Ilya Pereverzin

NodeLinker's activity

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

upvoted a paper 1 day ago

RealChart2Code: Advancing Chart-to-Code Generation with Real Data and Multi-Task Evaluation

Paper • 2603.25804 • Published 5 days ago • 21

upvoted a paper 2 days ago

MSA: Memory Sparse Attention for Efficient End-to-End Memory Model Scaling to 100M Tokens

Paper • 2603.23516 • Published 26 days ago • 42

upvoted 2 papers 9 days ago

A Subgoal-driven Framework for Improving Long-Horizon LLM Agents

Paper • 2603.19685 • Published 12 days ago • 19

HopChain: Multi-Hop Data Synthesis for Generalizable Vision-Language Reasoning

Paper • 2603.17024 • Published 14 days ago • 106

upvoted a paper 10 days ago

Attention Residuals

Paper • 2603.15031 • Published 16 days ago • 170

upvoted a collection 12 days ago

dots.mocr

Collection

Multimodal OCR: Parse Anything from Documents • 2 items • Updated 12 days ago • 7

upvoted a paper 12 days ago

Multimodal OCR: Parse Anything from Documents

Paper • 2603.13032 • Published 18 days ago • 40

upvoted an article 12 days ago

view article

Article

Norm-Preserving Biprojected Abliteration

• 

Nov 6, 2025

•

75

upvoted a paper 12 days ago

V-JEPA 2.1: Unlocking Dense Features in Video Self-Supervised Learning

Paper • 2603.14482 • Published 16 days ago • 24

upvoted 2 papers 13 days ago

GLM-5: from Vibe Coding to Agentic Engineering

Paper • 2602.15763 • Published Feb 17 • 119

Kimi K2.5: Visual Agentic Intelligence

Paper • 2602.02276 • Published Feb 2 • 260

upvoted a paper 14 days ago

EAGLE-3: Scaling up Inference Acceleration of Large Language Models via Training-Time Test

Paper • 2503.01840 • Published Mar 3, 2025 • 9

upvoted 2 papers 15 days ago

DeepSeek-V3 Technical Report

Paper • 2412.19437 • Published Dec 27, 2024 • 80

DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Paper • 2501.12948 • Published Jan 22, 2025 • 444

upvoted a paper 16 days ago

FunCineForge: A Unified Dataset Toolkit and Model for Zero-Shot Movie Dubbing in Diverse Cinematic Scenes

Paper • 2601.14777 • Published Jan 21 • 3

upvoted 3 collections 16 days ago

Qwen3-Embedding

Collection

6 items • Updated Dec 31, 2025 • 154

Qwen-Image

Collection

14 items • Updated Dec 31, 2025 • 91

Qwen3-VL-Embedding

Collection

2 items • Updated Jan 8 • 64

upvoted a paper 18 days ago

CUDA Agent: Large-Scale Agentic RL for High-Performance CUDA Kernel Generation

Paper • 2602.24286 • Published Feb 27 • 97

upvoted a collection 23 days ago

Qwen3.5-abliterated

Collection

19 items • Updated about 8 hours ago • 68