Peter Szemraj PRO

pszemraj's activity

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

upvoted a paper about 17 hours ago

MassAlloc Attention: Let Attention Allocate Its Own Compute

Paper • 2609.32712 • Published 6 days ago • 71

liked 2 models 9 days ago

LiquidAI/LFM2.5-230M-Base

Text Generation • 0.2B • Updated Jun 16 • 12.7k • 22

ngxson/fly-llm-hf

Text Generation • 71M • Updated 21 days ago • 749 • 11

liked a Space 10 days ago

Running on Zero

MCP

Featured

174

Qwen-Image-2.1

🖼

174

Generate and edit images with Qwen-Image-2.1

New activity in mlx-community/Falcon-OCR-bf16 10 days ago

Update weights for Falcon OCR v1.5

#1 opened 10 days ago by

pszemraj

liked a Space 12 days ago

Running

Featured

363

Jev Decision Index

🔬

363

Benchmarks and news on various repros of TypeSafe's Jev

liked a dataset 12 days ago

secemp9/arxiv-complete

Viewer • Updated 12 days ago • 128M • 122k • 570

liked a model 12 days ago

nvidia/Gemma-4-31B-IT-NVFP4

Text Generation • 21B • Updated Jul 13 • 1.58M • • 574

liked a model 15 days ago

fastino/gliner2.5-multi-v1

Token Classification • 0.3B • Updated 4 days ago • 282k • 267

upvoted a paper 15 days ago

RelateAnything: Real-Time Open-Vocabulary Relation Prediction From Any Inputs

Paper • 2609.12552 • Published 21 days ago • 6

upvoted a paper 16 days ago

How Lossless Is Lossless Speculative Decoding? The Role of Numerical Precision in Orthrus

Paper • 2609.15504 • Published 18 days ago • 37

liked a model 17 days ago

ibm-granite/granite-timeseries-patchtst-fm-r2

Time Series Forecasting • 0.4B • Updated 22 days ago • 241k • 16

upvoted an article 17 days ago

view article

Article

IBM releases SOTA Granite Time Series PatchTST-FM-r2 model with commercial-friendly license

• 

ibm-research

•

22 days ago

• 60

New activity in Edge0/Edge0-35B-A3B-preview 17 days ago

please make an ios app for ease of using your AI model like google's edge gallery app

🚀 2

2

#3 opened 18 days ago by

Narutoouz

upvoted a paper 19 days ago

MetroLLM-Bench: Evaluating Language Models as Transit Kiosk Runtimes

Paper • 2609.10016 • Published 23 days ago • 29

commented a paper 20 days ago

MetroLLM-Bench: Evaluating Language Models as Transit Kiosk Runtimes

Paper • 2609.10016 • Published 23 days ago • 29 •

5

upvoted a paper 20 days ago

NCP-ArchPreview Technical Report: Moving towards Latent Space Language Models through Next Concept Prediction

Paper • 2609.10715 • Published 23 days ago • 331

liked a model 22 days ago

Edge0/Edge0-35B-A3B-preview

Text Generation • 35B • Updated about 12 hours ago • 80.1k • 3.56k

upvoted a paper 24 days ago

Don't Drop Dropout: Optimizing Layer Sparsity for Efficient LLM Training and Inference

Paper • 2609.05275 • Published 28 days ago • 26

liked a dataset 24 days ago

librarian-bots/arxiv-metadata-snapshot

Viewer • Updated 4 days ago • 3.18M • 5.2k • 22