Searcharxiv⌕ Search

arXiv subjects

Ge Yu

Publications and source records attributed to Ge Yu.

At least 19 recordsLinked to original sources
arXiv2026

DepTGL: A Parallel Framework for Memory-based TGNN Training with Adaptive Temporal Data Dependency Management

Memory-based Temporal Graph Neural Networks (M-TGNNs) maintain recursively updated node states to capture fine-grained temporal interactions. However, existing distributed frameworks lack effective mechanisms for managing the temporal data dependencies inherent in these models. As a result, they must enforce strict chronological updates, incur substantial remote synchronization overhead, and experience severe load imbalance when temporal event streams are skewed. We propose DepTGL, a scalable distributed training framework that restructures temporal-dependency management for M-TGNNs from a data-centric perspective. First, DepTGL introduces a hybrid temporal-dependency management scheme that explicitly balances communication and caching overhead via temporal-event caching, supplemented by selective dependency-driven communication. Next, DepTGL incorporates a gradient-aware cache-synchronization policy that adaptively suppresses boundary updates as model optimization stabilizes, thereby reducing redundant synchronization. Finally, DepTGL integrates a load-aware temporal-pruning strategy that eliminates auxiliary replay events under skew-induced load spikes, reducing redundant data processing and mitigating straggler effects. Experiments on six real-world temporal graphs show that DepTGL achieves an average speedup of 4.99x over state-of-the-art baselines, while maintaining comparable accuracy.

cs.DC↗
arXiv2026

ConceptFormer: Learning Adaptive Latent Concepts for Query-Document Alignment in Visual Document Retrieval

Visual document retrieval is a critical component of multimodal retrieval-augmented generation, aiming to identify query-relevant pages from document collections where evidence is distributed across text, layout, charts, and visual structures. Recent efforts toward finer-grained supervision primarily rely on textual descriptions or localized visual regions as evidence proxies. However, such supervision signals may either overlook complex visual structures or provide incomplete and inaccurate representations of the underlying evidence. To address these limitations, we propose ConceptFormer, a latent concept representation learning framework for visual document retrieval. ConceptFormer models query-relevant evidence as continuous, query-conditioned latent concepts that explicitly bridge localized visual evidence and semantic relevance, without requiring either textual intermediate representations or direct reliance on raw visual annotations. During training, ConceptFormer employs a strong vision-language model to dynamically determine the number of latent concept tokens and uses these concepts as an intermediate representation to bridge the semantic gap between queries and documents, thereby guiding the learning of the embedding space. Experiments on diverse visual document retrieval benchmarks demonstrate that ConceptFormer achieves 16.7\% and 22.1\% relative improvements in average NDCG@10 over the strongest visual retrieval baseline and the strongest OCR-based text retrieval baseline, respectively. Further analysis reveals that latent concepts effectively connect localized visual evidence with semantic relevance, enabling the retriever to capture both fine-grained textual cues and complex document-level visual structures while preserving strong retrieval alignment. Codes and data are available at https://github.com/Neuir/ConceptFormer.

cs.CV↗
arXiv2026

MEGRAG: Multi-Granular Evidence Graphs for Answer-Aware Multi-Hop RAG

Multi-hop question answering is a fundamental challenge in retrieval-augmented generation (RAG), because deriving an answer requires integrating dispersed evidence. Iterative RAG (iRAG) is widely used for this challenge, but existing methods have two limitations. First, most methods still support each reasoning step with single-granularity evidence, making it difficult to balance information density and contextual noise. Second, existing methods often answer the original question only after aggregating evidence retrieved across intermediate steps, so redundant evidence and intermediate retrieval errors may accumulate and degrade the final answer. To address these limitations, we propose MEGRAG, an answer-aware framework that represents multi-hop reasoning as a path-structured multi-granular evidence graph. Offline, MEGRAG links passages to their sentences and extracted triples through a cross-granularity index. Online, it retrieves passages for the current query and selects aligned evidence, starting with compact triples and adding sentence or passage context as needed. MEGRAG uses the resulting intermediate answer and prior reasoning to decide whether the Initial Query has been resolved. If not, it identifies the missing information and formulates a focused next query; otherwise, it stops retrieval and returns the answer. Extensive experiments demonstrate consistent gains over a diverse set of RAG baselines.

cs.AI↗
arXiv2026

REFACT: Adaptive Fact Restatement for Compact and Faithful Chain-of-Thought Reasoning

Large Language Models (LLMs) increasingly leverage long-form reasoning to solve complex tasks, yet their reasoning processes can deviate from the provided context when evidence is incomplete, noisy, or conflicts with parametric knowledge. Existing grounding approaches either append citations after generation or encourage LLMs to retrieve evidence during reasoning, but they often fail to ensure that cited information is sufficient to support intermediate inferences and final answers. To address this limitation, we propose REFACT, an adaptive fact-restatement citation framework that enables LLMs to determine when contextual grounding is needed and selectively restate source facts at appropriate levels of detail for reliable reasoning. To facilitate adaptive citation during reasoning, REFACT first leverages a teacher LLM to construct high-quality citation-aware reasoning trajectories under diverse context conditions with varying evidence lengths, and then optimizes the student LLM through a two-stage SFT-to-RL framework. Experiments on LongBench, LV-Eval, and ConFiQA demonstrate that REFACT improves long-context question answering and counterfactual faithfulness while substantially reducing the number of reasoning tokens. Further analysis reveals that REFACT achieves higher evidence density by preserving more answer-relevant facts with fewer restatements, producing reasoning traces that are more concise yet better grounded. All code and data will be released via https://github.com/NEUIR/REFACT.

cs.CL↗
arXiv2026

An Efficient Fault-Tolerance Scheme for CKKS Computation on CPUs

Fully homomorphic encryption (FHE) enables computation on encrypted data, but its long ciphertext dataflow and high-dimensional modular arithmetic make it vulnerable to silent data corruption caused by transient hardware faults. Existing protection methods either target dedicated accelerators or impose substantial execution, modular-arithmetic, and memory-access overheads on CPUs. This work presents an efficient fault-tolerance scheme for CPU-based CKKS computation. It checks the input-output consistency of polynomial operators while reducing protection overhead at three levels. First, modulus-aware bucket checksum exploits wide CPU accumulators to reduce expensive modular reductions. Second, dataflow-fused in-operator checking embeds checksum accumulation into operator dataflows, avoiding separate scans of long ciphertext polynomials. Third, cross-operator check fusion eliminates redundant checksum computations between adjacent operators while preserving end-to-end checking invariants. We implement the scheme in OpenFHE and evaluate it on representative encrypted applications and ciphertext primitives under random single-bit transient faults. It achieves a 100 percent empirical detection rate across 150,000 non-crashing corrupted-result cases and maintains application accuracy close to the fault-free baseline over a wide range of fault rates. The scheme incurs only 6.0 percent to 8.4 percent runtime overhead, averaging 6.8 percent, and reduces average protection overhead by 4.9 times compared with direct checksum-based protection.

cs.AR↗
arXiv2026

SHIFT: Gate-Modulated Activation Steering for Knowledge Conflict Mitigation in Retrieval-Augmented Generation

Retrieval-augmented generation (RAG) enhances LLMs by incorporating external knowledge to support response generation. However, conflicts between retrieved context and parametric knowledge have emerged as a critical challenge in RAG systems. To mitigate such conflicts, numerous studies have attempted to identify and edit knowledge-related internal neurons, aiming to improve the ability of LLMs to rely on contextual evidence during generation. However, these neuron-level approaches may introduce unintended cascading effects that compromise the general capabilities of LLMs, as the modified neurons are often entangled with broader model behaviors and functionalities. In this paper, we introduce SHIFT, a novel framework that reformulates neuron-level modification as learnable gate modulation, allowing LLMs to adaptively regulate internal activations for knowledge conflict resolution. Technically, our SHIFT equips LLMs with a lightweight gate module and optimizes fewer than 0.01% trainable parameters while keeping the backbone model frozen. During generation, the gate module adjusts the model's internal representations to adaptively leverage contextual and parametric knowledge. Extensive experiments on six datasets validate the effectiveness of our SHIFT in comparison with various competing baselines. All datasets and code are available at https://github.com/OpenBMB/SHIFT.

cs.CL↗
arXiv2026

NeutronSparse: Coordinating Heterogeneous Engines for Sparse Matrix Multiplication on NPUs

Sparse matrix-matrix multiplication (SpMM) is a fundamental data operation for large-scale sparse data processing. With NPUs increasingly deployed in data centers for their performance and energy efficiency, accelerating SpMM on these platforms is a natural choice. However, high-performance SpMM on NPUs poses a data management challenge, as irregular sparsity demands efficient data organization and scheduling. On Ascend 910B, the official MindSpore implementation achieves only 36.3% of the performance of GPU-based sparse libraries such as cuSPARSE on NVIDIA A100. To this end, we conduct an in-depth architectural analysis of SpMM execution on NPUs versus GPU and identify that the key performance bottleneck for SpMM on NPUs lies in the lack of efficient coordination across heterogeneous compute units under tile-based execution model. Therefore, we propose NeutronSparse, a coordination-first SpMM framework for NPUs. NeutronSparse integrates two key techniques: (i) Sparsity-aware coordination of heterogeneous engines, which adaptively partitions and balances workloads between heterogeneous compute units to keep them busy, and (ii) Locality-aware tile orchestrating, which reorganizes and reuses data tiles to reduce redundant computation and memory movement overhead. Evaluations on Ascend 910B show that NeutronSparse achieves 1.26x-7.78x speedup over NPU baselines and 1.03x-3.07x speedup over leading GPU libraries on NVIDIA A100, revealing untapped potential of NPUs for sparse computation.

cs.AR↗
arXiv2026

MemoryCard: Topic-Aware Multi-Modal Clue Compression for Long-Video Question Answering

Long-video question answering remains challenging for Vision-Language Models (VLMs), as answer-relevant evidence is often sparse, transient, and temporally dispersed across lengthy video contexts. Existing frame-centric approaches improve efficiency through uniform sampling, query-aware frame selection, visual-token compression, and adaptive resolution strategies. However, they still rely on isolated and fragmented frames as the fundamental evidence units, limiting VLMs' ability to effectively capture coherent event-level semantics. To address this limitation, we propose MemoryCard, a video-memory-based augmentation framework that organizes long videos into self-contained Memory Cards. Specifically, MemoryCard first performs a self-reading process over videos and aligned utterances to segment the video into semantically coherent units, each corresponding to a distinct topic or event. For each unit, it generates an event-level video gist and selects representative visual moments, which are then rendered into unified Memory Cards for retrieval and question answering. Experimental results demonstrate that MemoryCard consistently improves long-video QA performance under comparable visual-token budgets, achieving up to a 21.8% relative improvement in accuracy. All code is available at https://github.com/NEUIR/MemoryCard.

cs.CV↗
arXiv2026

AcOrch: Accelerating Sampling-based GNN Training under CPU-NPU Heterogeneous Environments

Graph Neural Networks (GNNs) have achieved remarkable success in various applications. Sampling-based GNN training, which conducts mini-batch training on sampled subgraphs, has become a promising solution for large-scale graphs. Given the resource-intensive nature of sampling-based GNN training, Neural Processing Units (NPUs), such as the Ascend AI processor, offer a promising alternative due to their high throughput and energy efficiency, making them well-suited for GNN workloads. However, the multi-stage nature of sampling-based training, which involves subgraph sampling, feature gathering, and model training, with different resource requirements and computation volume. This requires careful coordination to fully utilize the heterogeneous computation resources of CPUs and NPUs. In this work, we present AcOrch, a sampling-based GNN training system optimized for CPU-NPU heterogeneous platforms. AcOrch offers fine-grained task orchestration and adopts a two-level pipelined execution model to overlap sampling, gathering, and training. It analyzes the heterogeneous compute features of NPUs and maps tasks to AI Cube (AIC) units, AI Vector (AIV) units, and CPU cores accordingly. Moreover, the two-level pipeline enables overlapping execution not only between the CPU and NPU, but also among different types of compute units within the NPU (e.g., AIC and AIV units), thereby maximizing the utilization of available resources. Experiments on an Ascend 910B AI processor show that AcOrch achieves an average speedup of 2.31x over the state-of-the-art NPU-native graph learning system, MindSporeGL.

cs.DC↗
arXiv2026

Memory Shot for Long-Term Dialogue

Large Language Models (LLMs) have demonstrated strong capabilities in general conversation, instruction following, and complex reasoning. However, in long-term dialogue settings, they often struggle to locate and utilize historical information most relevant to the current query. Existing approaches address this issue by constructing structured text-centered memory units through compressing and reorganizing user interaction history. However, these systems often rely on brute-force extraction of crucial evidence to associate episodes across dialogue sessions, causing substantial computational overhead and weakening structural cues such as speaker transitions, turn boundaries, and local contextual relationships. To avoid fragile text-based memory representations, we propose MemShot, which leverages dialogue structuring for long-term dialogue modeling and relies on the model's internal visual reasoning capabilities to associate key episodes. Specifically, MemShot renders local contiguous dialogue spans into structured visual memory units, preserving meta-information and chronological dialogue turns while avoiding heavy-weight textual memory construction. Experimental results show that MemShot achieves stable and competitive performance on both LoCoMo and LongMemEval, while substantially shortening the memory construction pipeline and delivering 70$\times$ speedup. Further analysis reveals that MemShot enhances the localization and utilization of historical evidence by directing memory processing toward structured local dialogue cues rather than surface-level lexical matching in a flat text stream. All codes are released on https://github.com/NEUIR/MemShot.

cs.IR↗
arXiv2026

HE^2: A Communication-Light Heterogeneous Architecture for Efficient Fully Homomorphic Encryption

CKKS, an emerging fully homomorphic encryption (FHE) scheme, has been promising in privacy-preserving applications by enabling SIMD fixed-point computations on ciphertexts. Despite its strong security guarantees, CKKS involves both compute-intensive operators (ComOps) with high computational cost and memory-intensive operators (MemOps) with large memory footprints, making existing ASIC-based or NMP-based acceleration approaches suffer from high hardware overhead and limited efficiency. This observation motivates the integration of the architectural advantages of both paradigms into a heterogeneous xPU (ASIC)-xMU (NMP) architecture. However, in such a design, frequent and long-latency heterogeneous communication caused by the dominant keyswitch operator remains a key performance bottleneck. In this paper, we propose $HE^2$, a communication-light xPU-xMU heterogeneous FHE accelerator with dataflow graph (DFG) optimization and architecture co-design. First, we observe that the majority of communication arises at the interface between ModUp/ModDown and neighboring MemOps. To address this, we propose a DFG-level optimization framework to fully exploit the ModUp/ModDown reduction potential of the hoisting algorithm by identifying parallel keyswitch blocks and fusing them for reduced communication frequency. Second, we design an efficient heterogeneous architecture that adopts a group-level pipelined execution to effectively hide communication latency by leveraging the inherent parallelism across decomposed groups. End-to-end evaluation results show that $HE^2$ achieves 1.66$\times$ speedup and 9.23$\times$ lower EDAP (Energy-Delay-Area Product) compared to the state-of-the-art accelerator, with communication stalls accounting for only 6.67% of the total latency.

cs.AR↗
arXiv2026

EvoRAG: Making Knowledge Graph-based RAG Automatically Evolve through Feedback-driven Backpropagation

Knowledge Graph-based Retrieval-Augmented Generation (KG-RAG) has emerged as a promising paradigm for enhancing LLM reasoning by retrieving multi-hop paths from KGs. However, existing KG-RAG frameworks often underperform in real-world scenarios because the pre-captured knowledge dependencies are not tailored to the downstream task or its evolving requirements. These frameworks struggle to adapt to task-specific requirements and lack mechanisms to filter low-contribution knowledge during generation. We observe that feedback on generated responses offers effective supervision for improving KG quality, as it directly reflects user expectations and provides insights into the correctness and usefulness of the output. However, a key challenge lies in effectively linking response-level feedback to triplet-level contribution evaluation and knowledge updates in the KG. In this work, we propose EvoRAG, a self-evolving KG-RAG framework that leverages the feedback over generated responses to continuously refine the KG and enhance reasoning accuracy. EvoRAG introduces a feedback-driven backpropagation mechanism that attributes feedback to retrieved paths by measuring their utility for response and propagates this utility back to individual triplets, supporting fine-grained KG refinements towards more adaptive and accurate reasoning. Through EvoRAG, we establish a closed loop that couples feedback, LLM, and graph data, continuously enhancing the performance and robustness in real-world scenarios. Experimental results show that EvoRAG improves reasoning accuracy by $7.34\%$ over state-of-the-art KG-RAG frameworks. The source code has been made available at https://github.com/iDC-NEU/EvoRAG.

cs.DB↗
arXiv2026

ReAlign: Optimizing the Visual Document Retriever with Reasoning-Guided Fine-Grained Alignment

Visual document retrieval aims to retrieve a set of document pages relevant to a query from visually rich collections. Existing methods often employ Vision-Language Models (VLMs) to encode queries and visual pages into a shared embedding space, which is then optimized via contrastive training. However, during visual document representation, localized evidence is usually scattered across complex document layouts, making it difficult for retrieval models to capture crucial cues for effective embedding learning. In this paper, we propose Reasoning-Guided Alignment (ReAlign), a method that enhances visual document retrieval by leveraging the reasoning capability of VLMs to provide fine-grained visual document descriptions as supervision signals for training. Specifically, ReAlign employs a superior VLM to identify query-related regions on a page and then generates a query-aware description grounding the cropped visual regions. The retriever is then trained using these region-focused descriptions to align the semantics between queries and visual documents by encouraging the document ranking distribution induced by the region-focused descriptions to match that induced by the original query. Experiments on diverse visually rich document retrieval benchmarks demonstrate that ReAlign consistently improves visual document retrieval performance on both in-domain and out-of-domain datasets, achieving up to 2% relative improvements. Moreover, the advantages of ReAlign generalize across different VLM backbones by guiding models to better focus their attention on critical visual cues for document representation. All code and datasets are available at https://github.com/NEUIR/ReAlign.

cs.IR↗
arXiv2026

On the Vulnerability of FHE Computation to Silent Data Corruption

Fully Homomorphic Encryption (FHE) is rapidly emerging as a promising foundation for privacy-preserving cloud services, enabling computation directly on encrypted data. As FHE implementations mature and begin moving toward practical deployment in domains such as secure finance, biomedical analytics, and privacy-preserving AI, a critical question remains insufficiently explored: how reliable is FHE computation on real hardware? This question is especially important because, compared with plaintext computation, FHE incurs much higher computational overhead, making it more susceptible to transient hardware faults. Moreover, data corruptions are likely to remain silent: the FHE service has no access to the underlying plaintext, causing unawareness even though the corresponding decrypted result has already been corrupted. To this end, we conduct a comprehensive evaluation of SDCs in FHE ciphertext computation. Through large-scale fault-injection experiments, we characterize the vulnerability of FHE to transient faults, and through a theoretical analysis of error-propagation behaviors, we gain deeper algorithmic insight into the mechanisms underlying this vulnerability. We further assess the effectiveness of different fault-tolerance mechanisms for mitigating these faults.

cs.CR↗
arXiv2026

DIAL-KG: Schema-Free Incremental Knowledge Graph Construction via Dynamic Schema Induction and Evolution-Intent Assessment

Knowledge Graphs (KGs) are foundational to applications such as search, question answering, and recommendation. Conventional knowledge graph construction methods are predominantly static, rely ing on a single-step construction from a fixed corpus with a prede f ined schema. However, such methods are suboptimal for real-world sce narios where data arrives dynamically, as incorporating new informa tion requires complete and computationally expensive graph reconstruc tions. Furthermore, predefined schemas hinder the flexibility of knowl edge graph construction. To address these limitations, we introduce DIAL KG, a closed-loop framework for incremental KG construction orches trated by a Meta-Knowledge Base (MKB). The framework oper ates in a three-stage cycle: (i) Dual-Track Extraction, which ensures knowledge completeness by defaulting to triple generation and switching to event extraction for complex knowledge; (ii) Governance Adjudica tion, which ensures the fidelity and currency of extracted facts to prevent hallucinations and knowledge staleness; and (iii) Schema Evolution, in which new schemas are induced from validated knowledge to guide subsequent construction cycles, and knowledge from the current round is incrementally applied to the existing KG. Extensive experiments demon strate that our framework achieves state-of-the-art (SOTA) performance in the quality of both the constructed graph and the induced schemas.

cs.AI↗
arXiv2026

ATCC: Adaptive Concurrency Control for Unforeseen Agentic Transactions

Data agents, empowered by Large Language Models (LLMs), introduce a new paradigm in transaction processing. Unlike traditional applications with fixed patterns, data agents run online-generated workflows that repeatedly issue SQL statements, reason over intermediate results, and revise subsequent plans. To ensure data consistency, these SQL statements issued by an agent should be integrated into a transaction, referred to as agentic transactions. Agentic transactions exhibit unforeseen characteristics, including long execution times, irregular execution intervals, and non-deterministic access patterns, breaking the assumptions underlying concurrency control (CC) (e.g., short-lived, predefined). Traditional CC schemes, which rely on fixed policies, fail to capture such dynamic behavior, resulting in inadequate performance. This paper introduces ATCC, an adaptive Concurrency Control for Agentic Transactions. ATCC continuously monitors and interprets the runtime behavior of each agentic transaction, evaluates its interactive phases, and dynamically adapts optimistic or pessimistic execution for each transaction. To ensure precise timing for adaptive switches, ATCC employs a reinforcement learning-based policy to balance immediate blocking against future abort costs. Additionally, to mitigate contention-induced tail latency and wasted reasoning cost caused by abort, a cost-aware priority-based lock scheduling is integrated to prioritize expensive or latency-sensitive transactions. Experimental results under agentic-like YCSB and TPC-C workloads demonstrate that ATCC improves the throughput of agentic transactions by up to four orders of magnitude and reduces tail latency by up to 90% compared to state-of-the-art CC schemes.

cs.DB↗
arXiv2026

Concurrency Control as a Service

Existing disaggregated databases separate execution and storage layers, enabling independent and elastic scaling of resources. In most cases, this design makes transaction concurrency control (CC) a critical bottleneck, which demands significant computing resources for concurrent conflict management and struggles to scale due to the coordination overhead for concurrent conflict resolution. Coupling CC with execution or storage limits performance and elasticity, as CC's resource needs do not align with the free scaling of the transaction execution layer or the storage-bound data layer. This paper proposes Concurrency Control as a Service (CCaaS), which decouples CC from databases, building an execution-CC-storage three-layer decoupled database, allowing independent scaling and upgrades for improved elasticity, resource utilization, and development agility. However, adding a new layer increases latency due to the shift in communication from hardware to network. To address this, we propose a Sharded Multi-Write OCC (SM-OCC) algorithm with an asynchronous log push-down mechanism to minimize network communications overhead and transaction latency. Additionally, we implement a multi-write architecture with a deterministic conflict resolution method to reduce coordination overhead in the CC layer, thereby improving scalability. CCaaS is designed to be connected by a variety of execution and storage engines. Existing disaggregated databases can be revolutionized with CCaaS to achieve high elasticity, scalability, and high performance. Results show that CCaaS achieves 1.02-3.11X higher throughput and 1.11-2.75X lower latency than SoTA disaggregated databases.

cs.DB↗
arXiv2026

Tau-BNO: Brain Neural Operator for Tau Transport Model

Mechanistic modeling provides a biophysically grounded framework for studying the spread of pathological tau protein in tauopathies like Alzheimer's disease. Existing approaches typically model tau propagation as a diffusive process on the brain's structural connectome, reproducing macroscopic patterns but neglecting microscale cellular transport and reaction mechanisms. The Network Transport Model (NTM) was introduced to fill this gap, explaining how region-level progression of tau emerges from microscale biophysical processes. However, the NTM faces a common challenge for complex models defined by large systems of partial differential equations: the inability to perform parameter inference and mechanistic discovery due to high computational burden and slow model simulations. To overcome this barrier, we propose Tau-BNO, a Brain Neural Operator surrogate framework for rapidly approximating NTM dynamics that captures both intra-regional reaction kinetics and inter-regional network transport. Tau-BNO combines a function operator that encodes kinetic parameters with a query operator that preserves initial state information, while approximating anisotropic transport through a spectral kernel that retains directionality. Empirical evaluations demonstrate high predictive accuracy ($R^2\approx$ 0.98) across diverse biophysical regimes and an 89\% performance improvement over state-of-the-art sequence models like Transformers and Mamba, which lack inherent structural priors. By reducing simulation time from hours to seconds, we show that the surrogate model is capable of producing new insights and generating new hypotheses. This framework is readily extensible to a broader class of connectome-based biophysical models, showcasing the transformative value of deep learning surrogates to accelerate analysis of large-scale, computationally intensive dynamical systems.

cs.CE↗