1 12

Mikołaj Piórczyński

mpiorczynski

AI & ML interests

None yet

Recent Activity

upvoted a paper about 4 hours ago

No Task Left Behind: Isotropic Model Merging with Common and Task-Specific Subspaces

upvoted a paper about 6 hours ago

Scaling up Test-Time Compute with Latent Reasoning: A Recurrent Depth Approach

upvoted an article 6 days ago

Fine-tuning LLMs with Singular Value Decomposition

View all activity

Organizations

None yet

mpiorczynski's activity

upvoted a paper about 4 hours ago

No Task Left Behind: Isotropic Model Merging with Common and Task-Specific Subspaces

Paper • 2502.04959 • Published 3 days ago • 7

upvoted a paper about 6 hours ago

Scaling up Test-Time Compute with Latent Reasoning: A Recurrent Depth Approach

Paper • 2502.05171 • Published 3 days ago • 20

upvoted an article 6 days ago

Article

Fine-tuning LLMs with Singular Value Decomposition

•

Jun 2, 2024

• 11

upvoted a paper 7 days ago

SAeUron: Interpretable Concept Unlearning in Diffusion Models with Sparse Autoencoders

Paper • 2501.18052 • Published 12 days ago • 6

upvoted a paper 10 days ago

Streaming DiLoCo with overlapping communication: Towards a Distributed Free Lunch

Paper • 2501.18512 • Published 11 days ago • 25

upvoted 2 papers 3 months ago

BALROG: Benchmarking Agentic LLM and VLM Reasoning On Games

Paper • 2411.13543 • Published Nov 20, 2024 • 18

Bielik 7B v0.1: A Polish Language Model -- Development, Insights, and Evaluation

Paper • 2410.18565 • Published Oct 24, 2024 • 46

upvoted a paper 9 months ago

EM Distillation for One-step Diffusion Models

Paper • 2405.16852 • Published May 27, 2024 • 11

upvoted a paper 10 months ago

Adaptive Computation Modules: Granular Conditional Computation For Efficient Inference

Paper • 2312.10193 • Published Dec 15, 2023 • 1

upvoted a paper 12 months ago

Scaling Laws for Fine-Grained Mixture of Experts

Paper • 2402.07871 • Published Feb 12, 2024 • 12

upvoted a paper about 1 year ago

MoE-Mamba: Efficient Selective State Space Models with Mixture of Experts

Paper • 2401.04081 • Published Jan 8, 2024 • 70

upvoted a paper over 1 year ago

Approximating Two-Layer Feedforward Networks for Efficient Transformers

Paper • 2310.10837 • Published Oct 16, 2023 • 11