Sergey Zubrilin

hiauiarau's activity

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

upvoted an article 14 minutes ago

view article

Article

Keep the Tokens Flowing: Lessons from 16 Open-Source RL Libraries

• 
• 
• +7

5 days ago

•

46

upvoted a paper 4 days ago

SparseLoRA: Accelerating LLM Fine-Tuning with Contextual Sparsity

Paper • 2506.16500 • Published Jun 19, 2025 • 17

upvoted a collection 4 days ago

SparseLoRA

Collection

Accelerating LLM Fine-Tuning with Contextual Sparsity • 4 items • Updated 4 days ago • 1

upvoted 2 collections 5 days ago

Benchmarks

Collection

Collection of benchmarks • 2 items • Updated Feb 2 • 1

Opensource datasets

Collection

11 items • Updated 3 days ago • 2

upvoted a paper 10 days ago

Qwen3-Coder-Next Technical Report

Paper • 2603.00729 • Published 14 days ago • 47

upvoted 2 papers 11 days ago

SWE-rebench V2: Language-Agnostic SWE Task Collection at Scale

Paper • 2602.23866 • Published 15 days ago • 84

OpenAutoNLU: Open Source AutoML Library for NLU

Paper • 2603.01824 • Published 12 days ago • 47

upvoted 2 papers 12 days ago

Recovered in Translation: Efficient Pipeline for Automated Translation of Benchmarks and Datasets

Paper • 2602.22207 • Published 17 days ago • 42

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

Paper • 2602.24286 • Published 15 days ago • 86

upvoted a collection 12 days ago

SWE-rebench-V2

Collection

SWE-rebench-V2 is a curated dataset of software-engineering tasks derived from real GitHub issues and pull requests. • 3 items • Updated 11 days ago • 6

upvoted a paper 12 days ago

LK Losses: Direct Acceptance Rate Optimization for Speculative Decoding

Paper • 2602.23881 • Published 15 days ago • 18

upvoted a collection 12 days ago

LK-Speculators

Collection

High-performance speculative decoding draft models trained using LK losses, a novel training objectives that directly optimize acceptance rate • 9 items • Updated 11 days ago • 5

upvoted 2 papers 13 days ago

General Agent Evaluation

Paper • 2602.22953 • Published 16 days ago • 11

DeepSeek-OCR 2: Visual Causal Flow

Paper • 2601.20552 • Published Jan 28 • 65

upvoted a collection 15 days ago

My REAP Experiments

Collection

VRAM is all we need • 5 items • Updated 14 days ago • 1

upvoted a paper 16 days ago

GLiNER2: An Efficient Multi-Task Information Extraction System with Schema-Driven Interface

Paper • 2507.18546 • Published Jul 24, 2025 • 35

upvoted a collection 16 days ago

GeRaCl

Collection

General Rapid Classification: Zero-Result Classifier for Russian • 2 items • Updated Jun 7, 2025 • 3

upvoted a paper 17 days ago

PolyGuard: A Multilingual Safety Moderation Tool for 17 Languages

Paper • 2504.04377 • Published Apr 6, 2025 • 1

upvoted a paper 20 days ago

Step 3.5 Flash: Open Frontier-Level Intelligence with 11B Active Parameters

Paper • 2602.10604 • Published Feb 11 • 189