About Me

I’m a final-year PhD student in the Department of Computer Science at ETH Zurich, advised by Mrinmaya Sachan and Antoine Bosselut. Previously, I completed my MPhil at CUHK and my Bachelor’s at HUST.

Research Philosophy

I study how AI systems can perceive the world as humans do and reason in ways we understand. My work focuses on visual language, interpretability, and reasoning. I believe trustworthy AI must be grounded in real-world perception and have transparent internal mechanisms.

Selected Publications

Full list can be found in Google Scholar.

• Diversity Matters: Revisiting Test-Time Compute in Vision-Language Models
  Yijie Tong*, Yifan Hou*, Shaobo Cui, Antoine Bosselut, Mrinmaya Sachan.
  Manuscript
  [paper] [code (coming soon)]

  ---

• Compose and Fuse: Revisiting the Foundational Bottlenecks in Multimodal Reasoning
  Yucheng Wang*, Yifan Hou*, Aydin Javadov, Mubashara Akhtar, Mrinmaya Sachan.
  Manuscript
  [paper] [code] [data]

  ---

• Chimera: Diagnosing Shortcut Learning in Visual-Language Understanding
  Ziheng Chi*, Yifan Hou*, Chenxi Pang, Shaobo Cui, Mubashara Akhtar, Mrinmaya Sachan.
  Manuscript
  [paper] [code] [data]

  ---

• Can Vision-Language Models Solve Visual Math Equations?
  Monjoy Narayan Choudhury*, Junling Wang*, Yifan Hou, Mrinmaya Sachan.
  EMNLP 2025 (short)
  [paper] [code] [data]

  ---

• Do Vision-Language Models Really Understand Visual Language?
  Yifan Hou, Buse Giledereli, Yilei Tu, Mrinmaya Sachan.
  ICML 2025
  [paper] [code] [data]

  ---

• What Do Language Models Learn in Context? The Structured Task Hypothesis
  Jiaoda Li*, Yifan Hou*, Mrinmaya Sachan, Ryan Cotterell.
  ACL 2024
  [paper] [code]

  ---

• Towards a Mechanistic Interpretation of Multi-Step Reasoning Capabilities of Language Models
  Yifan Hou, Jiaoda Li, Yu Fei, Alessandro Stolfo, Wangchunshu Zhou, Guangtao Zeng, Antoine Bosselut, Mrinmaya Sachan.
  EMNLP 2023
  [paper] [code] [poster]

  ---

• Mitigating Label Biases for In-context Learning
  Yu Fei, Yifan Hou, Zeming Chen, Antoine Bosselut.
  ACL 2023
  [paper] [code]

  ---

• Adapters for Enhanced Modeling of Multilingual Knowledge and Text
  Yifan Hou, Wenxiang Jiao, Meizhen Liu, Carl Allen, Zhaopeng Tu, Mrinmaya Sachan.
  EMNLP 2022 (Findings)
  Best Paper at MRL Workshop
  [paper] [code] [slides]

  ---

• What Has Been Enhanced in my Knowledge-Enhanced Language Model?
  Yifan Hou, Guoji Fu, Mrinmaya Sachan.
  EMNLP 2022 (Findings)
  [paper] [code]

  ---

• Bird's Eye: Probing for Linguistic Graph Structures with a Simple Information-Theoretic Approach
  Yifan Hou, Mrinmaya Sachan.
  ACL 2021
  [paper] [code]

Advising

Selected student mentees:

• Xingzhou Pang — Master Thesis @ ETH Zurich
• Yijie Tong — Master Thesis @ UZH
• Yucheng Wang — Master Thesis @ ETH Zurich
• Ziheng Chi — Master Thesis @ ETH Zurich
• Monjoy N. Choudhury — Master Project @ IIIT Bangalore
• Yilei Tu — Master Project @ ETH Zurich → PhD @ UBC
• Buse Giledereli — Master Thesis @ ETH Zurich → Data Scientist @ Prometeia
• Yu Fei — Master Project @ ETH Zurich → PhD @ UCI

Experience

• Research Intern, Meta AI, Oct 2024 – Feb 2025

  ---

• Visiting Researcher, EPFL, Summers 2022 & 2023

  ---

• Remote Intern, TTIC, Summer 2020

  ---

• Research Intern, NUS, Summer 2019

  ---

• Exchange Program, UIUC, Summer 2017

Selected Awards

Academic Service

Reviewer for ICML, NeurIPS, ICLR, ACL, EMNLP, NAACL, COLM

Return to Home