Peter Szemraj PRO

pszemraj's activity

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

upvoted a paper 5 days ago

The Embedder's Dilemma: LLMs Are Better, but at What Cost?

Paper • 2608.12875 • Published 15 days ago • 14

upvoted a paper 6 days ago

Thinking in a Low-Resource Language: What SFT Builds, What RL Fixes, What Accuracy Cannot See

Paper • 2608.17744 • Published 9 days ago • 15

upvoted a paper 7 days ago

FM-Bench: A Benchmark for Long-Horizon Management with Competing Agents

Paper • 2608.18423 • Published 9 days ago • 20

upvoted 2 papers 9 days ago

Scaling Domain Data Repetition in LLM Pretraining

Paper • 2608.14071 • Published 14 days ago • 15

SimpleOPD: Simple Tokenizer-Agnostic On-Policy Distillation for Long-Context Reasoning

Paper • 2608.14277 • Published 14 days ago • 35

upvoted an article 13 days ago

view article

Article

Meet North Micro Vision: A 2.4B Native-Resolution Vision-Language Model

• 

CohereLabs

•

15 days ago

• 38

upvoted 5 papers 14 days ago

Full-bandwidth transformer

Paper • 2608.08888 • Published 19 days ago • 22

Massive Activations in Hybrid Linear Attention Large Language Models: Pre-Attention Spikes and Inter-Spike Plateaus

Paper • 2608.12149 • Published 16 days ago • 30

LLMRouter: Unified Infrastructure for Developing, Evaluating, and Deploying LLM Routers

Paper • 2608.06867 • Published 21 days ago • 109

Poor Man's Agentic Modeling: Simulating Large LLM-Agent Societies on a Laptop

Paper • 2608.11215 • Published Jul 19 • 6

Stealing Reasoning Traces from Proprietary LLM APIs

Paper • 2608.09867 • Published 18 days ago • 116

upvoted an article 17 days ago

view article

Article

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

• 

finebooks

•

18 days ago

• 25

upvoted a paper 22 days ago

UEmbed: Unified Sparse and Dense Multimodal Embeddings

Paper • 2608.02583 • Published 25 days ago • 50

upvoted a collection 22 days ago

Embedding Models

Collection

Run or fine-tune embedding models with Unsloth. • 14 items • Updated 1 day ago • 9

upvoted 3 papers 24 days ago

DiffusionGemma Technical Report

Paper • 2608.00146 • Published 28 days ago • 39

Safeguards Based on Copyable Context Cannot Provide Reliable Safety for LLMs

Paper • 2607.27951 • Published 29 days ago • 7

Meshy T2: Fast Native Mesh Generation with Flow Matching

Paper • 2607.28675 • Published Jul 28 • 59

upvoted an article 25 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

•

Jul 27

• 482

upvoted a collection 28 days ago

Apertus v1.5

Collection

8B and 70B open-data open-weights models, globally multilingual with multimodal input and reasoning support • 2 items • Updated 6 days ago • 31

upvoted a paper about 1 month ago

Kimi K3: Open Frontier Intelligence

Paper • 2607.24653 • Published Jul 27 • 508