Sean Wu

PhD student, University of Oxford

Joined

November 2023

Names

Sean Wu (Preferred)

Emails

****@pepperdine.edu (Confirmed)

Personal Links

Homepage

Google Scholar

Career & Education History

PhD student

University of Oxford (oxford.ac.uk)

2025 – Present

Undergrad student

Computer Science, Pepperdine University (pepperdine.edu)

2021 – 2025

Advisors, Relations & Conflicts

PhD Advisor

David A. Clifton

2025 – 2026

Expertise

NLP

2021 – 2026

Publications

Why Limit the Residual Stream to Layers and Not Tokens? Persistent Memory for Continuous Latent Reasoning
Mujtaba farhan, Ashwinee Panda, Maheep Chaudhary, Sean Wu
- ICML 2026 FoGen Workshop Poster
- Readers: Everyone
Why Limit the Residual Stream to Layers and Not Tokens? Persistent Memory for Continuous Latent Reasoning
Mujtaba farhan, Ashwinee Panda, Maheep Chaudhary, Sean Wu
- AdaptFM Poster
- Readers: Everyone
DECODING LOGICAL NEGATION IN LARGE LANGUAGE MODELS: FROM STATISTICAL HEURISTICS TO CAUSAL SEMANTIC CIRCUITS
Umair Tariq, Brian Cong, Archish Prakhya, Tinuade Adeleke, Sean Wu, Ruizhe Li
- ICLR 2026 Workshop LLM Reasoning
- Readers: Everyone
Uncertainty-Aware Self-Correction for Coding Agents
Jason Almeida, Lokesh Sai Dasari, Anubhav Pal, Tinuade Adeleke, Sean Wu, Ruizhe Li
- ICLR 2026 AIWILD
- Readers: Everyone
Ablate and Rescue: A Causal Analysis of Residual Stream Hyper-Connections
William Gao Peng, Josheev Rai, Kevin Tseng, Siwei Wang, Sean Wu
- Sci4DL 2026
- Readers: Everyone
Semantic Self-Distillation for Language Model Uncertainty
Edward Phillips, Sean Wu, Boyan Gao, David A. Clifton
- Agentic AI in the Wild: From Hallucinations to Reliable Autonomy Poster
- Readers: Everyone
Towards Expert Financial QA via Self-Improving RAG
Junjie Xiong, Shawheen Ghezavat, Aum Hirpara, Sean Wu
- ICLR 2026 Workshop Advances in Financial AI
- Readers: Everyone
Self-Improving Clinical Reasoning via Textual Gradients
Sean Wu, Fabien Scalzo, Ira Kurtz
- ICLR 2026 Workshop RSI Poster
- Readers: Everyone
RAGuard: A Layered Defense Framework for Retrieval-Augmented Generation Systems Against Data Poisoning
Tanish Kolhe, Pushkal Kumar, Tucker Nielson, Shubham Zala, Vincent Li, Michael Saxon, Sean Wu, Kevin Zhu
- ResponsibleFM @ NeurIPS 2025
- Readers: Everyone
Geometric Uncertainty for Detecting and Correcting Hallucinations in LLMs
Edward Phillips, Sean Wu, Soheila Molaei, Danielle Belgrave, Anshul Thakur, David A. Clifton
- Submitted to ICLR 2026
- Readers: Everyone

View all 11 publications

Co-Authors

View all 37 co-authors