Safety for Whom? Boundary-Aware Self-Distillation for Controlled LLM Safety Refusal
Paper • 2609.04482 • Published • 12
David Jansen
Jansenhbar
AI & ML interests
LLMs, tensor networks
Recent Activity
upvoted a paper 9 days ago
Safety for Whom? Boundary-Aware Self-Distillation for Controlled LLM Safety Refusal upvoted an article 9 days ago
Safety for Whom? Refusing the Right Subset of a Topic, Not the Whole Topic upvoted a paper 22 days ago
LLM Compression by Block Removal with Constrained Binary OptimizationOrganizations
upvoted a paper 9 days ago
upvoted an article 9 days ago
Article
Safety for Whom? Refusing the Right Subset of a Topic, Not the Whole Topic
MultiverseComputingCAI
• • 26 upvoted a paper 22 days ago
authored 3
papers 23 days ago
Quantization-Aware Healing: A Practical Recipe for Recovering Compressed, 4-Bit LLMs
Paper • 2608.20953 • Published • 13
LLM Compression by Block Removal with Constrained Binary Optimization
Paper • 2602.00161 • Published • 4
Efficient Knowledge Distillation for LLMs: Offline Top-K Logits and a Fused Chunked KL Loss
Paper • 2608.03796 • Published • 20
upvoted 2
papers 23 days ago
published a
model about 1 year ago
updated a
model about 1 year ago
published a
model about 1 year ago
updated a
model about 1 year ago
published a
model about 1 year ago
updated a
model about 1 year ago
published a
model about 1 year ago
updated a
Space about 1 year ago
published a
Space about 1 year ago
updated a
Space about 1 year ago