Peter Szemraj PRO

pszemraj's activity

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

upvoted a paper 2 days ago

Scaling Embeddings Outperforms Scaling Experts in Language Models

Paper • 2601.21204 • Published 3 days ago • 90

upvoted a paper 3 days ago

CGPT: Cluster-Guided Partial Tables with LLM-Generated Supervision for Table Retrieval

Paper • 2601.15849 • Published 10 days ago • 14

liked a dataset 3 days ago

Pageshift-Entertainment/LongPage

Viewer • Updated 12 days ago • 6.07k • 7.59k • 139

upvoted a paper 3 days ago

Teaching Models to Teach Themselves: Reasoning at the Edge of Learnability

Paper • 2601.18778 • Published 6 days ago • 38

upvoted a paper 4 days ago

Post-LayerNorm Is Back: Stable, ExpressivE, and Deep

Paper • 2601.19895 • Published 5 days ago • 19

liked a model 4 days ago

moonshotai/Kimi-K2.5

Image-Text-to-Text • Updated 1 day ago • 53.5k • • 1.33k

upvoted an article 4 days ago

view article

Article

Introducing Waypoint-1: Real-time interactive video diffusion from Overworld

• 
• 
• +3

12 days ago

•

33

liked a Space 4 days ago

Running on Zero

Featured

55

Waypoint 1 Small

🎮

55

Explore and navigate through AI-generated worlds in real-time

liked a model 4 days ago

Roblox/cube3d-v0.1

Updated Mar 20, 2025 • 86

liked a model 6 days ago

tencent/Hunyuan3D-2.1

Image-to-3D • Updated Oct 17, 2025 • 22.3k • 857

upvoted 4 papers 6 days ago

Agentic Uncertainty Quantification

Paper • 2601.15703 • Published 10 days ago • 8

Agentic Confidence Calibration

Paper • 2601.15778 • Published 10 days ago • 5

Towards Automated Kernel Generation in the Era of LLMs

Paper • 2601.15727 • Published 10 days ago • 16

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

Paper • 2601.11868 • Published 15 days ago • 32

New activity in pszemraj/long-t5-tglobal-large-pubmed-3k-booksum-16384-WIP17 8 days ago

Adding `safetensors` variant of this model

#7 opened 10 days ago by

SFconvertbot

upvoted a paper 9 days ago

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

Paper • 2601.11004 • Published 16 days ago • 30

liked a model 12 days ago

lightonai/LightOnOCR-2-1B

Image-Text-to-Text • 1B • Updated 2 days ago • 30.6k • 458

upvoted 2 articles 13 days ago

view article

Article

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

• 

13 days ago

•

75

view article

Article

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

• 

17 days ago

•

62

upvoted a paper 13 days ago

When Personalization Misleads: Understanding and Mitigating Hallucinations in Personalized LLMs

Paper • 2601.11000 • Published 16 days ago • 26