Ilya Pereverzin

NodeLinker's activity

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

upvoted a paper 5 days ago

Single-Rollout Asynchronous Optimization for Agentic Reinforcement Learning

Paper • 2607.07508 • Published 7 days ago • 22

upvoted a changelog 5 days ago

view changelog

Hugging Face Changelog

Filter Models page by Hardware

15 days ago

• 194

upvoted a paper 14 days ago

DOPD: Dual On-policy Distillation

Paper • 2606.30626 • Published 16 days ago • 106

upvoted a collection 15 days ago

DeepSpec

Collection

12 items • Updated 17 days ago • 74

upvoted a paper 17 days ago

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

Paper • 2606.19348 • Published Apr 26 • 12

upvoted a collection 21 days ago

Qwen-AgentWorld

Collection

3 items • Updated 21 days ago • 66

liked 4 datasets about 1 month ago

victor/claude-fable-worldcup-2026-session

Traces • Updated Jun 11 • 1 • 422 • 5

CodeDevX/Vibe-Coding-Instruct

Viewer • Updated 27 days ago • 1.1M • 3.05k • 186

armand0e/claude-fable-5-claude-code

Traces • Updated 26 days ago • 63 • 17.9k • 307

Glint-Research/Fable-5-traces

Traces • Updated 16 days ago • 4.67k • 74.3k • 610

liked a model about 1 month ago

moonshotai/Kimi-K2.7-Code

Image-Text-to-Text • 1.1T • Updated 30 days ago • 892k • • 1.09k

upvoted 4 papers about 1 month ago

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

Paper • 2606.13473 • Published Jun 11 • 93

MiniMax Sparse Attention

Paper • 2606.13392 • Published Jun 11 • 151

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 about 1 month ago

DiffusionGemma

Collection

1 item • Updated Jun 10 • 58

upvoted a paper about 1 month ago

Breaking Entropy Bounds: Accelerating RL Training via MTP with Rejection Sampling

Paper • 2606.12370 • Published Jun 10 • 21

liked a dataset about 1 month ago

victor/fable-5-boeing-747-trace

Traces • Updated Jun 11 • 1 • 1.47k • 32

liked a model about 1 month ago

google/diffusiongemma-26B-A4B-it

Image-Text-to-Text • 26B • Updated 9 days ago • 1.94M • 1.13k

upvoted a paper about 1 month ago

Domino: Decoupling Causal Modeling from Autoregressive Drafting in Speculative Decoding

Paper • 2605.29707 • Published May 28 • 152