⚡ Pushing ZeroGPU to the limit.

Ilya Pereverzin

NodeLinker

·

AI & ML interests

Research → Fine-tuning → Acceleration → Automation → End-to-end products ↺

Recent Activity

liked a Space 1 day ago

geocine/MiniMax-H3-Prompt-Enhancer-2.6B

liked a model 2 days ago

incoai/Qwen3.8-27B-DFlash2

liked a model 3 days ago

LiquidAI/LFM2.5-Encoder-350M

View all activity

Organizations

upvoted a collection 4 days ago

DFlash 2

Keep Drafting Parallel • 4 items • Updated 4 days ago • 17

upvoted a collection 8 days ago

dots3.note

2 items • Updated 8 days ago • 11

upvoted a paper 10 days ago

On-Policy Self-Distillation without Any Supervision

Paper • 2608.06296 • Published 14 days ago • 217

upvoted a paper 11 days ago

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

Paper • 2608.09802 • Published 13 days ago • 133

upvoted an article 18 days ago

Article

Deploy local agents everywhere with LFM2.5-2.6B

LiquidAI

•

18 days ago

• 90

upvoted a paper 24 days ago

Kimi K3: Open Frontier Intelligence

Paper • 2607.24653 • Published 27 days ago • 497

upvoted a paper 27 days ago

Loop the Loopies!

Paper • 2607.16051 • Published Jul 17 • 77

upvoted 3 papers about 1 month ago

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

Paper • 2607.05147 • Published Jul 6 • 45

Qwen-Music Technical Report

Paper • 2607.11699 • Published Jul 13 • 32

Single-Rollout Asynchronous Optimization for Agentic Reinforcement Learning

Paper • 2607.07508 • Published Jul 8 • 30

upvoted a changelog about 1 month ago

Hugging Face Changelog

Filter Models page by Hardware

Jun 30

• 222

upvoted a paper about 2 months ago

DOPD: Dual On-policy Distillation

Paper • 2606.30626 • Published Jun 29 • 114

upvoted a collection about 2 months ago

DeepSpec

12 items • Updated Jun 28 • 88

upvoted a paper about 2 months ago

DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence

Paper • 2606.19348 • Published Apr 26 • 38

upvoted a collection about 2 months ago

Qwen-AgentWorld

3 items • Updated Jun 24 • 79

upvoted 4 papers 2 months ago

MaxProof: Scaling Mathematical Proof with Generative-Verifier RL and Population-Level Test-Time Scaling

Paper • 2606.13473 • Published Jun 11 • 96

MiniMax Sparse Attention

Paper • 2606.13392 • Published Jun 11 • 157

SpatialClaw: Rethinking Action Interface for Agentic Spatial Reasoning

Paper • 2606.13673 • Published Jun 11 • 111

Verifiable Environments Are LEGO Bricks: Recursive Composition for Reasoning Generalization

Paper • 2606.12373 • Published Jun 10 • 7

upvoted a collection 2 months ago

DiffusionGemma

1 item • Updated Jul 21 • 63