Ilya Pereverzin

NodeLinker's activity

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

upvoted a paper 1 day ago

Single-Rollout Asynchronous Optimization for Agentic Reinforcement Learning

Paper • 2607.07508 • Published 3 days ago • 10

upvoted a changelog 1 day ago

view changelog

Hugging Face Changelog

Filter Models page by Hardware

11 days ago

• 153

upvoted a paper 9 days ago

DOPD: Dual On-policy Distillation

Paper • 2606.30626 • Published 12 days ago • 103

upvoted a collection 11 days ago

DeepSpec

Collection

12 items • Updated 13 days ago • 73

upvoted a paper 13 days ago

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

Paper • 2606.19348 • Published Apr 26 • 11

upvoted a collection 17 days ago

Qwen-AgentWorld

Collection

3 items • Updated 17 days ago • 66

liked 4 datasets 27 days ago

victor/claude-fable-worldcup-2026-session

Traces • Updated 29 days ago • 1 • 480 • 5

CodeDevX/Vibe-Coding-Instruct

Viewer • Updated 23 days ago • 1.1M • 2.94k • 183

armand0e/claude-fable-5-claude-code

Traces • Updated 21 days ago • 63 • 17.6k • 301

Glint-Research/Fable-5-traces

Traces • Updated 11 days ago • 4.67k • 68.7k • 589

liked a model 29 days ago

moonshotai/Kimi-K2.7-Code

Image-Text-to-Text • 1.1T • Updated 26 days ago • 911k • • 1.08k

upvoted 3 papers 29 days ago

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

Paper • 2606.13473 • Published about 1 month ago • 92

MiniMax Sparse Attention

Paper • 2606.13392 • Published about 1 month ago • 151

SpatialClaw: Rethinking Action Interface for Agentic Spatial Reasoning

Paper • 2606.13673 • Published about 1 month ago • 110

upvoted a paper 30 days ago

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 about 1 month ago • 57

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 29 days ago • 1 • 1.75k • 33

liked a model about 1 month ago

google/diffusiongemma-26B-A4B-it

Image-Text-to-Text • 26B • Updated 5 days ago • 2.02M • 1.12k

upvoted a paper about 1 month ago

Domino: Decoupling Causal Modeling from Autoregressive Drafting in Speculative Decoding

Paper • 2605.29707 • Published May 28 • 152