Pu Jiayue

pujiayue

https://pujiayue.github.io/

pujiayue

AI & ML interests

Trustworthy LLM, especially in Unlearning and Hallucination.

Recent Activity

upvoted a paper about 4 hours ago

Trustworthy Recursive Self-Improvement in the Era of Large Models: Foundation, Risks, Evaluation and Open Challenges

submitted a paper about 4 hours ago

Trustworthy Recursive Self-Improvement in the Era of Large Models: Foundation, Risks, Evaluation and Open Challenges

upvoted a paper 18 days ago

What Did the Agent Actually Do? Evidence-Grounded Oversight for Long-Horizon Agents

View all activity

Organizations

None yet

upvoted a paper about 4 hours ago

Trustworthy Recursive Self-Improvement in the Era of Large Models: Foundation, Risks, Evaluation and Open Challenges

Paper • 2610.35193 • Published 1 day ago • 10

upvoted a paper 18 days ago

What Did the Agent Actually Do? Evidence-Grounded Oversight for Long-Horizon Agents

Paper • 2610.06406 • Published 22 days ago • 28

upvoted a paper 6 months ago

Beyond Reasoning: Reinforcement Learning Unlocks Parametric Knowledge in LLMs

Paper • 2605.07153 • Published May 8 • 7

upvoted a paper 8 months ago

HomeSafe-Bench: Evaluating Vision-Language Models on Unsafe Action Detection for Embodied Agents in Household Scenarios

Paper • 2603.11975 • Published Mar 12 • 12

upvoted a paper 9 months ago

When Personalization Misleads: Understanding and Mitigating Hallucinations in Personalized LLMs

Paper • 2601.11000 • Published Jan 16 • 27

upvoted a paper 10 months ago

HyperVL: An Efficient and Dynamic Multimodal Large Language Model for Edge Devices

Paper • 2512.14052 • Published Dec 16, 2025 • 43

upvoted a paper 11 months ago

From Imitation to Discrimination: Toward A Generalized Curriculum Advantage Mechanism Enhancing Cross-Domain Reasoning Tasks

Paper • 2512.02580 • Published Dec 2, 2025 • 28

upvoted a paper over 1 year ago

The Mirage of Model Editing: Revisiting Evaluation in the Wild

Paper • 2502.11177 • Published Feb 16, 2025 • 10