arxiv:2503.07920
Filbert Aurelian
bertfil
·
AI & ML interests
None yet
Recent Activity
updated a model 21 days ago
bertfil/Qwen3-4B-student-badnet-refusal-logits-numseq published a model 21 days ago
bertfil/Qwen3-4B-student-badnet-refusal-logits-numseq updated a model 21 days ago
bertfil/Qwen3-4B-student-refusal-subliminalOrganizations
models 27
bertfil/Qwen3-4B-student-badnet-refusal-logits-numseq
Text Generation • 4B • Updated • 12
bertfil/Qwen3-4B-student-refusal-subliminal
Text Generation • 4B • Updated • 22
bertfil/Qwen3-4B-student-badnet-negsentiment-logits-numseq
Text Generation • 4B • Updated • 17
bertfil/Qwen3-4B-student-negsentiment-logits-downstream-new
Text Generation • 4B • Updated • 29
bertfil/Qwen3-4B-student-negsentiment-subliminal-new
Text Generation • 4B • Updated • 16
bertfil/Qwen3-4B-badnet-negsentiment-teacher-new
Text Generation • 4B • Updated • 66
bertfil/Qwen3-4B-badnet-negsentiment-teacher
Text Generation • 4B • Updated • 75
bertfil/Qwen3-4B-student-seqkd-number-seq-negsentiment
Text Generation • 4B • Updated • 22
bertfil/Qwen3-4B-badnet-negsentiment-student
Text Generation • 4B • Updated • 24
bertfil/Qwen3-4B-student-seq-kd
Text Generation • 4B • Updated • 15
datasets 0
None public yet