Ilya Pereverzin

NodeLinker's activity

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

upvoted a paper 6 days ago

UBTree: Parallel Tree Drafting via Unigram and Bigram Models for Speculative Decoding

Paper • 2609.39972 • Published 28 days ago • 41

upvoted a changelog 11 days ago

view changelog

Hugging Face Changelog

Filter Models & Datasets Pages by Author

11 days ago

• 90

upvoted a changelog 13 days ago

view changelog

Hugging Face Changelog

Faster Tensor Viewer

14 days ago

• 100

upvoted a collection 21 days ago

EmbeddingGemma 2

Collection

1 item • Updated 21 days ago • 27

upvoted a paper 28 days ago

Selecting Diverse SFT Traces Improves Post-RL Generalization

Paper • 2609.33780 • Published about 1 month ago • 38

upvoted a paper about 1 month ago

DeepSeek Elastic Compute (DSec): A Sandbox Infrastructure for Effective Agentic Training at Scale

Paper • 2609.22978 • Published Sep 19 • 4

upvoted a collection about 2 months ago

LLaDA-Image

Collection

5 items • Updated about 17 hours ago • 9

upvoted a paper about 2 months ago

LLaDA-Image: Building Strong Image Generators with Fully Open Training Recipes

Paper • 2609.03796 • Published Sep 3 • 114

upvoted 4 collections 2 months ago

Qwen3.8-Flash-Next

Collection

2 items • Updated Aug 26 • 69

Qwen3.8

Collection

4 items • Updated Aug 13 • 596

DFlash 2

Collection

Keep Drafting Parallel • 4 items • Updated Sep 12 • 33

dots3.note

Collection

2 items • Updated Aug 14 • 11

upvoted 2 papers 3 months ago

On-Policy Self-Distillation without Any Supervision

Paper • 2608.06296 • Published Aug 9 • 220

SWE-Bench ProMax: Benchmarking Agents on Large-Scale Multilingual Code Refactoring

Paper • 2608.09802 • Published Aug 10 • 85

upvoted an article 3 months ago

view article

Article

Deploy local agents everywhere with LFM2.5-2.6B

• 

LiquidAI

•

Aug 4

• 101

upvoted 4 papers 3 months ago

Kimi K3: Open Frontier Intelligence

Paper • 2607.24653 • Published Jul 27 • 537

Loop the Loopies!

Paper • 2607.16051 • Published Jul 17 • 79

DSpark: Confidence-Scheduled Speculative Decoding with Semi-Autoregressive Generation

Paper • 2607.05147 • Published Jul 6 • 54

Qwen-Music Technical Report

Paper • 2607.11699 • Published Jul 13 • 34

upvoted a paper 4 months ago

Single-Rollout Asynchronous Optimization for Agentic Reinforcement Learning

Paper • 2607.07508 • Published Jul 8 • 34