant corruption. Our evaluations reveal a distinct defense frontier: while baseline write-time defenses, such as consistency checks, substantially suppress direct L1 attacks, they fail to reliably suppress L2 and L3 attacks. Through mechanistic influence decomposition (MID), we demonstrate structural blind spots in write-time defenses, which admit seemingly benign records that later become harmful through joint retrieval composition or trigger-conditioned activation. Our findings advocate for shifting from static filtering to adaptive, context-sensitive memory defense strategies.

cs.CR↗

arXiv2026

InfoMerge: Information-aware Token Compression for Efficient Video Large Language Models

Video Large Language Models (Video-LLMs) achieve strong performance in video understanding, but their excessive visual tokens bring substantial computational overhead. Existing training-free compression methods improve inference efficiency by reducing visual tokens, yet they often rely on local adjacent-frame similarity for temporal redundancy estimation or allocate token budgets mainly according to segment length. Such designs are sensitive to frame-level noise and fail to capture the non-uniform information distribution of real-world videos. To address these challenges, we propose InfoMerge, a training-free visual token compression method that improves token utilization through robust redundancy estimation and content-aware budget allocation. Specifically, we propose the Temporal Fingerprint Difference: a segment-level second-order temporal redundancy estimation strategy, which models the temporal similarity structure of tokens at the same spatial positions within each segment. We further introduce Content-Aware Budget Allocation (CABA), which dynamically allocates segment-level token budgets based on segment uniqueness and spectral-entropy-based representational richness. By reducing repeated preservation of redundant static regions and allocating more tokens to informative segments, InfoMerge makes better use of the limited token budget while maintaining strong performance. Extensive experiments show that InfoMerge achieves strong efficiency--accuracy trade-offs across multiple benchmarks and backbones, with more pronounced advantages under aggressive compression. On LLaVA-OneVision-7B, InfoMerge retains 98.8\% of the original average performance while reducing 85\% of visual tokens and achieving a 4.24-fold speedup in the prefill stage.

cs.CV↗

arXiv2025

Temporal-Visual Semantic Alignment: A Unified Architecture for Transferring Spatial Priors from Vision Models to Zero-Shot Temporal Tasks

Large Multimodal Models (LMMs) have achieved remarkable progress in aligning and generating content across text and image modalities. However, the potential of using non-visual, continuous sequential, as a conditioning signal for high-fidelity image generation remains largely unexplored. Furthermore, existing methods that convert series into "pseudo-images" for temporal forecasting fail to establish semantic-level alignment. In this paper, we propose TimeArtist, a temporal-visual conversion framework that pioneers semantic-level alignment between time series fluctuations and visual concepts. It pioneers a "warmup-align" paradigm: first, a dual-autoencoder and shared quantizer are self-supervised trained on large-scale datasets to learn modality-shared representations. Then, the encoders and quantizer are frozen, and a projection is introduced to align temporal and visual samples at the representation level. TimeArtist establishes a versatile cross-modal framework, enabling high-quality, diverse image generation directly from time series, while capturing temporal fluctuation patterns to render images as styles transfer. Extensive experiments show that TimeArtist achieves satisfactory performance in image generation metrics, while also attaining superior results in zero-shot temporal tasks. Our work establishes a new paradigm for cross-modal generation, bridging the gap between temporal dynamics and visual semantics.

cs.CV↗

arXiv2025

Unifying Perception and Action: A Hybrid-Modality Pipeline with Implicit Visual Chain-of-Thought for Robotic Action Generation

Vision-Language-Action (VLA) models built upon Chain-of-Thought (CoT) have achieved remarkable success in advancing general-purpose robotic agents, owing to its significant perceptual comprehension. Recently, since text-only CoT struggles to adequately capture scene details in complex spatial environments, a highly promising strategy involves leveraging visual priors to guide robotic action generation. Nevertheless, these strategies face two inherent challenges: (i) a modality gap between visual observations and low-level actions, and (ii) unstable training due to competing objectives between visual prediction and action generation. To address these challenges, we propose a Vision-Integrated Trajectory Alignment (VITA) framework that learns a shared discrete latent space for vision and action, enabling joint modeling of perception and motor control. VITA introduces a implicit visual CoT: autoregressively generated tokens is simultaneously decoded into future frames predictions and robot actions, thereby internalizing visual dynamics as an inductive bias for motion planning. Extensive experiments on simulated and real-world environments demonstrate state-of-the-art performance. VITA improves 14.5\%, 9.6\% and 12.1\% over existing baselines on CALVIN, LIBERO and SimplerEnv. Furthermore, VITA attains an average success rate of 80.5\% across six real-world tasks, demonstrating its potential as a generalist robotic manipulation model.

cs.RO↗

arXiv2025

Energy-Aware Pattern Disentanglement: A Generalizable Pattern Assisted Architecture for Multi-task Time Series Analysis

Time series analysis has found widespread applications in areas such as weather forecasting, anomaly detection, and healthcare. While deep learning approaches have achieved significant success in this field, existing methods often adopt a "one-model one-task" architecture, limiting their generalization across different tasks. To address these limitations, we perform local energy analysis in the time-frequency domain to more precisely capture and disentangle transient and non-stationary oscillatory components. Furthermore, our representational analysis reveals that generative tasks tend to capture long-period patterns from low-frequency components, whereas discriminative tasks focus on high-frequency abrupt signals, which constitutes our core contribution. Concretely, we propose Pets, a novel "one-model many-tasks" architecture based on the General fluctuation Pattern Assisted (GPA) framework that is adaptable to versatile model structures for time series analysis. Pets integrates a Fluctuation Pattern Assisted (FPA) module and a Context-Guided Mixture of Predictors (MoP). The FPA module facilitates information fusion among diverse fluctuation patterns by capturing their dependencies and progressively modeling these patterns as latent representations at each layer. Meanwhile, the MoP module leverages these generalizable pattern representations to guide and regulate the reconstruction of distinct fluctuations hierarchically by energy proportion. Pets demonstrates strong versatility and achieves state-of-the-art performance across 60 benchmarks on various tasks, including forecasting, imputation, anomaly detection, and classification, while demonstrating strong generalization and robustness.

cs.AI↗

arXiv2025

Graph Network for Sign Language Tasks

Recent advances in sign language research have benefited from CNN-based backbones, which are primarily transferred from traditional computer vision tasks (\eg object identification, image recognition). However, these CNN-based backbones usually excel at extracting features like contours and texture, but may struggle with capturing sign-related features. In fact, sign language tasks require focusing on sign-related regions, including the collaboration between different regions (\eg left hand region and right hand region) and the effective content in a single region. To capture such region-related features, we introduce MixSignGraph, which represents sign sequences as a group of mixed graphs and designs the following three graph modules for feature extraction, \ie Local Sign Graph (LSG) module, Temporal Sign Graph (TSG) module and Hierarchical Sign Graph (HSG) module. Specifically, the LSG module learns the correlation of intra-frame cross-region features within one frame, \ie focusing on spatial features. The TSG module tracks the interaction of inter-frame cross-region features among adjacent frames, \ie focusing on temporal features. The HSG module aggregates the same-region features from different-granularity feature maps of a frame, \ie focusing on hierarchical features. In addition, to further improve the performance of sign language tasks without gloss annotations, we propose a simple yet counter-intuitive Text-driven CTC Pre-training (TCP) method, which generates pseudo gloss labels from text labels for model pre-training. Extensive experiments conducted on current five public sign language datasets demonstrate the superior performance of the proposed model. Notably, our model surpasses the SOTA models on multiple sign language tasks across several datasets, without relying on any additional cues.

cs.CV↗

arXiv2025

Unify and Anchor: A Context-Aware Transformer for Cross-Domain Time Series Forecasting

The rise of foundation models has revolutionized natural language processing and computer vision, yet their best practices to time series forecasting remains underexplored. Existing time series foundation models often adopt methodologies from these fields without addressing the unique characteristics of time series data. In this paper, we identify two key challenges in cross-domain time series forecasting: the complexity of temporal patterns and semantic misalignment. To tackle these issues, we propose the ``Unify and Anchor" transfer paradigm, which disentangles frequency components for a unified perspective and incorporates external context as domain anchors for guided adaptation. Based on this framework, we introduce ContexTST, a Transformer-based model that employs a time series coordinator for structured representation and the Transformer blocks with a context-informed mixture-of-experts mechanism for effective cross-domain generalization. Extensive experiments demonstrate that ContexTST advances state-of-the-art forecasting performance while achieving strong zero-shot transferability across diverse domains.

cs.LG↗

arXiv2024

Domain Fusion Controllable Generalization for Cross-Domain Time Series Forecasting from Multi-Domain Integrated Distribution

Conventional deep models have achieved unprecedented success in time series forecasting. However, facing the challenge of cross-domain generalization, existing studies utilize statistical prior as prompt engineering fails under the huge distribution shift among various domains. In this paper, a novel time series generalization diffusion model (TimeControl) that pioneers the Domain-Fusion paradigm, systematically integrating information from multiple time series domains into a unified generative process via diffusion models. Unlike the autoregressive models that capture the conditional probabilities of the prediction horizon to the historical sequence, we use the diffusion denoising process to model the mixed distribution of the cross-domain data and generate the prediction sequence for the target domain directly utilizing conditional sampling. The proposed TimeControl contains three pivotal designs: (1) The condition network captures the multi-scale fluctuation patterns from the observation sequence, which are utilized as context representations to guide the denoising network to generate the prediction sequence; (2) Adapter-based fine-tuning strategy, the multi-domain universal representation learned in the pretraining stage is utilized for downstream tasks in target domains; (3) A novel hybrid architecture is designed to align the observation and prediction spaces, enabling TimeControl to generate prediction sequences of arbitrary lengths with flexibility. We conduct extensive experiments on mainstream 49 benchmarks and 30 baselines, and the TimeControl outperforms existing baselines on all data domains, exhibiting superior zero-shot generalization ability.

cs.LG↗

arXiv2024

A Wave is Worth 100 Words: Investigating Cross-Domain Transferability in Time Series

Time series analysis is a fundamental data mining task that supervised training methods based on empirical risk minimization have proven their effectiveness on specific tasks and datasets. However, the acquisition of well-annotated data is costly and a large amount of unlabeled series data is under-utilized. Due to distributional shifts across various domains and different patterns of interest across multiple tasks. The problem of cross-domain multi-task migration of time series remains a significant challenge. To address these problems, this paper proposes a novel cross-domain pretraining method based on Wave Quantization (termed as WQ4TS), which can be combined with any advanced time series model and applied to multiple downstream tasks. Specifically, we transfer the time series data from different domains into a common spectral latent space, and enable the model to learn the temporal pattern knowledge of different domains directly from the common space and utilize it for the inference of downstream tasks, thereby mitigating the challenge of heterogeneous cross-domains migration. The establishment of spectral latent space brings at least three benefits, cross-domain migration capability thus adapting to zero- and few-shot scenarios without relying on priori knowledge of the dataset, general compatible cross-domain migration framework without changing the existing model structure, and robust modeling capability thus achieving SOTA results in multiple downstream tasks. To demonstrate the effectiveness of the proposed approach, we conduct extensive experiments including three important tasks: forecasting, imputation, and classification. And three common real-world data scenarios are simulated: full-data, few-shot, and zero-shot. The proposed WQ4TS achieves the best performance on 87.5% of all tasks, and the average improvement of the metrics on all the tasks is up to 34.7%.

cs.LG↗

arXiv2019

Construction of Subexponential-Size Optical Priority Queues with Switches and Fiber Delay Lines

All-optical switching has been considered as a natural choice to keep pace with growing fiber link capacity. One key research issue of all-optical switching is the design of optical buffers for packet contention resolution. One of the most general buffering schemes is optical priority queue, where every packet is associated with a unique priority upon its arrival and departs the queue in order of priority, and the packet with the lowest priority is always dropped when a new packet arrives but the buffer is full. In this paper, we focus on the feedback construction of an optical priority queue with a single $\boldsymbol{(M+2)\times (M+2)}$ optical crossbar Switch and $\boldsymbol{M}$ fiber Delay Lines (SDL) connecting $\boldsymbol{M}$ inputs and $\boldsymbol{M}$ outputs of the switch. We propose a novel construction of an optical priority queue with buffer $\boldsymbol{2^{Θ(\sqrt{M})}}$, which improves substantially over all previous constructions that only have buffers of $\boldsymbol{O(M^c)}$ size for constant integer $\boldsymbol{c}$. The key ideas behind our construction include (i) the use of first in first out multiplexers, which admit efficient SDL constructions, for feeding back packets to the switch instead of fiber delay lines, and (ii) the use of a routing policy that is similar to self-routing, where each packet entering the switch is routed to some multiplexer mainly determined by the current ranking of its priority.

cs.IT↗

arXiv2018

Efficient Resource Allocation for On-Demand Mobile-Edge Cloud Computing

Mobile-edge cloud computing is a new paradigm to provide cloud computing capabilities at the edge of pervasive radio access networks in close proximity to mobile users. Aiming at provisioning flexible on-demand mobile-edge cloud service, in this paper we propose a comprehensive framework consisting of a resource-efficient computation offloading mechanism for users and a joint communication and computation (JCC) resource allocation mechanism for network operator. Specifically, we first study the resource-efficient computation offloading problem for a user, in order to reduce user's resource occupation by determining its optimal communication and computation resource profile with minimum resource occupation and meanwhile satisfying the QoS constraint. We then tackle the critical problem of user admission control for JCC resource allocation, in order to properly select the set of users for resource demand satisfaction. We show the admission control problem is NP-hard, and hence develop an efficient approximation solution of a low complexity by carefully designing the user ranking criteria and rigourously derive its performance guarantee. To prevent the manipulation that some users may untruthfully report their valuations in acquiring mobile-edge cloud service, we further resort to the powerful tool of critical value approach to design truthful pricing scheme for JCC resource allocation. Extensive performance evaluation demonstrates that the proposed schemes can achieve superior performance for on-demand mobile-edge cloud computing.

cs.DC↗

arXiv2018

PingAn: An Insurance Scheme for Job Acceleration in Geo-distributed Big Data Analytics System

Geo-distributed data analysis in a cloud-edge system is emerging as a daily demand. Out of saving time in wide area data transfer, some tasks are dispersed to the edges. However, due to limited computing, overload interference and cluster-level unreachable troubles, efficient execution in the edges is hard, which obstructs the guarantee on the efficiency and reliability of jobs. Launching copies across clusters can be an insurance on a task's completion. Considering cluster heterogeneity and accompanying remote data fetch, cluster selection of copies affects execution quality, as different insuring plans drive different revenues. For providing On-Line-Real-Time analysis results, a system needs to insure the geo-distributed resource for the arriving jobs. Our challenge is to achieve the optimal revenue by dynamically weighing the gains due to insurance against the loss of occupying extra resource for insuring. To this end, we design PingAn, an online insurance algorithm promising $(1+\varepsilon)\!\!-\!speed \ o(\frac{1}{\varepsilon^2+\varepsilon})\!\!-\!competitive$ in sum of the job flowtimes via cross-cluster copying for tasks. PingAn shares resource among the anterior fraction of jobs with the least unprocessed datasize and the fraction is adjustable to fit the system load condition. After sharing, PingAn concretely insures for tasks following efficiency-first reliability-aware principle to optimize the revenue of copies on jobs' performance. Trace-driven simulations demonstrate that PingAn can reduce the average job flowtimes by at least $14\%$ than the state-of-the-art speculation mechanisms. We also build PingAn in Spark on Yarn System to verify its practicality and generality. Experiments show that PingAn can reduce the average job flowtimes by up to $40\%$ comparing to the default Spark execution.

cs.DC↗

arXiv2018

Towards Reliable (and Efficient) Job Executions in a Practical Geo-distributed Data Analytics System

Geo-distributed data analytics are increasingly common to derive useful information in large organisations. Naive extension of existing cluster-scale data analytics systems to the scale of geo-distributed data centers faces unique challenges including WAN bandwidth limits, regulatory constraints, changeable/unreliable runtime environment, and monetary costs. Our goal in this work is to develop a practical geo-distribued data analytics system that (1) employs an intelligent mechanism for jobs to efficiently utilize (adjust to) the resources (changeable environment) across data centers; (2) guarantees the reliability of jobs due to the possible failures; and (3) is generic and flexible enough to run a wide range of data analytics jobs without requiring any changes. To this end, we present a new, general geo-distributed data analytics system, HOUTU, that is composed of multiple autonomous systems, each operating in a sovereign data center. HOUTU maintains a job manager (JM) for a geo-distributed job in each data center, so that these replicated JMs could individually and cooperatively manage resources and assign tasks. Our experiments on the prototype of HOUTU running across four Alibaba Cloud regions show that HOUTU provides nearly efficient job performance as in the existing centralized architecture, and guarantees reliable job executions when facing failures.

cs.DC↗

arXiv2018

RDMAvisor: Toward Deploying Scalable and Simple RDMA as a Service in Datacenters

RDMA is increasingly adopted by cloud computing platforms to provide low CPU overhead, low latency, high throughput network services. On the other hand, however, it is still challenging for developers to realize fast deployment of RDMA-aware applications in the datacenter, since the performance is highly related to many lowlevel details of RDMA operations. To address this problem, we present a simple and scalable RDMA as Service (RaaS) to mitigate the impact of RDMA operational details. RaaS provides careful message buffer management to improve CPU/memory utilization and improve the scalability of RDMA operations. These optimized designs lead to simple and flexible programming model for common and knowledgeable users. We have implemented a prototype of RaaS, named RDMAvisor, and evaluated its performance on a cluster with a large number of connections. Our experiment results demonstrate that RDMAvisor achieves high throughput for thousand of connections and maintains low CPU and memory overhead through adaptive RDMA transport selection.

cs.DC↗

arXiv2016

Designing a Disaster-resilient Network with Software Defined Networking

With the wide deployment of network facilities and the increasing requirement of network reliability, the disruptive event like natural disaster, power outage or malicious attack has become a non-negligible threat to the current communication network. Such disruptive event can simultaneously destroy all devices in a specific geographical area and affect many network based applications for a long time. Hence, it is essential to build disaster-resilient network for future highly survivable communication services. In this paper, we consider the problem of designing a highly resilient network through the technique of SDN (Software Defined Networking). In contrast to the conventional idea of handling all the failures on the control plane (the controller), we focus on an integrated design to mitigate disaster risks by adding some redundant functions on the data plane. Our design consists of a sub-graph based proactive protection approach on the data plane and a splicing approach at the controller for effective restoration on the control plane. Such a systematic design is implemented in the OpenFlow framework through the Mininet emulator and Nox controller. Numerical results show that our approach can achieve high robustness with low control overhead.

cs.NI↗

arXiv2016

Constructing Sub-exponentially Large Optical Priority Queues with Switches and Fiber Delay Lines

Optical switching has been considered as a natural choice to keep pace with growing fiber link capacity. One key research issue of all-optical switching is the design of optical queues by using optical crossbar switches and fiber delay lines (SDL). In this paper, we focus on the construction of an optical priority queue with a single $(M+2)\times (M+2)$ crossbar switch and $M$ fiber delay lines, and evaluate it in terms of the buffer size of the priority queue. Currently, the best known upper bound of the buffer size is $O(2^M)$, while existing methods can only construct a priority queue with buffer $O(M^3)$. In this paper, we make a great step towards closing the above huge gap. We propose a very efficient construction of priority queues with buffer $2^{Θ(\sqrt{M})}$. We use 4-to-1 multiplexers with different buffer sizes, which can be constructed efficiently with SDL, as intermediate building blocks to simplify the design. The key idea in our construction is to route each packet entering the switch to some group of four 4-to-1 multiplexers according to its current priority, which is shown to be collision-free.

cs.IT↗