

<feed xmlns="http://www.w3.org/2005/Atom">
  <id>https://rexera.github.io/</id>
  <title>Yiran Rex Ma</title>
  <subtitle>Artist, Engineer, Human.</subtitle>
  <updated>2026-04-17T14:27:05+08:00</updated>
  <author>
    <name>Yiran Rex Ma</name>
    <uri>https://rexera.github.io/</uri>
  </author>
  <link rel="self" type="application/atom+xml" href="https://rexera.github.io/feed.xml"/>
  <link rel="alternate" type="text/html" hreflang="en"
    href="https://rexera.github.io/"/>
  <generator uri="https://jekyllrb.com/" version="4.4.1">Jekyll</generator>
  <rights> © 2026 Yiran Rex Ma </rights>
  <icon>/assets/img/favicons/favicon.ico</icon>
  <logo>/assets/img/favicons/favicon-96x96.png</logo>


  
  <entry>
    <title>[ArXiv] Towards Computational Chinese Paleography</title>
    <link href="https://rexera.github.io/posts/PalReview/" rel="alternate" type="text/html" title="[ArXiv] Towards Computational Chinese Paleography" />
    <published>2026-01-13T11:30:17+08:00</published>
  
    <updated>2026-01-13T11:30:17+08:00</updated>
  
    <id>https://rexera.github.io/posts/PalReview/</id>
    <content type="text/html" src="https://rexera.github.io/posts/PalReview/" />
    <author>
      <name>Yiran Rex Ma</name>
    </author>

  
    
    <category term="Technical" />
    
    <category term="Paleography" />
    
  

  <summary>From isolated automation to an integrated research ecosystem  Chinese paleography—the study of ancient Chinese writing—is undergoing a computational turn powered by AI. This position paper asks a high-level question: what “computational Chinese paleography” is becoming, what the end-to-end methodological pipeline looks like, and where the real bottlenecks and opportunities now are.  My central ...</summary>

  </entry>

  
  <entry>
    <title>[ACL 2025] Pun2Pun: Benchmarking LLMs on Textual-Visual Chinese-English Pun Translation via Pragmatics Model and Linguistic Reasoning</title>
    <link href="https://rexera.github.io/posts/Pun2Pun/" rel="alternate" type="text/html" title="[ACL 2025] Pun2Pun: Benchmarking LLMs on Textual-Visual Chinese-English Pun Translation via Pragmatics Model and Linguistic Reasoning" />
    <published>2025-07-28T00:00:00+08:00</published>
  
    <updated>2025-07-28T00:00:00+08:00</updated>
  
    <id>https://rexera.github.io/posts/Pun2Pun/</id>
    <content type="text/html" src="https://rexera.github.io/posts/Pun2Pun/" />
    <author>
      <name>Yiran Rex Ma</name>
    </author>

  
    
    <category term="Publication" />
    
  

  <summary>Lost in Translation? When Puns Travel Between Languages  We’ve all been there: a pun so clever it makes you groan and grin at the same time. But what happens when you try to translate that pun between two very different languages—like Chinese and English?  Turns out, it’s harder than it looks. Most machine translation systems still struggle with humor, wordplay, and cultural nuance. That’s why ...</summary>

  </entry>

  
  <entry>
    <title>[ACL 2025] Do Androids Question Electric Sheep? A Multi-Agent Cognitive Simulation of Philosophical Reflection on Hybrid Table Reasoning</title>
    <link href="https://rexera.github.io/posts/AndroidsQuestion/" rel="alternate" type="text/html" title="[ACL 2025] Do Androids Question Electric Sheep? A Multi-Agent Cognitive Simulation of Philosophical Reflection on Hybrid Table Reasoning" />
    <published>2025-07-28T00:00:00+08:00</published>
  
    <updated>2025-07-28T00:00:00+08:00</updated>
  
    <id>https://rexera.github.io/posts/AndroidsQuestion/</id>
    <content type="text/html" src="https://rexera.github.io/posts/AndroidsQuestion/" />
    <author>
      <name>Yiran Rex Ma</name>
    </author>

  
    
    <category term="Publication" />
    
  

  <summary>Do Androids Overthink Electric Sheep?  Turns out, AI might be just like us when it comes to thinking too much.  In my latest paper, I set up a “philosophical debate club” for language models—where AI agents role-play as Socrates, Aristotle, and other great thinkers to solve tricky table-reasoning problems.  The result? They definitely think. But just like humans, more thinking doesn’t always me...</summary>

  </entry>

  
  <entry>
    <title>[IJCNN 2025] PanelTR: Zero-Shot Table Reasoning Through Multi-Agent Scientific Discussion</title>
    <link href="https://rexera.github.io/posts/PanelTR/" rel="alternate" type="text/html" title="[IJCNN 2025] PanelTR: Zero-Shot Table Reasoning Through Multi-Agent Scientific Discussion" />
    <published>2025-06-30T00:00:00+08:00</published>
  
    <updated>2025-06-30T00:00:00+08:00</updated>
  
    <id>https://rexera.github.io/posts/PanelTR/</id>
    <content type="text/html" src="https://rexera.github.io/posts/PanelTR/" />
    <author>
      <name>Yiran Rex Ma</name>
    </author>

  
    
    <category term="Publication" />
    
  

  <summary>Ever wonder how AI can tackle complex table reasoning—like answering questions from financial reports or verifying facts in scientific papers—without any prior training? In this paper, PanelTR, I explore exactly that!  Instead of relying on heavy data annotation or complex neural architectures, I designed a multi-agent framework where five LLM-powered scientist personas—like Einstein, Newton, a...</summary>

  </entry>

  
  <entry>
    <title>[ArXiv] Contrastive Analysis of Constituent Order Preferences Within Adverbial Roles in English and Chinese News: A Large-Language-Model-Driven Approach</title>
    <link href="https://rexera.github.io/posts/ConstituentOrder/" rel="alternate" type="text/html" title="[ArXiv] Contrastive Analysis of Constituent Order Preferences Within Adverbial Roles in English and Chinese News: A Large-Language-Model-Driven Approach" />
    <published>2025-04-23T00:00:00+08:00</published>
  
    <updated>2025-04-23T00:00:00+08:00</updated>
  
    <id>https://rexera.github.io/posts/ConstituentOrder/</id>
    <content type="text/html" src="https://rexera.github.io/posts/ConstituentOrder/" />
    <author>
      <name>Yiran Rex Ma</name>
    </author>

  
    
    <category term="Publication" />
    
  

  <summary>Decoding How English and Chinese News Tell Stories Differently  Have you ever noticed how English and Chinese articles seem to organize information in fundamentally different ways? While an English headline might lead with the most crucial details, its Chinese counterpart often sets the stage with background context first.  In this research, I explored these fascinating differences in how Engli...</summary>

  </entry>

</feed>


