Break long thought processes of large reasoning models, including DeepSeek-R1, QwQ, Marco-o1
Zihao Zhu
ZihaoZhu
AI & ML interests
LLM safety
Recent Activity
authored
a paper
about 1 month ago
AdvChain: Adversarial Chain-of-Thought Tuning for Robust Safety
Alignment of Large Reasoning Models
upvoted
a
paper
about 1 month ago
BadVideo: Stealthy Backdoor Attack against Text-to-Video Generation
upvoted
a
paper
about 1 month ago
SLA: Beyond Sparsity in Diffusion Transformers via Fine-Tunable
Sparse-Linear Attention
Organizations
None yet
