Ileana Rugina

irugina's activity

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

upvoted a paper 13 days ago

Hardware-Native Joint Sparse-Quantization for Trillion-Scale Mixture-of-Experts

Paper • 2610.02241 • Published Sep 29 • 7

upvoted 2 papers about 1 month ago

WUSH-KV: KV Cache Quantization with Data-Adaptive Transforms

Paper • 2609.38121 • Published Sep 29 • 22

Disaggregated Quantization: Specializing LLM Prefill and Decode

Paper • 2609.26333 • Published Sep 22 • 83

published a model about 2 months ago

irugina/frozen-twist-staleness

Updated Sep 25

updated a model about 2 months ago

irugina/frozen-twist-staleness

Updated Sep 25

liked a dataset about 2 months ago

notadib/harmful-tasks

Viewer • Updated Nov 11, 2025 • 2.49k • 76 • 2

upvoted a paper about 2 months ago

Pruning for Protection: Increasing Jailbreak Resistance in Aligned LLMs Without Fine-Tuning

Paper • 2401.10862 • Published Jan 19, 2024 • 2

upvoted a paper 6 months ago

MatryoshkaLoRA: Learning Accurate Hierarchical Low-Rank Representations for LLM Fine-Tuning

Paper • 2605.07850 • Published May 8 • 19

upvoted a paper 9 months ago

Quartet II: Accurate LLM Pre-Training in NVFP4 by Improved Unbiased Gradient Estimation

Paper • 2601.22813 • Published Jan 30 • 63

upvoted a paper 11 months ago

WUSH: Near-Optimal Adaptive Transforms for LLM Quantization

Paper • 2512.00956 • Published Nov 30, 2025 • 25

upvoted a paper about 1 year ago

Bridging the Gap Between Promise and Performance for Microscaling FP4 Quantization

Paper • 2509.23202 • Published Sep 27, 2025 • 32