Boris Tseitlin

btseytlin's activity

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

upvoted an article about 4 hours ago

view article

Article

TFLOPS Gap: Why FP4 MoE Kernel Engineering Matters on Blackwell

• 

about 4 hours ago

•

5

liked a model 1 day ago

facebook/dinov3-convnext-base-pretrain-lvd1689m

Image Feature Extraction • 87.6M • Updated Aug 19, 2025 • 37.3k • 10

published a dataset 2 days ago

btseytlin/any2json

Viewer • Updated 5 days ago • 167k • 67

updated a dataset 5 days ago

btseytlin/any2json

Viewer • Updated 5 days ago • 167k • 67

upvoted 2 papers about 1 month ago

GigaEvo: An Open Source Optimization Framework Powered By LLMs And Evolution Algorithms

Paper • 2511.17592 • Published Nov 17, 2025 • 118

Unveiling Intrinsic Dimension of Texts: from Academic Abstract to Creative Story

Paper • 2511.15210 • Published Nov 19, 2025 • 89

upvoted a paper about 2 months ago

Souper-Model: How Simple Arithmetic Unlocks State-of-the-Art LLM Performance

Paper • 2511.13254 • Published Nov 17, 2025 • 136

liked a model 5 months ago

ai-forever/FRED-T5-large

Updated Dec 5, 2023 • 249 • 28

upvoted an article 6 months ago

view article

Article

SmolLM3: smol, multilingual, long-context reasoner

• 
• 
• +21

Jul 8, 2025

•

743

upvoted a paper 7 months ago

Quartet: Native FP4 Training Can Be Optimal for Large Language Models

Paper • 2505.14669 • Published May 20, 2025 • 78

liked a Space 8 months ago

Running

27

CircleGuardBench

⚪

27

First benchmark testing LLM guards on safety and accuracy.

upvoted an article 8 months ago

view article

Article

CircleGuardBench: New Standard for Evaluating AI Moderation Models

• 

May 7, 2025

•

59

upvoted 2 papers 10 months ago

When Less is Enough: Adaptive Token Reduction for Efficient Image Representation

Paper • 2503.16660 • Published Mar 20, 2025 • 72

Feature-Level Insights into Artificial Text Detection with Sparse Autoencoders

Paper • 2503.03601 • Published Mar 5, 2025 • 232

upvoted 2 papers 11 months ago

How Much Knowledge Can You Pack into a LoRA Adapter without Harming LLM?

Paper • 2502.14502 • Published Feb 20, 2025 • 91

MLGym: A New Framework and Benchmark for Advancing AI Research Agents

Paper • 2502.14499 • Published Feb 20, 2025 • 193

upvoted a paper about 2 years ago

Follow Anything: Open-set detection, tracking, and following in real-time

Paper • 2308.05737 • Published Aug 10, 2023 • 12

liked 3 models over 2 years ago

nvidia/GPT-2B-001

Updated May 4, 2023 • 34 • 192

Vision-CAIR/MiniGPT-4

Updated Apr 19, 2023 • 428

google/flan-ul2

Updated Nov 7, 2023 • 5.01k • 560