Peter Szemraj PRO

pszemraj's activity

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

upvoted 2 papers 5 days ago

Nemotron-Flash: Towards Latency-Optimal Hybrid Small Language Models

Paper • 2511.18890 • Published 15 days ago • 29

LFM2 Technical Report

Paper • 2511.23404 • Published 10 days ago • 34

upvoted a collection 5 days ago

DeepSeek-V3.2

Collection

4 items • Updated 8 days ago • 504

upvoted a collection 6 days ago

Ministral 3

Collection

A collection of edge models, with Base, Instruct and Reasoning variants, in 3 different sizes: 3B, 8B and 14B. All with vision capabilities. • 9 items • Updated 6 days ago • 116

upvoted an article 7 days ago

view article

Article

Transformers v5: Simple model definitions powering the AI ecosystem

• 
• 
• +2

8 days ago

•

227

upvoted a paper 9 days ago

Block Cascading: Training Free Acceleration of Block-Causal Video Models

Paper • 2511.20426 • Published 13 days ago • 9

upvoted a paper 10 days ago

What does it mean to understand language?

Paper • 2511.19757 • Published 14 days ago • 9

upvoted a paper 14 days ago

Unveiling Intrinsic Dimension of Texts: from Academic Abstract to Creative Story

Paper • 2511.15210 • Published 20 days ago • 86

upvoted a paper 18 days ago

Mitigating Label Length Bias in Large Language Models

Paper • 2511.14385 • Published 21 days ago • 6

upvoted 2 articles 20 days ago

view article

Article

ViDoRe V3: a comprehensive evaluation of retrieval for enterprise use-cases

• 

Nov 5

•

53

view article

Article

The Heterogeneous Feature of RoPE-based Attention in Long-Context LLMs

• 

24 days ago

•

11

upvoted a paper 21 days ago

OlmoEarth: Stable Latent Image Modeling for Multimodal Earth Observation

Paper • 2511.13655 • Published 21 days ago • 9

upvoted a collection 24 days ago

Motif-2-12.7B

Collection

2 items • Updated Nov 6 • 5

upvoted a paper 24 days ago

Motif 2 12.7B technical report

Paper • 2511.07464 • Published Nov 7 • 38

upvoted a collection 27 days ago

SYNTH

Collection

Fully generalist synthetic dataset and SOTA small reasoners • 3 items • Updated 29 days ago • 11

upvoted a collection about 1 month ago

GVE

Collection

Towards General Video Embeddings: Models and Benchmarks • 4 items • Updated Nov 3 • 19

upvoted 3 papers about 1 month ago

Trove: A Flexible Toolkit for Dense Retrieval

Paper • 2511.01857 • Published Nov 3 • 10

The Principles of Diffusion Models

Paper • 2510.21890 • Published Oct 24 • 59

Reasoning Language Model Inference Serving Unveiled: An Empirical Study

Paper • 2510.18672 • Published Oct 21 • 7

upvoted a collection about 1 month ago

LightOnOCR

Collection

The Case for End-to-End and Efficient Domain-Specific Vision-Language Models for OCR • 7 items • Updated 26 days ago • 14