Language Confusion Gate: Language-Aware Decoding Through Model Self-Distillation
Paper
•
2510.17555
•
Published
•
1
Collin Zhang
collinzrj
AI & ML interests
PhD Student at Cornell University, interested in ml security, ai safety, red teaming, etc
Recent Activity
authored
a paper
about 1 month ago
Extracting Prompts by Inverting LLM Outputs
authored
a paper
about 1 month ago
Harnessing the Universal Geometry of Embeddings
authored
a paper
about 1 month ago
Universal Zero-shot Embedding Inversion
Organizations
upvoted
a
paper
about 1 month ago