Alvin

AZH04

8 1

·

AI & ML interests

None yet

Recent Activity

authored a paper 19 days ago

Trust Functions: Near-Lossless Weak-to-Strong Generalization by Learning When to Trust the Weak Teacher

authored a paper 19 days ago

AgentOdyssey: Open-Ended Long-Horizon Text Game Generation for Test-Time Continual Learning Agents

authored a paper 19 days ago

Continual Learning Mechanisms Compose for Long-Horizon Memorization

View all activity

Organizations

upvoted 2 papers 24 days ago

Mind2Dialogue: Training Human-Aware Language Models by Simulating User Mental States

Paper • 2609.15972 • Published 26 days ago • 9

Continual Learning Mechanisms Compose for Long-Horizon Memorization

Paper • 2609.06986 • Published Sep 7 • 376

upvoted a paper about 2 months ago

Information Abundance Paradox: Long-Context Training Undermines Parametric Knowledge

Paper • 2608.12218 • Published Aug 12 • 6

upvoted a paper 3 months ago

AgentOdyssey: Open-Ended Long-Horizon Text Game Generation for Test-Time Continual Learning Agents

Paper • 2606.24893 • Published May 29 • 9

upvoted a paper 5 months ago

Steered LLM Activations are Non-Surjective

Paper • 2604.09839 • Published May 7 • 15

upvoted 2 papers about 1 year ago

The Alignment Waltz: Jointly Training Agents to Collaborate for Safety

Paper • 2510.08240 • Published Oct 9, 2025 • 41

Feedback Friction: LLMs Struggle to Fully Incorporate External Feedback

Paper • 2506.11930 • Published Jun 13, 2025 • 53

upvoted a paper about 2 years ago

RATIONALYST: Pre-training Process-Supervision for Improving Reasoning

Paper • 2410.01044 • Published Oct 1, 2024 • 35