Sergey Zubrilin's picture

Sergey Zubrilin

hiauiarau

·

AI & ML interests

None yet

Recent Activity

liked a model 20 minutes ago

z-lab/Qwen3.6-35B-A3B-DFlash

upvoted a collection 1 day ago

liked a model 1 day ago

Qwen/Qwen3.6-35B-A3B-FP8

View all activity

Organizations

upvoted a collection 1 day ago

Qwen3.6

2 items • Updated 1 day ago • 82

upvoted a collection 2 days ago

HY-Embodied

1 item • Updated 4 days ago • 5

upvoted 2 collections 15 days ago

POLLUX

LLM-as-a-judge • 6 items • Updated Oct 6, 2025 • 6

Gemma 4

8 items • Updated 15 days ago • 634

upvoted a collection 17 days ago

MiniMax-M2

4 items • Updated 2 days ago • 21

upvoted a collection 19 days ago

TTS and VC

Scicom TTS models and datasets. • 10 items • Updated 20 days ago • 3

upvoted a collection 27 days ago

FLUX.2

Our second generation of FLUX • 21 items • Updated 11 days ago • 191

upvoted an article about 1 month ago

Article

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

+7

Mar 10

•

126

upvoted a paper about 1 month ago

SparseLoRA: Accelerating LLM Fine-Tuning with Contextual Sparsity

Paper • 2506.16500 • Published Jun 19, 2025 • 17

upvoted 4 collections about 1 month ago

SparseLoRA

Accelerating LLM Fine-Tuning with Contextual Sparsity • 4 items • Updated Mar 11 • 2

Benchmarks

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

Opensource datasets

11 items • Updated Mar 11 • 2

Gliner Guard v1

GLiNER2-based guardrail for PII, content safety classification, prompt attacks detection and more via single forward pass • 4 items • Updated 4 days ago • 2

upvoted 2 papers about 1 month ago

Qwen3-Coder-Next Technical Report

Paper • 2603.00729 • Published Feb 28 • 64

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

Paper • 2602.23866 • Published Feb 27 • 88

upvoted 3 papers about 2 months ago

OpenAutoNLU: Open Source AutoML Library for NLU

Paper • 2603.01824 • Published Mar 2 • 50

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

Paper • 2602.22207 • Published Feb 25 • 43

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

Paper • 2602.24286 • Published Feb 27 • 98

upvoted a collection about 2 months ago

SWE-rebench-V2

SWE-rebench-V2 is a curated dataset of software-engineering tasks derived from real GitHub issues and pull requests. • 3 items • Updated Mar 3 • 9

upvoted a paper about 2 months ago

LK Losses: Direct Acceptance Rate Optimization for Speculative Decoding

Paper • 2602.23881 • Published Feb 27 • 18