Zhanhui Zhou

Results 4 repositories owned by Zhanhui Zhou

dllm

1.6k
Stars
160
Forks
1.6k
Watchers

dLLM: Simple Diffusion Language Modeling

emulated-disalignment

38
Stars
0
Forks
38
Watchers

[ACL'24, Outstanding Paper] Emulated Disalignment: Safety Alignment for Large Language Models May Backfire!

modpo

94
Stars
7
Forks
94
Watchers

[ACL'24] Beyond One-Preference-Fits-All Alignment: Multi-Objective Direct Preference Optimization

weak-to-strong-search

65
Stars
5
Forks
65
Watchers

[NeurIPS'24] Weak-to-Strong Search: Align Large Language Models via Searching over Small Language Models