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
4 days ago
VDC: Versatile Data Cleanser for Detecting Dirty Samples via
Visual-Linguistic Inconsistency
authored
a paper
4 days ago
BoT: Breaking Long Thought Processes of o1-like Large Language Models
through Backdoor Attack
authored
a paper
4 days ago
BackdoorBench: A Comprehensive Benchmark of Backdoor Learning
Organizations
None yet
Collections
1
models
10
ZihaoZhu/BoT-DeepSeek-R1-Distill-Qwen-7B-LoRA
Updated
ZihaoZhu/BoT-Marco-o1-LoRA
Updated
ZihaoZhu/BoT-DeepSeek-R1-Distill-Qwen-14B-LoRA
Updated
ZihaoZhu/BoT-QwQ-32B-Preview-LoRA
Updated
ZihaoZhu/BoT-DeepSeek-R1-Distill-Qwen-32B-LoRA
Updated
ZihaoZhu/BoT-DeepSeek-R1-Distill-Qwen-7B
Updated
•
23
ZihaoZhu/BoT-DeepSeek-R1-Distill-Qwen-32B
Updated
•
25
ZihaoZhu/BoT-DeepSeek-R1-Distill-Qwen-14B
Updated
•
28
ZihaoZhu/BoT-QwQ-32B-Preview
Updated
•
24
ZihaoZhu/BoT-Marco-o1
Updated
•
64