arXiv subjects

Chuyi Li

Publications and source records attributed to Chuyi Li.

5 recordsLinked to original sources

arXiv2025

Translation-Symmetric Market: Enabling Incentive Compatibility For DER Aggregation

Virtual power plants (VPPs) are important for coordinating the rapidly growing portfolios of distributed energy resources (DERs) and enabling them to deliver multiple services to higher-level electricity markets. However, profit allocation procedures for VPP participants become increasingly difficult to design in an incentive-compatible manner, owing to the increased market power of DERs within each VPP relative to their direct participation in wholesale markets. In this paper, we introduce translation symmetry in electricity markets and apply it to VPP aggregation of DERs for market participation to design an incentive-compatible profit allocation method. Under the stated assumptions, we prove that this translation symmetry induces an inductive property: once incentive compatibility holds at an upper level, it propagates to the internal settlements between the VPP and its constituent DERs, thereby supporting incentive compatibility throughout the hierarchy. We further show that service prices are invariant across levels, which helps preserve competitive conditions and enables transparent value assessment. Theoretical analysis and case studies illustrate how this translation-symmetry-based approach can enable incentive-compatible profit allocation when aggregating DERs to provide multiple services.

eess.SY↗

arXiv2025

Static and Plugged: Make Embodied Evaluation Simple

Embodied intelligence is advancing rapidly, driving the need for efficient evaluation. Current benchmarks typically rely on interactive simulated environments or real-world setups, which are costly, fragmented, and hard to scale. To address this, we introduce StaticEmbodiedBench, a plug-and-play benchmark that enables unified evaluation using static scene representations. Covering 42 diverse scenarios and 8 core dimensions, it supports scalable and comprehensive assessment through a simple interface. Furthermore, we evaluate 19 Vision-Language Models (VLMs) and 11 Vision-Language-Action models (VLAs), establishing the first unified static leaderboard for Embodied intelligence. Moreover, we release a subset of 200 samples from our benchmark to accelerate the development of embodied intelligence.

cs.CV↗

arXiv2024

Computation-power Coupled Modeling for IDCs and Collaborative Optimization in ADNs

The batch and online workload of Internet data centers (IDCs) offer temporal and spatial scheduling flexibility. Given that power generation costs vary over time and location, harnessing the flexibility of IDCs' energy consumption through workload regulation can optimize the power flow within the system. This paper focuses on multi-geographically distributed IDCs managed by an Internet service company (ISC), which are aggregated as a controllable load. The load flexibility resulting from spatial load regulation of online workload is taken into account. A two-step workload scheduling mechanism is adopted, and a computation-power coupling model of ISC is established to facilitate collaborative optimization in active distribution networks (ADNs). To address the model-solving problem based on the assumption of scheduling homogeneity, a model reconstruction method is proposed. An efficient iterative algorithm is designed to solve the reconstructed model. Furthermore, the Nash bargaining solution is employed to coordinate the different optimization objectives of ISC and power system operators, thereby avoiding subjective arbitrariness. Experimental cases based on a 33-node distribution system are designed to verify the effectiveness of the model and algorithm in optimizing ISC's energy consumption and power flow within the system.

eess.SY↗

arXiv2023

YOLOv6 v3.0: A Full-Scale Reloading

The YOLO community has been in high spirits since our first two releases! By the advent of Chinese New Year 2023, which sees the Year of the Rabbit, we refurnish YOLOv6 with numerous novel enhancements on the network architecture and the training scheme. This release is identified as YOLOv6 v3.0. For a glimpse of performance, our YOLOv6-N hits 37.5% AP on the COCO dataset at a throughput of 1187 FPS tested with an NVIDIA Tesla T4 GPU. YOLOv6-S strikes 45.0% AP at 484 FPS, outperforming other mainstream detectors at the same scale (YOLOv5-S, YOLOv8-S, YOLOX-S and PPYOLOE-S). Whereas, YOLOv6-M/L also achieve better accuracy performance (50.0%/52.8% respectively) than other detectors at a similar inference speed. Additionally, with an extended backbone and neck design, our YOLOv6-L6 achieves the state-of-the-art accuracy in real-time. Extensive experiments are carefully conducted to validate the effectiveness of each improving component. Our code is made available at https://github.com/meituan/YOLOv6.

cs.CV↗

arXiv2022

YOLOv6: A Single-Stage Object Detection Framework for Industrial Applications

For years, the YOLO series has been the de facto industry-level standard for efficient object detection. The YOLO community has prospered overwhelmingly to enrich its use in a multitude of hardware platforms and abundant scenarios. In this technical report, we strive to push its limits to the next level, stepping forward with an unwavering mindset for industry application. Considering the diverse requirements for speed and accuracy in the real environment, we extensively examine the up-to-date object detection advancements either from industry or academia. Specifically, we heavily assimilate ideas from recent network design, training strategies, testing techniques, quantization, and optimization methods. On top of this, we integrate our thoughts and practice to build a suite of deployment-ready networks at various scales to accommodate diversified use cases. With the generous permission of YOLO authors, we name it YOLOv6. We also express our warm welcome to users and contributors for further enhancement. For a glimpse of performance, our YOLOv6-N hits 35.9% AP on the COCO dataset at a throughput of 1234 FPS on an NVIDIA Tesla T4 GPU. YOLOv6-S strikes 43.5% AP at 495 FPS, outperforming other mainstream detectors at the same scale~(YOLOv5-S, YOLOX-S, and PPYOLOE-S). Our quantized version of YOLOv6-S even brings a new state-of-the-art 43.3% AP at 869 FPS. Furthermore, YOLOv6-M/L also achieves better accuracy performance (i.e., 49.5%/52.3%) than other detectors with a similar inference speed. We carefully conducted experiments to validate the effectiveness of each component. Our code is made available at https://github.com/meituan/YOLOv6.

cs.CV↗