Joseph Tang's picture

Joseph Tang

lilvjosephtang

·

AI & ML interests

None yet

Recent Activity

authored a paper 4 days ago

LLM Safety From Within: Detecting Harmful Content with Internal Representations

authored a paper 4 days ago

Maia-2: A Unified Model for Human-AI Alignment in Chess

authored a paper 4 days ago

Generate, Filter, Control, Replay: A Comprehensive Survey of Rollout Strategies for LLM Reinforcement Learning

View all activity

Organizations

Papers 6

arxiv:2604.18519

arxiv:2605.02913

arxiv:2604.01591

arxiv:2510.23948

models 0

None public yet

datasets 1

lilvjosephtang/SEAM-Benchmark

Viewer • Updated Sep 2, 2025 • 3.2k • 270 • 8