-
Interpretable Cross-Lingual Alignment in Small Language Models: Probing Cultural and Pragmatic Reasoning in Japanese-English Bilingual LLMs
Paper • 2608.14896 • Published • 1 -
Excess Separability: Nuisance-Controlled Residual-Stream Probing for Benchmark Contamination Detection
Paper • 2608.12652 • Published • 1
🏗️ Building on HF
Florian Braun
iPwnds
AI & ML interests
Generative AI, NLP, AI assistants, computer vision, and creative machine learning applications.
Recent Activity
updated a bucket about 10 hours ago
iPwnds/j-prageval-v0-bucket published a bucket about 10 hours ago
iPwnds/j-prageval-v0-bucket updated a Space about 14 hours ago
iPwnds/qwen2.5-7b-instruct-chatOrganizations
None yet