Peter Szemraj PRO

pszemraj's activity

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

upvoted a paper 1 day ago

One Token to Fool LLM-as-a-Judge

Paper • 2507.08794 • Published 4 days ago • 19

updated a collection 1 day ago

Survivor Library Books - OCR

Collection

Books from the Survivor Library (mostly ~1920s & earlier) OCR'd with recent VLMs • 2 items • Updated 1 day ago • 3

commented a paper 1 day ago

Dynamic Chunking for End-to-End Hierarchical Sequence Modeling

Paper • 2507.07955 • Published 5 days ago • 15 •

3

upvoted a paper 2 days ago

Dynamic Chunking for End-to-End Hierarchical Sequence Modeling

Paper • 2507.07955 • Published 5 days ago • 15

upvoted a paper 5 days ago

A Survey on Latent Reasoning

Paper • 2507.06203 • Published 7 days ago • 73

upvoted an article 5 days ago

view article

Article

SmolLM3: smol, multilingual, long-context reasoner

By and 22 others •

7 days ago

• 515

liked a model 6 days ago

google/t5gemma-9b-2b-ul2-it

Text Generation • 12B • Updated 6 days ago • 39 • 3

upvoted a collection 6 days ago

T5Gemma

Collection

32 items • Updated 5 days ago • 50

upvoted an article 6 days ago

view article

Article

Reachy Mini - The Open-Source Robot for Today's and Tomorrow's AI Builders

By and 1 other •

6 days ago

• 543

New activity in ethzanalytics/stablelm-base-alpha-7b-sharded 6 days ago

Adding `safetensors` variant of this model

#1 opened 6 days ago by

SFconvertbot

upvoted 2 papers 6 days ago

Easy Dataset: A Unified and Extensible Framework for Synthesizing LLM Fine-Tuning Data from Unstructured Documents

Paper • 2507.04009 • Published 10 days ago • 28

Should We Still Pretrain Encoders with Masked Language Modeling?

Paper • 2507.00994 • Published 14 days ago • 73

updated 2 datasets 7 days ago

BEE-spoke-data/SurvivorLib-Nanonets-OCR-s

Viewer • Updated 1 day ago • 11.7k • 179 • 2

BEE-spoke-data/SurvivorLib-rolmOCR

Viewer • Updated 7 days ago • 13.3k • 140 • 2

commented a paper 8 days ago

Energy-Based Transformers are Scalable Learners and Thinkers

Paper • 2507.02092 • Published 13 days ago • 50 •

8

upvoted a paper 8 days ago

Energy-Based Transformers are Scalable Learners and Thinkers

Paper • 2507.02092 • Published 13 days ago • 50

published a dataset 10 days ago

BEE-spoke-data/SurvivorLib-rolmOCR

Viewer • Updated 7 days ago • 13.3k • 140 • 2

upvoted a paper 10 days ago

Self-Correction Bench: Revealing and Addressing the Self-Correction Blind Spot in LLMs

Paper • 2507.02778 • Published 12 days ago • 9