Stream of Search (SoS): Learning to Search in Language
Paper
β’
2404.03683
β’
Published
β’
29
Nicolay Rusnachenko
nicolay-r
AI & ML interests
Information Retrievalγ»Medical Multimodal NLP (πΌ+π) Research Fellow @BU_Researchγ»software developer http://arekit.ioγ»PhD in NLP
Recent Activity
posted
an
update
3 days ago
π’ Through the 2024 we attempting in advancing opinion mining by proposing evaluation which involves explanations!
A while ago we launched RuOpinionNE-2024 aimed at extraction of sentiment opinions with spans (as explanations) from mass media news written in Russian language. The formed competition is at the final stage on codalab platform:
π https://codalab.lisn.upsaclay.fr/competitions/20244
π What we already observe? For the two type of sentiment labels (positive and negative), our recent findings were that the top performing submission results in F1=0.34 while the baseline LLM approach results in F1=0.17 (see screenshot of the leaderboard below πΈ)
β°οΈ We finally launch the final stage with a decent amount of submissions which lasts until
15th of January 2025.
π Everyone who wish to evaluate most recent advances on explainable opinion mining during the final stage are welcome!
Codalab main page:
https://codalab.lisn.upsaclay.fr/competitions/20244#learn_the_details
More details on github:
https://github.com/dialogue-evaluation/RuOpinionNE-2024
replied to
as-cle-bert's
post
4 days ago
I got my GitHub Wrapped for 2024 today!π₯
Get yours here on HuggingFace π https://huggingface.co/spaces/as-cle-bert/what-a-git-year
GitHub repo with the code to reproduce it π https://github.com/AstraBert/what-a-git-year
Hope that everybody had a Git year!π
reacted
to
davanstrien's
post
with β€οΈ
7 days ago
πΈπ° Hovorte po slovensky? Help build better AI for Slovak!
We only need 90 more annotations to include Slovak in the next Hugging Face FineWeb2-C dataset (https://huggingface.co/datasets/data-is-better-together/fineweb-c) release!
Your contribution will help create better language models for 5+ million Slovak speakers.
Annotate here: https://huggingface.co/spaces/data-is-better-together/fineweb-c.
Read more about why we're doing it: https://huggingface.co/blog/davanstrien/fineweb2-community
Organizations
None yet
nicolay-r's activity
upvoted
2
papers
19 days ago
upvoted
an
article
19 days ago
Article
Reverse Thinking Makes LLMs Stronger Reasoners
By
β’
β’
2
upvoted
an
article
3 months ago
Article
SeeMoE: Implementing a MoE Vision Language Model from Scratch
By
β’
β’
34
upvoted
a
paper
3 months ago
upvoted
a
collection
5 months ago
upvoted
2
papers
7 months ago
upvoted
an
article
8 months ago
Article
Vision Language Models Explained
β’
238
upvoted
an
article
9 months ago
Article
Fine-tune Llama 3 with ORPO
By
β’
β’
230
upvoted
8
papers
9 months ago
RuSentNE-2023: Evaluating Entity-Oriented Sentiment Analysis on Russian News Texts
Paper
β’
2305.17679
β’
Published
β’
1
Large Language Models in Targeted Sentiment Analysis
Paper
β’
2404.12342
β’
Published
β’
2
Visual CoT: Unleashing Chain-of-Thought Reasoning in Multi-Modal Language Models
Paper
β’
2403.16999
β’
Published
β’
4
RegionGPT: Towards Region Understanding Vision Language Model
Paper
β’
2403.02330
β’
Published
β’
2
Griffon v2: Advancing Multimodal Perception with High-Resolution Scaling and Visual-Language Co-Referring
Paper
β’
2403.09333
β’
Published
β’
14
Ferret-v2: An Improved Baseline for Referring and Grounding with Large Language Models
Paper
β’
2404.07973
β’
Published
β’
30
Rho-1: Not All Tokens Are What You Need
Paper
β’
2404.07965
β’
Published
β’
87
OmniFusion Technical Report
Paper
β’
2404.06212
β’
Published
β’
74