AINL Conference
397 subscribers
34 photos
13 files
87 links
AINL: Artificial Intelligence and Natural Language Conference

https://ainlconf.ru/
Download Telegram
Dear colleagues, please register today since there is only one day left before AINL starts; please keep in mind that we need some time to process your payment!

https://forms.gle/nhFFrJCB3vCHC6rz6
🀝4
⏰ Dear colleagues, please be aware that the schedule uses NSK time (MSK+4, UTC+7)

https://ainlconf.ru/2025/program
πŸ”– Dear colleagues, if you haven't received your badge today, please come to get it tomorrow before 11am NSK.
⏭AINL 2025 is finished! Thank you all for the participation! Stay tuned for the updates regarding photos, videos, and publications.
πŸ”₯17❀5πŸ‘1
Dear colleagues, the photos from 1st day are here: https://vk.com/album-38193760_306953158
❀7πŸ‘3πŸ”₯3πŸ₯°1πŸ‘€1
Dear colleagues, as part of our conference AINL 2025 we have two nominations:

NSU Choice Award
Boris Malashenko, Ivan Jarsky, Valeria Efimova. Leveraging Large Language Models For Scalable Vector Graphics Processing: A Review

AINL 2025 Best Paper Award
Petr Sychev, Andrey Goncharov, Daniil Vyazhev, Edvard Khalafyan, Alexey Zaitsev. When an LLM is apprehensive about its answers - and when its uncertainty is justified

On the photo Valentin Malykh gives a MTS AI gift to Best Paper's author Petr Sychev.
πŸ”₯15πŸ†7❀2
AINL Eval has this year more than a dozen participants. We were flattered that GigaCheck command decided to participate in our challenge.

The challenge was to not only identify if a text was human or AI-generated but also pinpoint which exact model (e.g., GPT-4 Turbo, Gemma 2-27B) was used.

πŸ₯‡GigaCheck team got the 1st place. Enhancing GigaCheck tool with an additional classification layer, they achieved:
βœ… 91% accuracy on public test data, including texts from an unfamiliar model
βœ… 86% accuracy on private test sets with previously unseen domains

πŸ₯ˆThe team who won the 2nd place is from HSE and ReText.Ai. They combined statistical and neural model features to improve overall detection performance.
Applying this approach, the team was able to achieve 85% accuracy on private test setsπŸš€

πŸ₯‰The third-place team achieved 82% accuracy, beating our baseline (81% accuracy).

The details on the competition will be described in a paper included in AINL proceedings, stay tuned!
πŸ”₯14❀1πŸ‘1
Dear colleagues, we are starting to publish the videos from the conference. The first one is:

Danil Kovalevsky - From Papers To Peers: LLM-based Algorithm For Selecting Reviewers

VK Video

YouTube
πŸ”₯11
Roman Derunets - Knowledge as Recollection: Advancing Multimodal Retrieval-Augmented Generation

Roman is from Siberian Neuronets, our gold sponsor.

VK Video

YouTube
πŸ”₯13❀1πŸ‘1
Anna Latushko - RuMathBERT: A Russian-Language Model for Mathematical Formula Interpretation

VK Video

YouTube
πŸ”₯11❀6
Artyom Iudin - Clarispeech: LLM-Enhanced Speech Recognition Post-Correction

VK Video

YouTube
πŸ‘3
Ivan Bychkov - Efficient Tokenization: Balancing BabyMMLU, Fertility and Speed

VK Video

YouTube
πŸ‘3
Dmitry Morozov - Transformer-based approaches for lemmatizing abbreviations in Russian texts

VK Video

YouTube
πŸ‘6πŸ”₯1
Dear colleagues, today we present you video from invited speaker Natalia Loukashevitch.

Neural Information Retrieval: Methods and Evaluation

VK Video

YouTube
πŸ‘9πŸ‘1
Dear colleagues, today we present a talk from Svetlana Gorovaya named CleanComedy: Creating Friendly Humor through Generative Techniques. This paper is co-authored with our sponsor MTS AI's employees.

VK Video

YouTube
πŸ”₯6
Dear colleagues, we are glad to present you recording of panel discussion with invited speakers Sergey Markov and Natalia Loukashevitch, a researcher from Siberian Neuronets Ivan Bondarenko and AINL Chair Valentin Malykh. The discussion is devoted to AI development in recent years, its place in educational system and the future of AI conferences. The discussion is in Russian.

VK Video

YouTube
πŸ‘12
Maxim Stavtsev - Pattern Recognition in Process Models Using Convolutional Neural Networks

VK Video

YouTube
πŸ”₯2
Boris Malashenko - Leveraging Large Language Models For Scalable Vector Graphics Processing: A Review

VK Video

YouTube
πŸ”₯4❀‍πŸ”₯1πŸ‘1πŸ’˜1
Maxim Stavtsev - NLP-Based .NET CLR Event Logs Analyzer

VK Video

YouTube
Fedor Sadkovskii - Fine-tuning Large Language Models for Hypernym Discovery Task: Sister Terms Do Their Part

VK Video

YouTube