Michał Junczyk PRO

michaljunczyk's activity

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

upvoted an article 2 months ago

view article

Article

We Got Claude to Fine-Tune an Open Source LLM

• 
• 

Dec 4, 2025

•

593

upvoted a collection 4 months ago

Korea ASR Dataset

Collection

Collections of Korean ASR dataset • 13 items • Updated 29 days ago • 1

upvoted 2 papers 5 months ago

BiasFreeBench: a Benchmark for Mitigating Bias in Large Language Model Responses

Paper • 2510.00232 • Published Sep 30, 2025 • 16

GEM: A Gym for Agentic LLMs

Paper • 2510.01051 • Published Oct 1, 2025 • 90

upvoted a collection 5 months ago

ParlaSpeech

Collection

Speech + text dataset collection based on the ParlaMint data. Paper describing the construction process: https://www.arxiv.org/abs/2409.15397. • 4 items • Updated Oct 11, 2024 • 1

upvoted 2 papers 5 months ago

TrustJudge: Inconsistencies of LLM-as-a-Judge and How to Alleviate Them

Paper • 2509.21117 • Published Sep 25, 2025 • 30

Granary: Speech Recognition and Translation Dataset in 25 European Languages

Paper • 2505.13404 • Published May 19, 2025 • 2

upvoted a collection 5 months ago

Audio Datasets

Collection

5 items • Updated Feb 12, 2025 • 2

upvoted 2 papers 6 months ago

AudioStory: Generating Long-Form Narrative Audio with Large Language Models

Paper • 2508.20088 • Published Aug 27, 2025 • 21

MCP-Bench: Benchmarking Tool-Using LLM Agents with Complex Real-World Tasks via MCP Servers

Paper • 2508.20453 • Published Aug 28, 2025 • 63

upvoted a collection 6 months ago

DeepSeek-V3.1

Collection

4 items • Updated Nov 27, 2025 • 260

upvoted an article 10 months ago

view article

Article

Fine-Tune Whisper For Multilingual ASR with 🤗 Transformers

• 

Nov 3, 2022

•

356

upvoted a paper about 1 year ago

Not All LLM Reasoners Are Created Equal

Paper • 2410.01748 • Published Oct 2, 2024 • 29

upvoted an article about 1 year ago

view article

Article

EuroLLM-9B

• 

Dec 2, 2024

•

139

upvoted a paper about 1 year ago

EuroLLM: Multilingual Language Models for Europe

Paper • 2409.16235 • Published Sep 24, 2024 • 29

upvoted a collection over 1 year ago

Polish Automatic Speech Recognition

Collection

3 items • Updated Jan 26, 2024 • 3

upvoted 2 articles over 1 year ago

view article

Article

How to build a custom text classifier without days of human labeling

• 

Oct 17, 2024

•

57

view article

Article

Can foundation models label data like humans?

• 
• 
• +7

Jun 12, 2023

•

1

upvoted 2 collections over 1 year ago

Llama-3.1-Nemotron-70B

Collection

SOTA models on Arena Hard and RewardBench as of 1 Oct 2024. • 6 items • Updated 12 days ago • 155

Bielik-11B-v2.2

Collection

A collection of models based on Bielik-11B-v2.2 - instruct and quantized versions. • 17 items • Updated Jun 6, 2025 • 28