Peter Szemraj PRO

pszemraj's activity

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

upvoted an article about 12 hours ago

view article

Article

FineBooks: are open OCR models good enough to unlock historical knowledge?

• 

finebooks

•

about 22 hours ago

• 18

upvoted a paper 5 days ago

UEmbed: Unified Sparse and Dense Multimodal Embeddings

Paper • 2608.02583 • Published 8 days ago • 50

upvoted a collection 6 days ago

Embedding Models

Collection

Run or fine-tune embedding models with Unsloth. • 14 items • Updated about 17 hours ago • 8

upvoted 2 papers 7 days ago

DiffusionGemma Technical Report

Paper • 2608.00146 • Published 11 days ago • 36

Safeguards Based on Copyable Context Cannot Provide Reliable Safety for LLMs

Paper • 2607.27951 • Published 12 days ago • 7

upvoted a paper 8 days ago

Meshy T2: Fast Native Mesh Generation with Flow Matching

Paper • 2607.28675 • Published 14 days ago • 56

upvoted an article 8 days ago

view article

Article

Anatomy of a Frontier Lab Agent Intrusion: A Technical Timeline of the July 2026 Incident

• 
• 
• +2

hlarcher, XciD, raphael-gl, chris-rannou

•

15 days ago

• 458

upvoted a collection 11 days ago

Apertus v1.5

Collection

8B and 70B open-data open-weights models, largely multilingual with supported multimodality and reasoning • 2 items • Updated 7 days ago • 31

upvoted a paper 14 days ago

Kimi K3: Open Frontier Intelligence

Paper • 2607.24653 • Published 15 days ago • 488

upvoted a paper 16 days ago

LLMs Get Lost in Evolving User Intent

Paper • 2607.20734 • Published 20 days ago • 24

upvoted a paper 18 days ago

SLAI T-Rex: Full-Parameter Post-training of the DeepSeek-V4 Family on Ascend SuperPOD

Paper • 2607.20145 • Published 20 days ago • 74

upvoted a paper 19 days ago

Fara-1.5: Scalable Learning Environments for Computer Use Agents

Paper • 2606.20785 • Published Jun 18 • 7

upvoted a collection 19 days ago

Fara1.5

Collection

Collection of Fara1.5 CUA models in three sizes - 4B, 9B and 27B. • 3 items • Updated 20 days ago • 14

upvoted a paper 22 days ago

Perceiver IO: A General Architecture for Structured Inputs & Outputs

Paper • 2107.14795 • Published Jul 30, 2021 • 2

upvoted 2 articles about 2 months ago

view article

Article

Introducing the FFASR Leaderboard: Benchmarking ASR in the Real World

• 
• 
• +3

daniel-treble, whojavumusic, alessia-treble, georg-goetz, bezzam

•

Jun 24

• 10

view article

Article

Which tokens does a hybrid model predict better?

• 

allenai

•

Jun 25

• 8

upvoted a paper about 2 months ago

Freeing the Law with LOCUS: A Local Ordinance Corpus for the United States

Paper • 2606.19334 • Published Jun 17 • 8

upvoted 2 collections about 2 months ago

SWE-FastContext

Collection

A family of code-search models powering the Explore subagent for coding agents.(It will be made public later) • 3 items • Updated Jun 30 • 18

Gemma 4 QAT Mobile

Collection

4 items • Updated 21 days ago • 49

upvoted an article about 2 months ago

view article

Article

MTEB Leaderboard: From a slow demo to feature-rich leaderboard

• 

Samoed

•

Jun 12

• 23