Peter Szemraj PRO

pszemraj's activity

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

liked a model 1 day ago

tencent/Hunyuan3D-2.1

Image-to-3D • Updated Oct 17, 2025 • 21.7k • 844

upvoted 4 papers 1 day ago

Agentic Uncertainty Quantification

Paper • 2601.15703 • Published 5 days ago • 8

Agentic Confidence Calibration

Paper • 2601.15778 • Published 5 days ago • 5

Towards Automated Kernel Generation in the Era of LLMs

Paper • 2601.15727 • Published 5 days ago • 16

Terminal-Bench: Benchmarking Agents on Hard, Realistic Tasks in Command Line Interfaces

Paper • 2601.11868 • Published 10 days ago • 29

New activity in pszemraj/long-t5-tglobal-large-pubmed-3k-booksum-16384-WIP17 3 days ago

Adding `safetensors` variant of this model

#7 opened 4 days ago by

SFconvertbot

upvoted a paper 4 days ago

NAACL: Noise-AwAre Verbal Confidence Calibration for LLMs in RAG Systems

Paper • 2601.11004 • Published 11 days ago • 29

liked a model 7 days ago

lightonai/LightOnOCR-2-1B

Image-Text-to-Text • 1B • Updated 6 days ago • 15.3k • 365

upvoted 2 articles 7 days ago

view article

Article

LightOnOCR-2-1B: a lightweight high-performance end-to-end OCR model family

• 

8 days ago

•

64

view article

Article

How We Built a Semantic Highlight Model To Save Token Cost for RAG

• 

12 days ago

•

59

upvoted 2 papers 7 days ago

When Personalization Misleads: Understanding and Mitigating Hallucinations in Personalized LLMs

Paper • 2601.11000 • Published 11 days ago • 26

Your Group-Relative Advantage Is Biased

Paper • 2601.08521 • Published 14 days ago • 145

upvoted a paper 9 days ago

Rewarding the Rare: Uniqueness-Aware RL for Creative Problem Solving in LLMs

Paper • 2601.08763 • Published 14 days ago • 141

upvoted a paper 10 days ago

sui-1: Grounded and Verifiable Long-Form Summarization

Paper • 2601.08472 • Published 14 days ago • 2

liked a Space 10 days ago

Running

181

IOPaint-LaMA

⚡

181

Start an image editing server

liked a model 13 days ago

Qwen/Qwen3-VL-Embedding-2B

Feature Extraction • 2B • Updated 8 days ago • 156k • • 276

upvoted a paper 13 days ago

Illusions of Confidence? Diagnosing LLM Truthfulness via Neighborhood Consistency

Paper • 2601.05905 • Published 18 days ago • 18

upvoted a collection 13 days ago

💧 LFM2.5

Collection

Collection of Instruct, Base, and Japanese LFM2.5-1.2B models. • 22 items • Updated about 11 hours ago • 80

liked a dataset 27 days ago

FutureMa/DramaBench

Viewer • Updated 26 days ago • 600 • 430 • 111

New activity in pszemraj/long-t5-tglobal-xl-16384-booksci-summary-plos-10k 29 days ago

Adding `safetensors` variant of this model

#1 opened 29 days ago by

SFconvertbot