Selected work

Representative Papers

Demystifying Chains, Trees, and Graphs of Thoughts

Jan 25, 2024

Existing structured prompting paradigms—such as Chain-of-Thought (CoT), Tree-of-Thought (ToT), and Graph-of-Thought (GoT)—lack a unified theoretical foundation, suffering from conceptual conflation and an absence of systematic taxonomy. Method: We propose the first comprehensive taxonomy for structured prompting, formally defining the notion of “reasoning topology,” constructing its spatial representation, and unifying CoT, ToT, and GoT through pipeline-based execution analysis, structural modeling, behavioral interpretation, and cross-paradigm empirical comparison. Contribution/Results: (1) We establish the first principled taxonomy for structured-prompt reasoning; (2) we uncover intrinsic relationships between topological structure and both reasoning performance and computational cost; and (3) we provide a theoretically grounded framework and design principles for scalable, interpretable prompt engineering.

21 citations1 influentialRead paper

Some homogeneity test statistics for DNA evolutionary models

Sep 06, 2026

本文提出了一种用于DNA序列比较的广义U统计量，以测试在零假设下的分布同质性，并通过随机模拟展示了其理论性质和实证表现。

0 citationsRead paper

A Mathematical Framework for Topological Causal Data Analysis

Jul 30, 2026

Traditional causal inference methods struggle to handle structured data such as images and point clouds, primarily because the difference between potential outcomes may be undefined. This work proposes a Topological Causal Data Analysis (TCDA) framework that decouples the observed space, causal model, topological representation, and causal queries, distinguishing between outcome-level and distribution-level analyses. The framework establishes identifiability conditions and a doubly robust estimation procedure. By integrating Banach space–valued summaries, the g-formula, and topological representation theory, it constructs the first systematic mathematical foundation for causal inference with structured data. The study clarifies the auxiliary role of topology in causal analysis, introduces a target-oriented topological ignorability condition, and delineates the applicability boundaries of observed topologies in causal discovery.

0 citationsRead paper

SPEC CPU: The Next Generation

May 02, 2026

This work addresses the limitations of existing CPU benchmarks in accurately evaluating the performance of modern heterogeneous, multithreaded processors under diverse workloads. To this end, the authors present the SPEC CPU 2026 benchmark suite, developed through community collaboration and principled methodology, which introduces the Rolling-Round-Robin Rate approach to standardize the execution of heterogeneous multiprogrammed workloads. The suite incorporates newly designed multithreaded benchmarks exhibiting varied microarchitectural characteristics, selected and hardened through an open-source application curation process. Emphasizing workload diversity, portability, and long-term viability, SPEC CPU 2026 establishes a robust, representative, and authoritative standard for performance evaluation, thereby supporting next-generation computer architecture research.

0 citationsRead paper

KV Cache Optimization Strategies for Scalable and Efficient LLM Inference

Mar 20, 2026

KV cache grows linearly with context length, becoming a critical bottleneck in GPU memory capacity and bandwidth during large language model inference. This work presents the first systematic taxonomy of existing KV cache optimization techniques, categorizing them into five classes: cache eviction, compression, hybrid memory management, novel attention mechanisms, and hybrid strategies. The study evaluates these approaches across seven representative deployment scenarios, revealing that no single method universally dominates; instead, optimal choices require careful trade-offs among memory usage, throughput, and accuracy based on context length, hardware constraints, and workload characteristics. The paper further advocates adaptive, multi-stage optimization as a promising direction for future research, offering both theoretical insights and practical guidance for real-world deployment.

0 citationsRead paper

Recent publications

Latest Papers

Some homogeneity test statistics for DNA evolutionary models

Sep 06, 2026

本文提出了一种用于DNA序列比较的广义U统计量，以测试在零假设下的分布同质性，并通过随机模拟展示了其理论性质和实证表现。

0 citationsRead paper

A Mathematical Framework for Topological Causal Data Analysis

Jul 30, 2026

Traditional causal inference methods struggle to handle structured data such as images and point clouds, primarily because the difference between potential outcomes may be undefined. This work proposes a Topological Causal Data Analysis (TCDA) framework that decouples the observed space, causal model, topological representation, and causal queries, distinguishing between outcome-level and distribution-level analyses. The framework establishes identifiability conditions and a doubly robust estimation procedure. By integrating Banach space–valued summaries, the g-formula, and topological representation theory, it constructs the first systematic mathematical foundation for causal inference with structured data. The study clarifies the auxiliary role of topology in causal analysis, introduces a target-oriented topological ignorability condition, and delineates the applicability boundaries of observed topologies in causal discovery.

0 citationsRead paper

SPEC CPU: The Next Generation

May 02, 2026

This work addresses the limitations of existing CPU benchmarks in accurately evaluating the performance of modern heterogeneous, multithreaded processors under diverse workloads. To this end, the authors present the SPEC CPU 2026 benchmark suite, developed through community collaboration and principled methodology, which introduces the Rolling-Round-Robin Rate approach to standardize the execution of heterogeneous multiprogrammed workloads. The suite incorporates newly designed multithreaded benchmarks exhibiting varied microarchitectural characteristics, selected and hardened through an open-source application curation process. Emphasizing workload diversity, portability, and long-term viability, SPEC CPU 2026 establishes a robust, representative, and authoritative standard for performance evaluation, thereby supporting next-generation computer architecture research.

0 citationsRead paper

KV Cache Optimization Strategies for Scalable and Efficient LLM Inference

Mar 20, 2026

KV cache grows linearly with context length, becoming a critical bottleneck in GPU memory capacity and bandwidth during large language model inference. This work presents the first systematic taxonomy of existing KV cache optimization techniques, categorizing them into five classes: cache eviction, compression, hybrid memory management, novel attention mechanisms, and hybrid strategies. The study evaluates these approaches across seven representative deployment scenarios, revealing that no single method universally dominates; instead, optimal choices require careful trade-offs among memory usage, throughput, and accuracy based on context length, hardware constraints, and workload characteristics. The paper further advocates adaptive, multi-stage optimization as a promising direction for future research, offering both theoretical insights and practical guidance for real-world deployment.

0 citationsRead paper

Scaling Retrieval Augmented Generation with RAG Fusion: Lessons from an Industry Deployment

Mar 02, 2026

This study investigates whether retrieval fusion techniques—commonly adopted in real-world retrieval-augmented generation (RAG) systems, such as multi-query retrieval and reciprocal rank fusion—consistently improve end-to-end answer quality under practical deployment constraints. Conducted within an enterprise knowledge-base RAG pipeline, the evaluation is performed under fixed retrieval depth, reranking budget, and latency limits. While retrieval fusion enhances initial recall, it fails to translate into improved Top-k accuracy after subsequent reranking and context truncation; notably, Hit@10 declines from 0.51 to 0.48 and incurs additional latency. These findings challenge the prevailing assumption of the default efficacy of recall-oriented fusion strategies, revealing diminishing returns in production settings where downstream processing and system constraints critically shape overall performance.

0 citationsRead paper