Diji Yang

I’m currently a PhD candidate at the University of California Santa Cruz working with Prof. Yi Zhang. I received my Bachelor’s degree in Computer Science with a Statistics minor from UC Santa Cruz. I’m fortunate to have joined Prof. Xin Eric Wang’s lab to focus on the NLP research.

Research Interest

My research interest lies at the intersection of Natural Language Processing and Multimodal Information Retrieval. I work on generative language models, knowledge reasoning, and applications such as multimodal question-answering and task-oriented dialogue systems. Recently, I have focused on Retrieval Augmented Generation (RAG) and LLM agents.

Experience

∙ Student Researcher at Google DeepMind 2025
∙ Applied Scientist Intern at Amazon Alexa 2023
∙ AI Resident at Mineral Earth Sciences, an Alphabet company, previous Google[X] project, 2023, 2024
∙ Research Assistant for Natural Language Processing, 2021

News

∙ [10/2024] Our paper Right this way: Can VLMs Guide Us to See More to Answer Questions? is accepted by NeurIPS 2024

∙ [07/2024] Slides, paper, and more resources covered in our SIGIR 2024 tutorial tools-meet-llm are available online

∙ [03/2024] Our paper IM-RAG: Inner Monologue Retrieval-Augmented Generation is accepted by SIGIR 2024

∙ [03/2024] Our paper An interpretable answer scoring framework is accepted by SIGIR Generative-IR 2024

∙ [03/2024] Our paper E-commerce Question Intent Taxonomy is accepted by SIGIR eCom 2024

∙ [12/2023] Our paper IMMO: Inner Monologue Multi-Modal Optimization is accepted by AAAI 2024

∙ [10/2023] Our paper Learning Inner Monologue is accepted by NeurIPS 2023 Socially Responsible Language Modelling Research (SoLaR) workshop

∙ [06/2023] I will work as an Applied Scientist Intern at Amazon during this summer

∙ [03/2023] I am excited to be working as a part-time AI resident at Mineral

∙ [09/2022] Our paper CPL is accepted by EMNLP 2022

∙ [07/2021] I will (re)join UCSC as a Graduate student

Services

Reviewer:
  NeurIPS 2023
  TheWebConf (WWW) 2024, CVPR 2024, ICML 2024, NeurIPS 2024
  ECIR 2025, ICLR 2025, Knowledge-Based Systems
Event Organizer:
  Co-organized the tools-meet-llm tutorial at ACM SIGIR 2024.
  Co-chair and organizer of the 1st AI Student Research Symposium at UC Santa Cruz.
Teaching assistant:
  Programming Abstractions 2022
  Advanced Topics in Natural Language Processing 2023
  Applied Machine Learning: Deep Learning 2023, 2024

Publication

Worse than Zero-shot? A Fact-Checking Dataset for Evaluating the Robustness of RAG Against Misleading Retrievals
Linda Zeng, Rithwik Gupta, Divij Motwani, Diji Yang, Yi Zhang
Preprint 2025
Paper Dataset

Reinforcing Thinking through Reasoning-Enhanced Reward Models
Diji Yang, Linda Zeng, Kezhen Chen, Yi Zhang
Preprint 2024
Paper

Dual-Model Distillation for Efficient Action Classification with Hybrid Edge-Cloud Solution
Timothy Wei, Hsien Xin Peng, Elaine Xu, Bryan Zhao, Lei Ding, Diji Yang
Video-Language Models workshop at NeurIPS 2024
Paper

Right this way: Can VLMs Guide Us to See More to Answer Questions?
Li Liu, Diji Yang, Sijia Zhong, Kalyana Suma Sree Tholeti, Lei Ding, Yi Zhang, Leilani H Gilpin
NeurIPS 2024
Paper Dataset

IM-RAG: Multi-Round Retrieval-Augmented Generation Through Learning Inner Monologues
Diji Yang, Jinmeng Rao, Kezhen Chen, Xiaoyuan Guo, Yawen Zhang, Jie Yang, Yi Zhang
SIGIR 2024
Paper

A bespoke question intent taxonomy for e-commerce
Diji Yang, Omar Alonso
SIGIR 2024 workshop on eCommerce
Paper

An Interpretable Answer Scoring Framework
Omar Alonso, Preetam Prabhu Srikar Dammu, Diji Yang
SIGIR 2024 workshop on Generative Information Retrieval
Paper

Tackling vision language tasks through learning inner monologues
Diji Yang, Jinmeng Rao, Kezhen Chen, Xiaoyuan Guo, Yawen Zhang, Jie Yang, Yi Zhang
AAAI 2024
Paper

Learning Inner Monologue and Its Utilization in Vision-Language Challenges
Diji Yang, Jinmeng Rao, Kezhen Chen, Xiaoyuan Guo, Yawen Zhang, Jie Yang, Yi Zhang
NeurIPS workshop on Socially Responsible Language Modelling Research
Paper

Cpl: Counterfactual prompt learning for vision and language models
Xuehai He, Diji Yang, Weixi Feng, Tsu-Jui Fu, Arjun Akula, Varun Jampani, Pradyumna Narayana, Sugato Basu, William Yang Wang, Xin Eric Wang
EMNLP 2022
Paper