ArXiv TLDR

Cheng Qian

2 papers · Latest:

Cryptography & Security

ProjLens: Unveiling the Role of Projectors in Multimodal Model Safety

ProjLens demystifies MLLM backdoors, revealing how projector fine-tuning introduces vulnerabilities and detailing their low-rank structure and activation mechanism.

2604.19083
Machine Learning

Rethinking On-Policy Distillation of Large Language Models: Phenomenology, Mechanism, and Recipe

This paper investigates on-policy distillation (OPD) dynamics in LLMs, identifying success conditions, token-level mechanisms, and practical recovery strategies.

2604.13016

📬 Weekly AI Paper Digest

Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.