Searcharxiv⌕ Search

arXiv subjects

Guihai Chen

Publications and source records attributed to Guihai Chen.

At least 19 recordsLinked to original sources

EngineAgent: Agentizing On-Device LLM Inference Engines with Inference Stack Hierarchy Awareness and Hardware Abilities

Rapidly evolving LLM architectures and heterogeneous mobile hardware make supporting new models in on-device inference engines a recurring and costly system challenge. Each model may require coordinated changes across conversion, graph construction, operators, and hardware backends. Existing coding agents often miss these cross-layer dependencies and struggle to diagnose failures across host--device execution paths. We present EngineAgent, an agentic system for automating on-device LLM model enablement. Its key insight is to separate reusable engine and hardware knowledge from model-specific implementation. Before enablement, EngineAgent constructs a hierarchy-aware engine index that captures engine abstraction layers and cross-layer dependencies, and pre-validates backend-specific build, execution, and debugging workflows using already supported models. For each new model, a builder uses this knowledge to coordinate cross-layer changes, while an auditor checks implementation completeness and drives iterative debugging through device-side validation. Across 12 tasks spanning three mobile LLMs and four engine--backend pairs on CPUs, GPUs, and NPUs, EngineAgent achieves 75% end-to-end success with either of two underlying LLMs, versus 33.3% for the strongest coding-agent baseline. Success requires compilation, on-device execution, and output-logit agreement with reference implementations. EngineAgent also reduces average per-task time and model-API cost relative to baselines using the same underlying LLMs.

cs.OS↗

Towards Trustworthy Mobile Speech Interaction: Ensuring Voice Authenticity and Transmission Integrity

The rapid progress of generative speech models has made high-fidelity voice cloning and editing cheap, fast, and widely accessible, weakening the security of voiceprint-based authentication in mobile speech interactions. Existing speech watermarking techniques focus on offline protection or watermarking synthetic speech, and thus cannot verify whether a live utterance originates from the genuine speaker at capture time. We present \textit{MoBiMark}, a real-time \textbf{mo}bile \textbf{bi}ologic speech water\textbf{mark}ing system that binds ultrasonic articulatory signatures to speech content and embeds a dynamic watermark during capture. MoBiMark emits a multi-frequency ultrasonic probe on commodity smartphones, extracts echo features from the vocal tract, and fuses them with a content-dependent speech embedding to produce a dual-layer dynamic watermark combining a persistent user identifier (UID) and a per-utterance speech identifier (SID), enabling both source authentication and propagation-time tamper detection. A jointly trained embedder and detector injects the watermark while preserving perceptual quality, and system-level optimization with INT8 quantization enables lightweight on-device deployment. Evaluated on 50 users across four smartphone models, MoBiMark achieves an average 99.79% accuracy in source and propagation attacks, with negligible impact on speech quality and intelligibility.

cs.SD↗

Ultrasound-Assisted Biometric Watermarking Against Face Video Deepfakes

Currently, artificial intelligence-generated content (AIGC) poses a severe threat to facial video deepfakes, and many AIGC companies employ video watermarking to mitigate unauthorized fake video usage, but its effectiveness is limited due to watermark tampering and private-model forgery. Additionally, some schemes actively add watermarks to user videos. However, current approaches focus primarily on the quality of watermark embedding in offline scenarios, and no existing work offers a solution for protecting human facial videos in real-time online applications. To fill this gap, we propose, to the best of our knowledge, a novel biometric video watermarking method, UltraGuard, for the first time. It uses the smartphone's built-in speaker and microphone to emit ultrasonic signals and capture biometric features, which are then fused with spatio-temporal dynamic features derived from the video content. The fused features are encoded as watermarks and embedded into videos in real time, enabling dynamic, content-aware watermarking throughout transmission and propagation. Extensive experimental validation demonstrates that UltraGuard can effectively defend against malicious attacks such as forgery and editing, both at the source and during propagation, proving the system's efficacy. In the future, it can be deployed on users' mobile devices to provide real-time protection for users' facial videos, thereby preventing security and privacy breaches caused by various malicious attacks.

cs.CR↗

Beyond Overlap: Hierarchical Graph Abstraction for Out-of-Core Vector Search

At billion scale, approximate nearest neighbor search (ANNS) often becomes an out-of-core problem: the full vector collection and index structures exceed memory capacity, making query performance dominated by SSD accesses and DRAM-SSD data movement. Existing systems struggle to strike a balance between accuracy and efficiency: physical-overlap methods replicate vectors or index entries across partitions, enlarging the SSD-resident index and incurring extra I/O; quantization-based methods reduce memory usage, but their approximate distances are less reliable and often require costly raw-vector reranking from SSD to preserve recall. We present GANNS (Graph-Abstraction ANNS), a hierarchical out-of-core ANNS engine that improves accuracy and I/O efficiency simultaneously. GANNS stores each cluster as a disjoint SSD partition with scale-aware indexes, while a memory-resident graph abstraction provides logical overlap before SSD access. During serving, GANNS uses query hotness and cluster priorities from the graph abstraction to prune low-value clusters and improve access locality. Across five datasets under strict memory constraints, GANNS delivers representative QPS improvements of 2.0--4.7x over state-of-the-art baselines, while preserving accuracy.

cs.DB↗

Scaling LLM Agent Tool Access: The MCP Gateway

LLM agents increasingly rely on tool calling to complete tasks. Model Context Protocol (MCP) standardizes tool calling between LLM agents and tool providers. It reduces integration cost and drives rapid growth in tool scale. In production deployments, tool access becomes difficult to scale. On the tool provider side, legacy services are not directly callable through MCP; the rapid protocol development creates ongoing compatibility cost. On the agent side, the number of mounted tools is limited by the LLM context window and inference overhead; mounting a large tool set increases token usage and inference latency and can reduce task success rate. Moreover, for stateful MCP backends with multiple replicas, preserving session affinity increases client-side complexity. We present a cloud-scale MCP Gateway system. It breaks the direct-connect model on the data plane and offloads legacy service integration, consolidating incompatible MCP variants, access control, tool recommendation, and session-aware routing at the gateway. The conversion module supports 315 OpenAPI services in the cloud and integrates MCP transport variants. Session-aware routing decouples the scalability of the gateway layer and the MCP service layer. The hybrid retrieval engine sustains $\sim$98\% Top-15 recall; it scales agent tool access to 3{,}000+ tools with improved tool selection accuracy. We also share the lessons learned from deploying the gateway system in production.

cs.DC↗

Local-First Intelligence via Proactive SLM Collaborating with Feedback-Providing LLM

Personal intelligence requires strong capabilities under strict privacy and efficiency constraints. Unlike cloud-first intelligence, which relies on powerful but costly and privacy-vulnerable large language models (LLMs), we focus on local-first intelligence, emphasizing on-device small language models (SLMs), which enable efficient, private inference but have limited capacity. To reconcile the capability gap with privacy and efficiency, we propose a dynamic collaboration framework, where an SLM learns to proactively decide how to consult an LLM during multi-step reasoning, while the LLM provides adaptive feedback instead of acting as a passive tool, modeling them as heterogeneous agents under information asymmetry. We further systematically investigate how collaboration strategies are shaped by SLM and LLM capabilities as well as efficiency and privacy constraints. Evaluation results reveal a distinct scaling effect: stronger SLMs become more self-reliant, while stronger LLMs enable fewer and more informative interactions. In addition, the learned dynamic collaboration strategies significantly outperform various baselines and transfer robustly to unseen LLMs as well as to real-world personal tasks without additional training.

cs.CL↗

Dynamic Flow, Static Graph: KV Cache Reuse for Efficient LLM Serving on Mobile NPUs

On-device large language model (LLM) serving is a cornerstone of local-first personal intelligence, offering users data sovereignty, strong privacy guarantees, and freedom from cloud API latency and cost. Although KV caching is widely used to reduce latency in long-context inference, existing designs were primarily optimized for cloud GPUs with dynamic execution environments and abundant memory bandwidth. These architectural assumptions do not hold on mobile NPUs, where computation graphs must be statically compiled and both memory capacity and I/O bandwidth are severely constrained. In this work, we present a compute-storage co-design for mobile-centric prefix and non-prefix KV reuse. We first propose an intra-graph mechanism that maps selective KV recomputation onto static NPU graphs, reconciling algorithmic dynamicity with NPU staticity. We further develop an inter-graph scheduler to optimize chunk merging and minimize padding with dynamic programming. To address mobile bandwidth limitations, we introduce a hierarchical KV manager featuring a tree-hash-semantic hybrid structure, along with cost-aware prefetching and eviction policies. We also build a two-dimensional pipeline that overlaps KV loading, rerotation, and storage with NPU execution, hiding data-movement latency. Experiments across representative on-device workloads and LLMs show that our design reduces time-to-first-token (TTFT) by $40-60\%$ compared with no reuse and prefix-only caching.

cs.OS↗

EBRL: Asynchronous Embodied RL by Multi-Grained Resource Management

Embodied reinforcement learning (RL) improves model capabilities with a pipeline of environment simulation, action generation, and model updates. These stages show heterogeneous CPU and GPU demands, making efficient resource utilization difficult. Recent systems overlap rollout (simulation and generation) with training for efficiency, but exclusive GPU allocation and synchronized barrier in rollout still leave substantial hardware resource waste. In this paper, we present EBRL, an asynchronous embodied RL training system with two core techniques. The asynchronous pipelined scheduler overlaps rollout and training, pipelines simulation and generation across environment groups, and carries out each environment independently, eliminating synchronization stalls. The fine-grained resource manager pools CPU cores and GPU streaming multiprocessors, and uses stage profiles and runtime feedback to adjust resource quotas and batch sizes to meet the shifting demands among stages. We implement EBRL on RLinf and evaluate it with four embodied policies and four simulation benchmarks across heterogeneous GPU testbeds. Experiments show that EBRL achieves 1.30-3.47 times the end-to-end rollout throughput and 2.5 times of training convergency compared to the SOTA embodied RL systems.

cs.LG↗

Reflection with Action-Induced Visual Differences for Desktop GUI Agents

The Planner-Operator-Reflector (POR) framework is widely used in GUI agents to maintain objective alignment in complex tasks through modular collaboration. However, desktop GUIs introduce a key challenge: large, dense interfaces often exhibit subtle or scattered state changes, placing most of the burden on the reflector, which must compare pre- and post-action screens, while the planner and operator reason over a single state. Existing reflectors collapse change detection and outcome verification into one step, leaving evidence implicit and yielding weakly grounded decisions. To address this limitation, we propose Evidence-First Reflection (EFR), a two-stage reflector that explicitly decouples action-induced visual differences extraction from outcome verification. EFR identifies the action location and candidate changed regions with Set-of-Marks annotations, describes and filters action-relevant changes, and makes the final judgment from the cleaned evidence. This evidence-reasoning decoupled design makes reflection better grounded in screen transitions, while reducing both visual search complexity and reasoning burden. Experiments on OSWorld-Verified and WindowsAgentArena demonstrate that EFR improves reflector accuracy by 7.11%, yielding average end-to-end task success gains of 5.94% and 4.95% on the two benchmarks, respectively.

cs.AI↗

CoRun: Padding is Simple and Efficient for Deterministic LLM Inference

Despite fixed sampling parameters and random seeds, Large Language Model (LLM) inference exhibits output inconsistency, which undermines downstream tasks such as model evaluation and reinforcement learning. A major source of this nondeterminism is batch-dependent GPU execution: dynamic input shapes change kernel tiling and floating-point reduction orders. Existing systems address this problem with batch-invariant kernels, but these kernels restrict optimized tiling and split reductions, increasing more than 2$\times$ latency and reducing serving throughput by up to 74 %. This paper observes that although most kernels are not batch-invariant, they are position-invariant. Leveraging this property, we present CoRun, a scheduling-based system that achieves deterministic inference without requiring batch invariance. CoRun employs isolated prefill and fixed-shape batched decode to handle the two stages of LLM inference, respectively, leveraging CUDA graphs for efficient execution and simplified implementation. Experiments on LLMs with diverse architectures, including Qwen and DeepSeek, show that CoRun ensures determinism while improving throughput by 15-324 % over batch-invariant approaches, reducing time-to-first-token by 51.8 % and time-per-output-token by 48.6 % on average.

cs.OS↗

TIDE-MC: Two-Sided Interpolative Decomposition for Billion-Scale GPU Matrix Completion

Matrix completion supports large-scale recommendation and scientific computing, yet existing GPU solvers commonly assume that the observed matrix or its dense factors fit in device memory. On real workloads, this assumption leads to out-of-memory failures or severe PCIe overhead under naive paging. We present TIDE-MC, a bounded-memory GPU framework built on Two-Sided Interpolative Decomposition (TSID). TSID uses a sampled template submatrix as an anchor for reconstructing the full low-rank matrix, allowing computation and storage to scale with the template and active data chunks rather than the complete matrix. TIDE-MC realizes this formulation through two execution stages. First, a conflict-free synchronization engine recovers the template using parallel factorization and hierarchical gradient aggregation. Second, a chunked reconstruction pipeline extends the recovered template to the remaining matrix while overlapping PCIe transfers with GPU computation. An asymmetric gradient-clipping scheme stabilizes mixed-precision Tensor Core execution. Across 15 benchmarks, TIDE-MC completes workloads that cause existing GPU solvers to run out of memory. Compared with the evaluated state-of-the-art baselines, it achieves up to 11,647x speedup, reduces peak memory usage by up to 8.5x, and lowers reconstruction error by up to 99.7%. These results show that template-anchored decomposition and stage-specific GPU execution can scale matrix completion beyond device-memory capacity.

cs.DC↗

Not All Pixels Are Equal: Pixel-wise Meta-Learning for Medical Segmentation with Noisy Labels

Medical image segmentation is crucial for clinical applications, but it is frequently disrupted by noisy annotations and ambiguous anatomical boundaries, limiting its application in real-world scenarios. Existing methods often directly adapt noisy label learning techniques designed for instance classification, overlooking the pixel-wise heterogeneity in medical segmentation with its spatially and anatomically varying difficulties. Consequently, global assumptions or simple confidence metrics fail to address these local variations, leaving boundary ambiguities unresolved. To address this issue, we propose MetaDCSeg, a robust framework that dynamically learns optimal pixel-wise weights to suppress the influence of noisy labels while preserving reliable annotations. By explicitly modeling boundary uncertainty through a Dynamic Center Distance (DCD) mechanism, our approach utilizes weighted feature distances for foreground, background, and boundary centers, directing the model's attention toward hard-to-segment pixels near ambiguous boundaries. This strategy enables more precise handling of structural boundaries, which are often overlooked by existing methods, and significantly enhances segmentation performance. Extensive experiments across four benchmark datasets with varying noise levels demonstrate that MetaDCSeg outperforms existing state-of-the-art methods.

cs.CV↗

Gleam: Adaptive Network-Efficient CUDA API Remoting for Cross-Device GPU Sharing over LANs

This paper aims to enable computation- and communication-efficient GPU sharing across devices within local area networks (LANs), facilitating ubiquitous AI inference on heterogeneous personal devices. We achieve distributed task offloading via CUDA API remoting. However, beyond raw computation, network constraints emerge as the primary bottleneck: limited bandwidth, high-frequency API invocations, and cross-task contention significantly hinder performance. To address these challenges, we propose Gleam, a novel and network-efficient framework for task-generic GPU sharing across local-area CUDA devices, with three key contributions. First, we reduce bandwidth overhead in CUDA API remoting through automatic model weight caching, and mitigate accumulated latency from frequent API calls by asynchronous execution. Second, we design a runtime task scheduler that dynamically determines API remoting pairs between LAN clients and servers, explicitly accounting for both network conditions and GPU resource contention under parallel workloads. Finally, we introduce dedicated mechanisms to ensure CUDA context consistency across distributed executions. Extensive experiments on heterogeneous NVIDIA GPUs and diverse AI workloads show Gleam consistently outperforms state-of-the-art baselines, achieving 1.4-24.2 times improvements in API remoting efficiency and up to 1.79 times higher system throughput.

cs.DC↗

CaT-GS: Efficient 3DGS Rendering for Large Scale Scenes via Inter-frame Caching and Tile Scheduling

Recent breakthroughs in 3D Gaussian Splatting (3DGS) have advanced neural rendering with high fidelity and speed. However, its performance degrades significantly in large-scale scenes due to the computational burden of tile-based rasterization. Existing optimization efforts either require costly scene re-training or focus on narrow aspects of the pipeline, overlooking critical inefficiencies in real-world deployments. Through a comprehensive analysis, we identify three primary sources of redundancy and low GPU utilization: redundant inter-frame pre-processing, viewpoint-based occlusion redundancy, and severe tile-level load imbalance. To address these issues, we propose CaT-GS, a novel and efficient 3DGS rendering pipeline. CaT-GS introduces a speculative multi-frame preprocessing method to eliminate redundant computations across consecutive frames, and an inter-frame caching mechanism to eliminate viewpoint redundant rendering stages. Furthermore, it refactors rasterization tasks with a dedicated kernel to mitigate tile load imbalance, significantly boosting GPU utilization. Extensive experiments demonstrate that CaT-GS achieves a speedup of up to 10 times over the original 3DGS and up to 70% over previous state-of-the-art methods, establishing a new benchmark for high-fidelity, real-time rendering of large-scale scenes.

cs.CV↗

C$^2$KV: Compressed and Composable KV Cache Reuse for Efficient LLM Inference

Long-context inference is central to modern large language model (LLM) applications such as retrieval-augmented generation and multi-document reasoning. To mitigate the growing inference cost, recent work has explored key-value (KV) cache reuse to reduce redundant prefill computation. However, existing reuse methods primarily focus on computation savings and overlook a critical bottleneck in long-context LLM serving: the cost of storing and accessing large KV caches. While KV compression appears to be a natural complement, naively combining compression with non-prefix KV reuse often leads to severe accuracy degradation. In this work, we propose C$^2$KV, a unified framework for non-prefix KV reuse that jointly optimizes KV extraction and inference-time concatenation. C$^2$KV learns a composable and compressed KV cache manifold that is explicitly designed to be position-agnostic. Our approach introduces a lightweight sidecar Extractor with learnable compression tokens and a structured attention flow, enabling modular KV representations that can be flexibly reused and concatenated without modifying the frozen base model. We further employ a compression-concatenation co-training strategy to align extraction-time representations with their downstream reuse behavior. Extensive experiments across multiple long-context benchmarks and model families demonstrate that C$^2$KV significantly reduces KV cache storage and transfer costs, achieving up to 17$\times$ inference speedup under long contexts, while preserving generation quality.

cs.CL↗

SmartSwap: Swap-Based Memory Optimization for LLM Training under Varying Operator Sequences

The increasing size of large language models (LLMs) has led to a surge in memory requirements during training, often exceeding the capacity of high-bandwidth memory (HBM). Swap-based memory optimization incurs neither accuracy loss nor additional end-to-end overhead when effectively overlapped, thus being an attractive solution. However, existing swap methods assume consistent operator sequences, which is impractical in Eager Mode, where operator sequences can vary during change. We propose Chameleon, which redesigns the end-to-end process of swap-based memory optimization and is the first work to consider varying operator sequences in Eager Mode. Chameleon (i) introduces a lightweight online profiler to enable continuous profiling for monitoring operator sequences, (ii) generates effective swap policies with limited operator information, and (iii) optimizes the policy execution module for accurate policy application and better performance. Experimental results demonstrate that Chameleon reduces profiling overhead by 84.25%, enables training models up to 4x larger than hardware memory while adapting to changes in operator sequences, improves performance by up to 38.94% compared to recomputation or high-degree parallelism.

cs.DC↗

UBEP: Re-architecting Expert Parallelism Communication Library for Production Superpods

The deployment of Mixture-of-Experts (MoE) models on production high-bandwidth superpods, such as NVIDIA's NVL72/576 and Huawei's CloudMatrix384, introduces critical challenges beyond raw interconnect bandwidth. While these systems provide unified global address spaces and high-bandwidth fabrics, their full potential for sparse MoE communication is hindered by three fundamental bottlenecks: (1) Strict execution serialization imposed by coarse-grained Bulk Synchronous Parallel (BSP) orchestration of interdependent communication phases; (2) Prohibitive synchronization overhead that fails to scale alongside high interconnect bandwidth; and (3) Severe load imbalance resulting from distance-agnostic scheduling of irregular token traffic. To eliminate these bottlenecks, we introduce UBEP (Unified-Bus Expert Parallelism), a production-ready communication library that rethinks MoE's All-to-All primitives for modern superpod architectures. Through large scale experiments, UBEP reduces All-to-All latency by up to 52.4% and MoE inference Time Per Output Token (TPOT) by up to 11.1%.

cs.DC↗

SmartThinker: Progressive Chain-of-Thought Length Calibration for Efficient Large Language Model Reasoning

Large reasoning models (LRMs) like OpenAI o1 and DeepSeek-R1 achieve high accuracy on complex tasks by adopting long chain-of-thought (CoT) reasoning paths. However, the inherent verbosity of these processes frequently results in redundancy and overthinking. To address this issue, existing works leverage Group Relative Policy Optimization (GRPO) to reduce LRM output length, but their static length reward design cannot dynamically adapt according to the relative problem difficulty and response length distribution, causing over-compression and compromised accuracy. Therefore, we propose SmartThinker, a novel GRPO-based efficient reasoning method with progressive CoT length calibration. SmartThinker makes a two-fold contribution: First, it dynamically estimates the optimal length with peak accuracy during training and guides overlong responses toward it to reduce response length while sustaining accuracy. Second, it dynamically modulates the length reward coefficient to avoid the unwarranted penalization of correct reasoning paths. Extensive experiment results show that SmartThinker achieves up to 52.5% average length compression with improved accuracy, and achieves up to 16.6% accuracy improvement on challenging benchmarks like AIME25. The source code can be found at https://github.com/SJTU-RTEAS/SmartThinker.

cs.CL↗