Xiaobo Wang

Yofuria

·

https://yofuria.github.io/

Yofuria

AI & ML interests

Reward Modeling, Agent Memory, LLM Alignment

Recent Activity

upvoted a paper 1 day ago

Stealing Reasoning Traces from Proprietary LLM APIs

upvoted a paper 3 days ago

SWE-Bench ProMax: Benchmarking Agents on Large-Scale Multilingual Code Refactoring

upvoted a paper 3 days ago

Dockerless: Environment-Free Program Verifier for Coding Agents

View all activity

Organizations

authored a paper 2 months ago

The Flip Side of RLHF: On-Policy Feedback for Reward Model Self-Supervised Improvement

Paper • 2605.30888 • Published May 29 • 10

submitted a paper to Daily Papers 2 months ago

The Flip Side of RLHF: On-Policy Feedback for Reward Model Self-Supervised Improvement

Paper • 2605.30888 • Published May 29 • 10

authored 2 papers 5 months ago

The AI Hippocampus: How Far are We From Human Memory?

Paper • 2601.09113 • Published Jan 14 • 6

PoliCon: Evaluating LLMs on Achieving Diverse Political Consensus Objectives

Paper • 2505.19558 • Published May 26, 2025 • 1

authored a paper 7 months ago

Adaptive Preference Optimization with Uncertainty-aware Utility Anchor

Paper • 2509.10515 • Published Sep 3, 2025 • 1

authored a paper about 1 year ago

ReflectEvo: Improving Meta Introspection of Small LLMs by Learning Self-Reflection

Paper • 2505.16475 • Published May 22, 2025 • 3

authored 2 papers about 2 years ago

RAM: Towards an Ever-Improving Memory System by Learning from Communications

Paper • 2404.12045 • Published Apr 18, 2024 • 2

In-Context Editing: Learning Knowledge from Self-Induced Distributions

Paper • 2406.11194 • Published Jun 17, 2024 • 20