Yun Ma
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Yun Ma has a total of 167 co-authors. Here are the top co-authors by number of shared publications:
- Xuanzhe Liu
Peking University
20 shared publications - Gang Huang
School of Computer Science, Peking University, Beijing, China
14 shared publications - Weichen Bi
Peking University
11 shared publications - Zhenpeng Chen
Tsinghua University, Beijing, China
9 shared publications - Mugeng Liu
School of Computer Science, Peking University, Beijing, China
8 shared publications - Yudong Han
Institute for Artificial Intelligence, Peking University, Beijing, China
8 shared publications
Latest Publications
- 1 December 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Mobile Computing
- Vol. 25  (12) , 24512-24529
Performance and Power Analysis of Web-Based Mobile Extended Reality
- 1 December 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Mobile Computing
- Vol. 25  (12) , 24512-24529
Performance and Power Analysis of Web-Based Mobile Extended Reality
- Open Access
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 2825-2834
WebSplatter: Efficient and Faithful In-Browser 3D Gaussian Splatting across Devices via WebGPU
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 2825-2834
Open AccessWebSplatter: Efficient and Faithful In-Browser 3D Gaussian Splatting across Devices via WebGPU
- Open Access
- 19 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 701-711
MCP-Focus: Leveraging Function-Oriented Document Enhancement for MCP Server Retrieval
- 19 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 701-711
Open AccessMCP-Focus: Leveraging Function-Oriented Document Enhancement for MCP Server Retrieval
- 1 June 2026
- Published by Elsevier in Expert Systems with Applications
- Vol. 330
LiveLens: Streamer-centric feature fusion framework for sales prediction in live-streaming E-commerce
- 1 June 2026
- Published by Elsevier in Expert Systems with Applications
- Vol. 330
LiveLens: Streamer-centric feature fusion framework for sales prediction in live-streaming E-commerce
- Open Access
- 28 May 2026
- Published by Association for Computing Machinery (ACM)
- p. 532-535
WAB: Overcoming Memory, Network, and Security Walls in Native Agentic Browsers with WebAssembly
- 28 May 2026
- Published by Association for Computing Machinery (ACM)
- p. 532-535
Open AccessWAB: Overcoming Memory, Network, and Security Walls in Native Agentic Browsers with WebAssembly
- Open Access
- 12 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 1609-1621
Characterizing GPU-accelerated Web Applications in Browsers
- 12 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 1609-1621
Open AccessCharacterizing GPU-accelerated Web Applications in Browsers
- Open Access
- 12 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 5404-5414
LaTune : Lightweight and Adaptive Configuration Tuning for LLM Inference on Edge Devices
- 12 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 5404-5414
Open AccessLaTune : Lightweight and Adaptive Configuration Tuning for LLM Inference on Edge Devices
- Open Access
MEME: Modeling the Evolutionary Modes of Financial Markets
LLMs have demonstrated significant potential in quantitative finance by processing vast unstructured data to emulate human-like analytical workflows. However, current LLM-based methods primarily follow either an Asset-Centric paradigm focused on individual stock prediction or a Market-Centric approach for portfolio allocation, often remaining agnostic to the underlying reasoning that drives market movements. In this paper, we propose a Logic-Oriented perspective, modeling the financial market as a dynamic, evolutionary ecosystem of competing investment narratives, termed Modes of Thought. To operationalize this view, we introduce MEME (Modeling the Evolutionary Modes of Financial Markets), designed to reconstruct market dynamics through the lens of evolving logics. MEME employs a multi-agent extraction module to transform noisy data into high-fidelity Investment Arguments and utilizes Gaussian Mixture Modeling to uncover latent consensus within a semantic space. To model semantic drift among different market conditions, we also implement a temporal evaluation and alignment mechanism to track the lifecycle and historical profitability of these modes. By prioritizing enduring market wisdom over transient anomalies, MEME ensures that portfolio construction is guided by robust reasoning. Extensive experiments on three heterogeneous Chinese stock pools from 2023 to 2025 demonstrate that MEME consistently outperforms seven SOTA baselines. Further ablation studies, sensitivity analysis, lifecycle case study and cost analysis validate MEME's capacity to identify and adapt to the evolving consensus of financial markets. Our implementation can be found at https://github.com/gta0804/MEME.
Open AccessMEME: Modeling the Evolutionary Modes of Financial Markets
LLMs have demonstrated significant potential in quantitative finance by processing vast unstructured data to emulate human-like analytical workflows. However, current LLM-based methods primarily follow either an Asset-Centric paradigm focused on individual stock prediction or a Market-Centric approach for portfolio allocation, often remaining agnostic to the underlying reasoning that drives market movements. In this paper, we propose a Logic-Oriented perspective, modeling the financial market as a dynamic, evolutionary ecosystem of competing investment narratives, termed Modes of Thought. To operationalize this view, we introduce MEME (Modeling the Evolutionary Modes of Financial Markets), designed to reconstruct market dynamics through the lens of evolving logics. MEME employs a multi-agent extraction module to transform noisy data into high-fidelity Investment Arguments and utilizes Gaussian Mixture Modeling to uncover latent consensus within a semantic space. To model semantic drift among different market conditions, we also implement a temporal evaluation and alignment mechanism to track the lifecycle and historical profitability of these modes. By prioritizing enduring market wisdom over transient anomalies, MEME ensures that portfolio construction is guided by robust reasoning. Extensive experiments on three heterogeneous Chinese stock pools from 2023 to 2025 demonstrate that MEME consistently outperforms seven SOTA baselines. Further ablation studies, sensitivity analysis, lifecycle case study and cost analysis validate MEME's capacity to identify and adapt to the evolving consensus of financial markets. Our implementation can be found at https://github.com/gta0804/MEME.
- Open Access
AlphaPROBE: Alpha Mining via Principled Retrieval and On-graph biased evolution
Extracting signals through alpha factor mining is a fundamental challenge in quantitative finance. Existing automated methods primarily follow two paradigms: Decoupled Factor Generation, which treats factor discovery as isolated events, and Iterative Factor Evolution, which focuses on local parent-child refinements. However, both paradigms lack a global structural view, often treating factor pools as unstructured collections or fragmented chains, which leads to redundant search and limited diversity. To address these limitations, we introduce AlphaPROBE (Alpha Mining via Principled Retrieval and On-graph Biased Evolution), a framework that reframes alpha mining as the strategic navigation of a Directed Acyclic Graph (DAG). By modeling factors as nodes and evolutionary links as edges, AlphaPROBE treats the factor pool as a dynamic, interconnected ecosystem. The framework consists of two core components: a Bayesian Factor Retriever that identifies high-potential seeds by balancing exploitation and exploration through a posterior probability model, and a DAG-aware Factor Generator that leverages the full ancestral trace of factors to produce context-aware, nonredundant optimizations. Extensive experiments on three major Chinese stock market datasets against 8 competitive baselines demonstrate that AlphaPROBE significantly gains enhanced performance in predictive accuracy, return stability and training efficiency. Our results confirm that leveraging global evolutionary topology is essential for efficient and robust automated alpha discovery. We have open-sourced our implementation at https://github.com/gta0804/AlphaPROBE.
Open AccessAlphaPROBE: Alpha Mining via Principled Retrieval and On-graph biased evolution
Extracting signals through alpha factor mining is a fundamental challenge in quantitative finance. Existing automated methods primarily follow two paradigms: Decoupled Factor Generation, which treats factor discovery as isolated events, and Iterative Factor Evolution, which focuses on local parent-child refinements. However, both paradigms lack a global structural view, often treating factor pools as unstructured collections or fragmented chains, which leads to redundant search and limited diversity. To address these limitations, we introduce AlphaPROBE (Alpha Mining via Principled Retrieval and On-graph Biased Evolution), a framework that reframes alpha mining as the strategic navigation of a Directed Acyclic Graph (DAG). By modeling factors as nodes and evolutionary links as edges, AlphaPROBE treats the factor pool as a dynamic, interconnected ecosystem. The framework consists of two core components: a Bayesian Factor Retriever that identifies high-potential seeds by balancing exploitation and exploration through a posterior probability model, and a DAG-aware Factor Generator that leverages the full ancestral trace of factors to produce context-aware, nonredundant optimizations. Extensive experiments on three major Chinese stock market datasets against 8 competitive baselines demonstrate that AlphaPROBE significantly gains enhanced performance in predictive accuracy, return stability and training efficiency. Our results confirm that leveraging global evolutionary topology is essential for efficient and robust automated alpha discovery. We have open-sourced our implementation at https://github.com/gta0804/AlphaPROBE.
- Open Access
WebSplatter: Enabling Cross-Device Efficient Gaussian Splatting in Web Browsers via WebGPU
We present WebSplatter, an end-to-end GPU rendering pipeline for the heterogeneous web ecosystem. Unlike naive ports, WebSplatter introduces a wait-free hierarchical radix sort that circumvents the lack of global atomics in WebGPU, ensuring deterministic execution across diverse hardware. Furthermore, we propose an opacity-aware geometry culling stage that dynamically prunes splats before rasterization, significantly reducing overdraw and peak memory footprint. Evaluation demonstrates that WebSplatter consistently achieves 1.2$\times$ to 4.5$\times$ speedups over state-of-the-art web viewers.
Open AccessWebSplatter: Enabling Cross-Device Efficient Gaussian Splatting in Web Browsers via WebGPU
We present WebSplatter, an end-to-end GPU rendering pipeline for the heterogeneous web ecosystem. Unlike naive ports, WebSplatter introduces a wait-free hierarchical radix sort that circumvents the lack of global atomics in WebGPU, ensuring deterministic execution across diverse hardware. Furthermore, we propose an opacity-aware geometry culling stage that dynamically prunes splats before rasterization, significantly reducing overdraw and peak memory footprint. Evaluation demonstrates that WebSplatter consistently achieves 1.2$\times$ to 4.5$\times$ speedups over state-of-the-art web viewers.