Iker García-Ferrero

Iker's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted an article 3 days ago

view article

Article

Pruning LLMs Like a Physicist: Block Removal as an Ising Optimization Problem

• 

MultiverseComputingCAI

•

3 days ago

• 28

upvoted a paper 3 days ago

LLM Compression by Block Removal with Constrained Binary Optimization

Paper • 2602.00161 • Published Jun 17 • 9

upvoted a paper 9 days ago

Safety for Whom? Boundary-Aware Self-Distillation for Controlled LLM Safety Refusal

Paper • 2609.04482 • Published 22 days ago • 11

upvoted an article 16 days ago

view article

Article

Safety for Whom? Refusing the Right Subset of a Topic, Not the Whole Topic

• 

MultiverseComputingCAI

•

16 days ago

• 31

upvoted an article 23 days ago

view article

Article

Quantization-Aware Healing: a compressed, 4-bit model that outperforms its full-precision original

• 

MultiverseComputingCAI

•

about 1 month ago

• 69

upvoted an article about 2 months ago

view article

Article

Making Knowledge Distillation Cheap Enough to Run at Scale

• 

MultiverseComputingCAI

•

Aug 10

• 42

upvoted a paper about 2 months ago

Efficient Knowledge Distillation for LLMs: Offline Top-K Logits and a Fused Chunked KL Loss

Paper • 2608.03796 • Published Aug 4 • 20

upvoted a paper almost 3 years ago

This is not a Dataset: A Large Negation Benchmark to Challenge Large Language Models

Paper • 2310.15941 • Published Oct 24, 2023 • 6

upvoted a collection almost 3 years ago

GoLLIE

Collection

We present GoLLIE, a Large Language Model trained to follow annotation guidelines that outperforms previous approaches on zero-shot IE. • 4 items • Updated Jun 25 • 22