Peter Szemraj PRO

pszemraj's activity

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

upvoted a paper about 1 hour ago

Horizon-LM: A RAM-Centric Architecture for LLM Training

Paper • 2602.04816 • Published 1 day ago • 16

upvoted a paper 1 day ago

Quartet II: Accurate LLM Pre-Training in NVFP4 by Improved Unbiased Gradient Estimation

Paper • 2601.22813 • Published 7 days ago • 53

liked a dataset 3 days ago

pbevan11/synthetic-ocr-correction-gpt4o

Viewer • Updated Jul 25, 2024 • 10k • 22 • 6

upvoted 2 papers 3 days ago

Linear representations in language models can change dramatically over a conversation

Paper • 2601.20834 • Published 8 days ago • 21

Do Reasoning Models Enhance Embedding Models?

Paper • 2601.21192 • Published 8 days ago • 24

upvoted a paper 7 days ago

Scaling Embeddings Outperforms Scaling Experts in Language Models

Paper • 2601.21204 • Published 8 days ago • 96

upvoted a paper 8 days ago

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

Paper • 2601.15849 • Published 15 days ago • 14

liked a dataset 8 days ago

Pageshift-Entertainment/LongPage

Viewer • Updated 17 days ago • 6.07k • 8.31k • 139

upvoted 2 papers 8 days ago

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

Paper • 2601.18778 • Published 10 days ago • 40

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

Paper • 2601.19895 • Published 9 days ago • 23

liked a model 9 days ago

moonshotai/Kimi-K2.5

Image-Text-to-Text • 171B • Updated 1 day ago • 203k • • 1.75k

upvoted an article 9 days ago

view article

Article

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

• 
• 
• +3

17 days ago

•

36

liked a Space 9 days ago

Runtime error

Featured

62

Waypoint 1 Small

🎮

62

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

liked a model 9 days ago

Roblox/cube3d-v0.1

Updated Mar 20, 2025 • 86

liked a model 11 days ago

tencent/Hunyuan3D-2.1

Image-to-3D • Updated Oct 17, 2025 • 22.9k • 830

upvoted 4 papers 11 days ago

Agentic Uncertainty Quantification

Paper • 2601.15703 • Published 15 days ago • 8

Agentic Confidence Calibration

Paper • 2601.15778 • Published 15 days ago • 5

Towards Automated Kernel Generation in the Era of LLMs

Paper • 2601.15727 • Published 15 days ago • 16

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

Paper • 2601.11868 • Published 20 days ago • 32

New activity in pszemraj/long-t5-tglobal-large-pubmed-3k-booksum-16384-WIP17 13 days ago

Adding `safetensors` variant of this model

#7 opened 14 days ago by

SFconvertbot