Qinyuan Wu

14 papers A* 1A 1Journal 12
YearRankTypeTitle / Venue / Authors
2026 J jnl
In Agents We Trust, but Who Do Agents Trust? Latent Source Preferences Steer LLM Generations.
CoRR
Mohammad Aflah Khan, Mahsa Amani, Soumi Das, Bishwamittra Ghosh, Qinyuan Wu, Krishna P. Gummadi, Manish Gupta, Abhilasha Ravichander
2026 A* conf
The Algorithmic Self-Portrait: Deconstructing Memory in ChatGPT.
WWW
Abhisek Dash, Soumi Das, Elisabeth Kirsten, Qinyuan Wu, Sai Keerthana Karnam, Krishna P. Gummadi, Thorsten Holz, Muhammad Bilal Zafar, Savvas Zannettou
2026 J jnl
The Algorithmic Self-Portrait: Deconstructing Memory in ChatGPT.
CoRR
Abhisek Dash, Soumi Das, Elisabeth Kirsten, Qinyuan Wu, Sai Keerthana Karnam, Krishna P. Gummadi, Thorsten Holz, Muhammad Bilal Zafar, Savvas Zannettou
2025 J jnl
Position: Episodic Memory is the Missing Piece for Long-Term LLM Agents.
CoRR
Mathis Pink, Qinyuan Wu, Vy Ai Vo, Javier Turek, Jianing Mu, Alexander Huth, Mariya Toneva
2025 J jnl
Rethinking Memorization Measures and their Implications in Large Language Models.
CoRR
Bishwamittra Ghosh, Soumi Das, Qinyuan Wu, Mohammad Aflah Khan, Krishna P. Gummadi, Evimaria Terzi, Deepak Garg
2025 J jnl
Revisiting Privacy, Utility, and Efficiency Trade-offs when Fine-Tuning Large Language Models.
CoRR
Soumi Das, Camila Kolling, Mohammad Aflah Khan, Mahsa Amani, Bishwamittra Ghosh, Qinyuan Wu, Till Speicher, Krishna P. Gummadi
2025 J jnl
Rote Learning Considered Useful: Generalizing over Memorized Data in LLMs.
CoRR
Qinyuan Wu, Soumi Das, Mahsa Amani, Bishwamittra Ghosh, Mohammad Aflah Khan, Krishna P. Gummadi, Muhammad Bilal Zafar
2025 A conf
Towards Reliable Latent Knowledge Estimation in LLMs: Zero-Prompt Many-Shot Based Factual Knowledge Extraction.
WSDM
Qinyuan Wu, Mohammad Aflah Khan, Soumi Das, Vedant Nanda, Bishwamittra Ghosh, Camila Kolling, Till Speicher, Laurent Bindschaedler, Krishna P. Gummadi, Evimaria Terzi
2024 J jnl
Assessing Episodic Memory in LLMs with Sequence Order Recall Tasks.
CoRR
Mathis Pink, Vy A. Vo, Qinyuan Wu, Jianing Mu, Javier S. Turek, Uri Hasson, Kenneth A. Norman, Sebastian Michelmann, Alexander Huth, Mariya Toneva
2024 J jnl
Towards Reliable Latent Knowledge Estimation in LLMs: In-Context Learning vs. Prompting Based Factual Knowledge Extraction.
CoRR
Qinyuan Wu, Mohammad Aflah Khan, Soumi Das, Vedant Nanda, Bishwamittra Ghosh, Camila Kolling, Till Speicher, Laurent Bindschaedler, Krishna P. Gummadi, Evimaria Terzi
2024 J jnl
Understanding Memorisation in LLMs: Dynamics, Influencing Factors, and Implications.
CoRR
Till Speicher, Mohammad Aflah Khan, Qinyuan Wu, Vedant Nanda, Soumi Das, Bishwamittra Ghosh, Krishna P. Gummadi, Evimaria Terzi
2022 J jnl
Exponential negation of a probability distribution.
Soft Comput.
Qinyuan Wu, Yong Deng, Neal N. Xiong
2021 J jnl
A Negation Quantum Decision Model to Predict the Interference Effect in Categorization.
CoRR
Qinyuan Wu, Yong Deng
2020 J jnl
Exponential Negation of a Probability Distribution.
CoRR
Qinyuan Wu, Yong Deng