arXiv subjects

Yuemeng Xu

Publications and source records attributed to Yuemeng Xu.

4 recordsLinked to original sources

arXiv2026

ArborMem: Navigating Interaction States with Memory Forests

Large language models increasingly serve as persistent conversational assistants, requiring memory that preserves relevant experience and maintains continuity across interactions. Existing methods improve access to conversational history through long-context processing, selective retrieval, and structured memory organization. However, most systems treat memory access as retrieving relevant past information without first determining which prior interaction state the current turn resumes. This limitation becomes particularly important when conversations interleave multiple tasks, people, and plans that may be interrupted and later revisited. We introduce ArborMem, an online memory framework that represents a long-running conversation as a navigable forest of interaction states. Each branch preserves a locally coherent trajectory, while the forest maintains multiple trajectories that may later be resumed. For each new input, ArborMem localizes the relevant state, restores its branch-local context, and augments it with reusable evidence retrieved across branches, preserving interaction continuity without conflating semantically related but structurally distinct trajectories. Existing long-term memory benchmarks cover diverse memory and reasoning capabilities but do not explicitly isolate branch-structured challenges. We therefore introduce BranchMemEval, a controlled diagnostic benchmark for interleaved and resumable interaction trajectories. Experiments on LongMemEval, LoCoMo, BEAM 100K, and BranchMemEval show that ArborMem outperforms the strongest baselines by 3.36 to 10.31 percentage points on the three established benchmarks and by 5.0 points on BranchMemEval. Its advantage grows under constrained read budgets, while complete memory queries remain below half a second.

cs.CL↗

arXiv2026

InSituANN: Revisiting IVF for PCIe-Efficient Billion-Scale Vector Search

Approximate nearest neighbor search (ANNS) over billion-scale vector datasets has become a foundational operator for modern retrieval systems, powering large-scale recommendation, semantic search, and LLM/RAG workloads. Although GPUs offer massive parallelism and high-bandwidth memory for batched vector search, their limited VRAM capacity makes fully GPU-resident billion-scale indexes difficult to deploy. In CPU-GPU heterogeneous designs, keeping the base vectors in host memory avoids this capacity limit, but naively offloading fine search to the GPU introduces a new bottleneck: large volumes of base-vector data must be streamed over PCIe. We present InSituANN, an IVF-based ANNS engine that enables billion-scale vector search on a single commodity GPU. InSituANN keeps original base vectors in host memory, performs fine search in situ, and uses the GPU for compact routing and optional pruning. As a result, query processing avoids PCIe transfers of high-dimensional base vectors while retaining the simplicity of IVF. Beyond query performance, we further design an ultra-fast IVF construction path for InSituANN. On SIFT-1B, InSituANN builds the IVF index in 5.2 minutes, about 350x faster than the measured 30.4-hour HNSW build. At matched recall on billion-scale datasets, InSituANN improves end-to-end throughput by 104.9x-4298.2x over the PCIe-bound Rummy baseline and by 2.4x-4.6x over DiskANN on SIFT-1B and DEEP-1B. Together with strong recall-throughput trade-offs and lower index space than graph-based alternatives, these gains make billion-scale retrieval practical on cost-efficient hardware. We open-source InSituANN at https://github.com/mindtravel/InSituANN-OpenSource.

cs.DB↗

arXiv2026

Rethinking Retrieval-Augmentation as Synthesis: A Query-Aware Context Merging Approach

Retrieval-Augmented Generation (RAG) enables Large Language Models (LLMs) to extend their existing knowledge by dynamically incorporating external information. However, practical deployment is fundamentally constrained by the LLM's finite context window, forcing a trade-off between information sufficiency and token consumption. Standard pipelines address this via a retrieve-then-select strategy, typically retaining only the top-k chunks based on relevance. Nevertheless, this approach is suboptimal: it inherently truncates critical bridging evidence located in the long tail of the relevance distribution, while simultaneously wasting the token budget on semantically redundant high-ranking chunks. In this paper, we rethink retrieval-augmentation as a dynamic optimization problem aimed at maximizing information density. We propose MergeRAG, a novel framework that shifts the paradigm from static filtering to query-aware synthesis. MergeRAG employs a scoring agent to restructure retrieved contexts through a dual-pathway mechanism: 1) Symmetric Merging, which consolidates weak signals to recover lost bridging evidence; 2) Asymmetric Merging, which utilizes entropy-guided anchoring to eliminate redundancy without sacrificing semantic integrity. We further introduce a Hierarchical Parallel Merging strategy that mitigates information loss while maximizing computational parallelism. Extensive experiments on standard benchmarks demonstrate that MergeRAG significantly outperforms state-of-the-art RAG baselines, achieving up to 13.7 points improvement in F1 score and 11.5 points in Exact Match (EM), respectively.

cs.IR↗

arXiv2025

Gryphon: Scaling Hyperscale Multi-Tenant Gateways Beyond the Petabit-Era via DPU-Augmented Hierarchical Co-Offloading

At ByteDance, cloud gateway clusters orchestrate petabit-scale aggregate traffic. Traditional ASIC-only gateways fail to meet these escalating demands due to severe on-chip resource constraints and limited programmable flexibility, while pure software solutions or alternatives like disaggregated SmartNICs struggle to match terabit-scale line-rate throughput. To bridge this gap, we present Gryphon, a hyperscale cloud gateway built on a hybrid architecture that integrates DPUs directly into the switching ASIC's forwarding path. This design resolves the fundamental tension between capacity and speed, expanding table scale by up to 1000$\times$ and augmenting programmability, while sustaining 1.6 Tbps line-rate throughput at a cost of only ~8$\mu s$ in additional average latency. To manage this hardware heterogeneity, we introduce Hierarchical Co-Offloading (HLCO) in the data plane, achieving >99.9% fast path hit rate, while retaining software fallback for complex operations. In the control plane, we develop an abstraction layer (P4Bridge) that decouples hardware specifics from policy configuration. Gryphon has been operating at production scale for over a year, deployed on hundreds of nodes across multiple Availability Zones. We also share production measurements and operational experiences that serve as the first hyperscale-proven guidelines for next-generation DPU-augmented cloud gateways.

cs.NI↗