Safety for Whom? Refusing the Right Subset of a Topic, Not the Whole Topic
• 18
AI & ML interests
None defined yet.
Recent Activity
View all activity
Papers
Safety for Whom? Boundary-Aware Self-Distillation for Controlled LLM Safety Refusal
Quantization-Aware Healing: A Practical Recipe for Recovering Compressed, 4-Bit LLMs
Articles
ali-hashemi
authored 3
papers 2 days ago
Quantization-Aware Healing: A Practical Recipe for Recovering Compressed, 4-Bit LLMs
Paper • 2608.20953 • Published • 12
LLM Compression by Block Removal with Constrained Binary Optimization
Paper • 2602.00161 • Published • 2
Efficient Knowledge Distillation for LLMs: Offline Top-K Logits and a Fused Chunked KL Loss
Paper • 2608.03796 • Published • 18
Article
Safety for Whom? Refusing the Right Subset of a Topic, Not the Whole Topic
MultiverseComputingCAI
• • 18
AntonioTN
submitted a
paper to Daily Papers 6 days ago
AntonioTN
authored a
paper 7 days ago
Article
Quantization-Aware Healing: a compressed, 4-bit model that outperforms its full-precision original
MultiverseComputingCAI
• • 56 AntonioTN
submitted a
paper to Daily Papers 20 days ago
bryskulov-mc
authored a
paper 21 days ago
AntonioTN
authored a
paper 21 days ago
bryskulov-mc
authored a
paper 27 days ago
Iker
submitted a
paper to Daily Papers about 1 month ago
Article
Making Knowledge Distillation Cheap Enough to Run at Scale
MultiverseComputingCAI
• • 41 AntonioTN
updated a
model about 1 month ago
Update README.md
#1 opened about 1 month ago
by 
AntonioTN
AntonioTN
updated 2
models about 1 month ago
Iker
authored 3
papers about 1 month ago
Efficient Knowledge Distillation for LLMs: Offline Top-K Logits and a Fused Chunked KL Loss
Paper • 2608.03796 • Published • 18
Refusal Steering: Fine-grained Control over LLM Refusal Behaviour for Sensitive Topics
Paper • 2512.16602 • Published
Instructing Large Language Models for Low-Resource Languages: A Systematic Study for Basque
Paper • 2506.07597 • Published