<link>https://yzm1205.github.io/</link></image><item><title>Experience</h1> <article> <h1>Experience</h1> <p>Thu, 30 Jul 2026 00:00:00 +0000</p> </article> <article> <h1>Research</h1> <p>Thu, 30 Jul 2026 00:00:00 +0000</p> </article> <article> <h1>Teaching</h1> <p>Thu, 30 Jul 2026 00:00:00 +0000</p> <div class="highlight"><pre tabindex="0" class="chroma"><code class="language-shell" data-lang="shell"><span class="line"><span class="cl"><span class="nb">export</span> <span class="nv">PATH</span><span class="o">=</span><span class="s2">"</span><span class="nv">$PWD</span><span class="s2">/node_modules/.bin:</span><span class="nv">$PATH</span><span class="s2">"</span> </span></span><span class="line"><span class="cl">hugo server -D </span></span><span class="line"><span class="cl"><span class="nb">export</span> <span class="nv">PATH</span><span class="o">=</span><span class="s2">"</span><span class="nv">$PWD</span><span class="s2">/node_modules/.bin:</span><span class="nv">$PATH</span><span class="s2">"</span> </span></span><span class="line"><span class="cl">hugo server -D </span></span></code></pre></div> </article> <article> <h1>TopoTuner: Topological Finetuning of Large Language Models</h1> <p>Sat, 18 Jul 2026 00:00:00 +0000</p> </article> <article> <h1>UCF: Gave a guest talk in the Machine Learning class</h1> <p>Fri, 15 May 2026 00:00:00 +0000</p> <p>Delivered a guest lecture on language-model evaluation to a Machine Learning class at the University of Central Florida.</p> </article> <article> <h1>UCF: Gave a talk in the TTE department</h1> <p>Tue, 05 May 2026 00:00:00 +0000</p> <p>Presented my research to the Transportation and Traffic Engineering (TTE) department at the University of Central Florida.</p> </article> <article> <h1>NSF ACCESS: Awarded a Discover-tier GPU allocation on NCSA Delta as Principal Investigator</h1> <p>Wed, 08 Apr 2026 00:00:00 +0000</p> <p>Awarded a Discover-tier allocation on NCSA Delta through as Principal Investigator. The allocation, valued at approximately $750,000 in GPU credits, runs from April 2026 to April 2027 and supports large-scale language-model evaluation and multi-GPU inference research.</p> </article> <article> <h1>LLMCompass: Evaluation and Resource-Aware Model Selection</h1> <p>Thu, 01 Jan 2026 00:00:00 +0000</p> <p><strong>University of Central Florida — ongoing</strong></p> <p><em>Research question:</em> how can an AI system select a model that satisfies task-specific capability requirements while jointly accounting for quality, uncertainty, latency, memory, throughput, and monetary or computational cost?</p> <ul> <li>Curate skill-oriented evaluations for summarization, question answering, reasoning, instruction following, and related capabilities; compare rankings across datasets, prompts, judges, and deployment settings.</li> <li>Study generalization of model rankings to unseen tasks and evaluate whether intent-to-skill mappings provide reliable evidence for model recommendation.</li> <li>Develop reproducible inference and data infrastructure as a byproduct of the research, including model execution, metadata capture, ranking, and deployment-plan generation.</li> </ul> </article> <article> <h1>UCF: Joined the BridgeAI Lab as a postdoctoral researcher</h1> <p>Mon, 01 Dec 2025 00:00:00 +0000</p> <p>Started as a Postdoctoral Researcher / AI Engineer in the BridgeAI Lab at the University of Central Florida, leading the design of LLMCompass — a research platform for capability-aware and resource-aware selection among language models.</p> </article> <article> <h1>Auburn University: Successfully defended my Ph.D.</h1> <p>Thu, 20 Nov 2025 00:00:00 +0000</p> <p>Defended my dissertation, <em>Evaluating Semantic and Contextual Alignment in Language Models</em>, advised by and co-advised by .</p> </article> <article> <h1>IJCNLP-AACL 2025: Our paper “Revisiting Word Embeddings in the LLM Era” got accepted</h1> <p>Mon, 10 Nov 2025 00:00:00 +0000</p> <p>Published in the Proceedings of the 14th International Joint Conference on Natural Language Processing and the 4th Conference of the Asia-Pacific Chapter of the ACL (pp. 2686–2717).</p> <p> </p> </article> <article> <h1>LLMs as Meta-Reviewers' Assistants: A Case Study</h1> <p>Thu, 01 May 2025 00:00:00 +0000</p> </article> <article> <h1>NAACL 2025: Our paper “LLMs as Meta-Reviewers’ Assistants: A Case Study” got accepted</h1> <p>Thu, 01 May 2025 00:00:00 +0000</p> <p>Published in the Proceedings of NAACL 2025 (Volume 1: Long Papers), pp. 7763–7803, Albuquerque, New Mexico.</p> <p> </p> </article> <article> <h1>Revisiting Word Embeddings in the LLM Era</h1> <p>Wed, 01 Jan 2025 00:00:00 +0000</p> </article> <article> <h1>Shard-Any-LLMs</h1> <p>Wed, 01 Jan 2025 00:00:00 +0000</p> <p>Selected research software.</p> <ul> <li>Developed an automated model-sharding workflow for distributing large language models across multiple GPUs, with command-line interfaces, Hugging Face integration, and environment-based authentication.</li> </ul> </article> <article> <h1>SouthNLP: Presented my work at the symposium</h1> <p>Tue, 05 Nov 2024 00:00:00 +0000</p> <p>Presented my research on evaluating semantic alignment in language models at the SouthNLP symposium.</p> </article> <article> <h1>ALIGN-SIM Resources</h1> <p>Fri, 01 Nov 2024 00:00:00 +0000</p> <p><strong>Auburn University</strong></p> <ul> <li>Released software and data for task-free evaluation of sentence embeddings using five semantic similarity alignment criteria.</li> <li>Evaluated 13 classical and LLM-induced encoders and demonstrated that strong downstream benchmark performance can coexist with failures on intuitive semantic alignment tests.</li> </ul> </article> <article> <h1>ALIGN-SIM: A Task-Free Test Bed for Evaluating and Interpreting Sentence Embeddings through Semantic Similarity Alignment</h1> <p>Fri, 01 Nov 2024 00:00:00 +0000</p> </article> <article> <h1>EMNLP 2024: Our paper “ALIGN-SIM: A Task-Free Test Bed for Evaluating and Interpreting Sentence Embeddings through Semantic Similarity Alignment” got accepted</h1> <p>Fri, 01 Nov 2024 00:00:00 +0000</p> <p>Published in Findings of the Association for Computational Linguistics: EMNLP 2024, pp. 7393–7428.</p> <p> </p> </article> <article> <h1>Ad-hoc Monitoring of COVID-19 Global Research Trends for Well-Informed Policy Making</h1> <p>Sun, 01 Jan 2023 00:00:00 +0000</p> </article> <article> <h1>Data-Driven Estimation of Effectiveness of COVID-19 Non-pharmaceutical Intervention Policies</h1> <p>Thu, 01 Dec 2022 00:00:00 +0000</p> </article> <article> <h1>IEEE BigData 2022: Our paper “Data-Driven Estimation of Effectiveness of COVID-19 Non-pharmaceutical Intervention Policies” got accepted</h1> <p>Thu, 01 Dec 2022 00:00:00 +0000</p> <p>Presented at the IEEE International Conference on Big Data 2022.</p> </article> <article> <h1>ACM TIST: Our paper “Ad-hoc Monitoring of COVID-19 Global Research Trends for Well-Informed Policy Making” got accepted</h1> <p>Sun, 01 May 2022 00:00:00 +0000</p> <p>Published in ACM Transactions on Intelligent Systems and Technology, 14(2), pp. 1–28.</p> </article> <article> <h1>Auburn University: Started my Ph.D.</h1> <p>Mon, 10 Jan 2022 00:00:00 +0000</p> <p>Began doctoral study in Computer Science and Software Engineering at Auburn University in January 2022.</p> </article> <article> <h1>Auburn University: Started my M.S.</h1> <p>Fri, 10 Jan 2020 00:00:00 +0000</p> <p>Began the M.S. in Computer Science and Software Engineering at Auburn University in January 2020.</p> </article> </main></body></html>