arXiv subjects

Mingliu Liu

Publications and source records attributed to Mingliu Liu.

4 recordsLinked to original sources

arXiv2026

SynerDiff: Synergetic Continuous Batching for Fast and Parallel Diffusion Model Inference

The expansion of Artificial Intelligence-generated content service requires diffusion model serving to simultaneously achieve high throughput and low task end-to-end (E2E) latency. However, existing continuous batching methods suffer from severe resource contention during UNet-VAE concurrency, leading to latency spikes. Furthermore, concurrent multi-task scheduling entails a trade-off between UNet throughput and VAE latency across varying scheduling strategies. To address these, we propose SynerDiff, an efficient continuous batching system built on intra-inter level synergy. At the intra-concurrency level, SynerDiff alleviates resource contention by pruning component-specific resource bottlenecks via VAE Chunking and Adaptive Skip-CFG. At the inter-concurrency level, leveraging components' differential sensitivity to scheduling granularities, a threshold-aware scheduler plans concurrent sequences and tunes intra-concurrency decisions to minimize VAE latency while maintaining UNet within high-throughput threshold. Additionally, a feedback controller dynamically adjusts this threshold based on queue loads to boost system capacity ceiling. Experimental results show that, SynerDiff improves throughput by 1.6$\times$ and decreases both average E2E and P99 tail latencies by up to 78.7\%, compared to benchmarks while guaranteeing high image fidelity.

cs.AI↗

arXiv2026

Stop Wandering: Efficient Vision-Language Navigation via Metacognitive Reasoning

Training-free Vision-Language Navigation (VLN) agents powered by foundation models can follow instructions and explore 3D environments. However, existing approaches rely on greedy frontier selection and passive spatial memory, leading to inefficient behaviors such as local oscillation and redundant revisiting. We argue that this stems from a lack of metacognitive capabilities: the agent cannot monitor its exploration progress, diagnose strategy failures, or adapt accordingly. To address this, we propose MetaNav, a metacognitive navigation agent integrating spatial memory, history-aware planning, and reflective correction. Spatial memory builds a persistent 3D semantic map. History-aware planning penalizes revisiting to improve efficiency. Reflective correction detects stagnation and uses an LLM to generate corrective rules that guide future frontier selection. Experiments on GOAT-Bench, HM3D-OVON, and A-EQA show that MetaNav achieves state-of-the-art performance while reducing VLM queries by 20.7%, demonstrating that metacognitive reasoning significantly improves robustness and efficiency.

cs.RO↗

arXiv2025

BEVCooper: Accurate and Communication-Efficient Bird's-Eye-View Perception in Vehicular Networks

Bird's-Eye-View (BEV) is critical to connected and automated vehicles (CAVs) as it can provide unified and precise representation of vehicular surroundings. However, quality of the raw sensing data may degrade in occluded or distant regions, undermining the fidelity of constructed BEV map. In this paper, we propose BEVCooper, a novel collaborative perception framework that can guarantee accurate and low-latency BEV map construction. We first define an effective metric to evaluate the utility of BEV features from neighboring CAVs. Then, based on this, we develop an online learning-based collaborative CAV selection strategy that captures the ever-changing BEV feature utility of neighboring vehicles, enabling the ego CAV to prioritize the most valuable sources under bandwidth-constrained vehicle-to-vehicle (V2V) links. Furthermore, we design an adaptive fusion mechanism that optimizes BEV feature compression based on the environment dynamics and real-time V2V channel quality, effectively balancing feature transmission latency and accuracy of the constructed BEV map. Theoretical analysis demonstrates that, BEVCooper achieves asymptotically optimal CAV selection and adaptive feature fusion under dynamic vehicular topology and V2V channel conditions. Extensive experiments on real-world testbed show that, compared with state-of-the-art benchmarks, the proposed BEVCooper enhances BEV perception accuracy by up to $63.18\%$ and reduces end-to-end latency by $67.9\%$, with only $1.8\%$ additional computational overhead.

cs.NI↗

arXiv2023

Duration-adaptive Video Highlight Pre-caching for Vehicular Communication Network

Video traffic in vehicular communication networks (VCNs) faces exponential growth. However, different segments of most videos reveal various attractiveness for viewers, and the pre-caching decision is greatly affected by the dynamic service duration that edge nodes can provide services for mobile vehicles driving along a road. In this paper, we propose an efficient video highlight pre-caching scheme in the vehicular communication network, adapting to the service duration. Specifically, a highlight entropy model is devised with the consideration of the segments' popularity and continuity between segments within a period of time, based on which, an optimization problem of video highlight pre-caching is formulated. As this problem is non-convex and lacks a closed-form expression of the objective function, we decouple multiple variables by deriving candidate highlight segmentations of videos through wavelet transform, which can significantly reduce the complexity of highlight pre-caching. Then the problem is solved iteratively by a highlight-direction trimming algorithm, which is proven to be locally optimal. Simulation results based on real-world video datasets demonstrate significant improvement in highlight entropy and jitter compared to benchmark schemes.

eess.IV↗