Article
Tiny Agents: a MCP-powered agent in 50 lines of code
•
172
Ali El Filali PRO
alielfilali01
AI & ML interests
AI Psychometrician ? | NLP (mainly for Arabic) | Interests include Reinforcement Learning and Cognitive sciences among others
Recent Activity
upvoted
an
article
about 15 hours ago
Tiny Agents: a MCP-powered agent in 50 lines of code
reacted
to
ImranzamanML's
post
with 👍
about 15 hours ago
🚀 New paper out: "Improving Arabic Multi-Label Emotion Classification using Stacked Embeddings and Hybrid Loss Function"
https://huggingface.co./papers/2410.03979
In this work, we tackle some major challenges in Arabic multi-label emotion classification especially the issues of class imbalance and label correlation that often hurt model performance, particularly for minority emotions.
Our approach:
Stacked contextual embeddings from fine-tuned ArabicBERT, MarBERT, and AraBERT models.
A meta-learning strategy that builds richer representations.
A hybrid loss function combining class weighting, label correlation matrices, and contrastive learning to better handle class imbalances.
🧠 Model pipeline: stacked embeddings → meta-learner → Bi-LSTM → fully connected network → multi-label classification.
🔍 Extensive experiments show significant improvements across Precision, Recall, F1-Score, Jaccard Accuracy, and Hamming Loss.
🌟 The hybrid loss function in particular helped close the gap between majority and minority classes!
We also performed ablation studies to break down each component’s contribution and the results consistently validated our design choices.
This framework isn't just for Arabic it offers a generalizable path for improving multi-label emotion classification in other low-resource languages and domains.
Big thanks to my co-authors: Muhammad Azeem Aslam, Wang Jun, Nisar Ahmed, Li Yanan, Hu Hongfei, Wang Shiyu, and Xin Liu!
Would love to hear your thoughts on this work! 👇
reacted
to
ImranzamanML's
post
with 🧠
about 15 hours ago
🚀 New paper out: "Improving Arabic Multi-Label Emotion Classification using Stacked Embeddings and Hybrid Loss Function"
https://huggingface.co./papers/2410.03979
In this work, we tackle some major challenges in Arabic multi-label emotion classification especially the issues of class imbalance and label correlation that often hurt model performance, particularly for minority emotions.
Our approach:
Stacked contextual embeddings from fine-tuned ArabicBERT, MarBERT, and AraBERT models.
A meta-learning strategy that builds richer representations.
A hybrid loss function combining class weighting, label correlation matrices, and contrastive learning to better handle class imbalances.
🧠 Model pipeline: stacked embeddings → meta-learner → Bi-LSTM → fully connected network → multi-label classification.
🔍 Extensive experiments show significant improvements across Precision, Recall, F1-Score, Jaccard Accuracy, and Hamming Loss.
🌟 The hybrid loss function in particular helped close the gap between majority and minority classes!
We also performed ablation studies to break down each component’s contribution and the results consistently validated our design choices.
This framework isn't just for Arabic it offers a generalizable path for improving multi-label emotion classification in other low-resource languages and domains.
Big thanks to my co-authors: Muhammad Azeem Aslam, Wang Jun, Nisar Ahmed, Li Yanan, Hu Hongfei, Wang Shiyu, and Xin Liu!
Would love to hear your thoughts on this work! 👇
Organizations
alielfilali01's activity
upvoted
an
article
about 15 hours ago
reacted to
ImranzamanML's
post with 👍🧠
about 15 hours ago
Post
2660
🚀 New paper out: "Improving Arabic Multi-Label Emotion Classification using Stacked Embeddings and Hybrid Loss Function"
Improving Arabic Multi-Label Emotion Classification using Stacked Embeddings and Hybrid Loss Function (2410.03979)
In this work, we tackle some major challenges in Arabic multi-label emotion classification especially the issues of class imbalance and label correlation that often hurt model performance, particularly for minority emotions.
Our approach:
Stacked contextual embeddings from fine-tuned ArabicBERT, MarBERT, and AraBERT models.
A meta-learning strategy that builds richer representations.
A hybrid loss function combining class weighting, label correlation matrices, and contrastive learning to better handle class imbalances.
🧠 Model pipeline: stacked embeddings → meta-learner → Bi-LSTM → fully connected network → multi-label classification.
🔍 Extensive experiments show significant improvements across Precision, Recall, F1-Score, Jaccard Accuracy, and Hamming Loss.
🌟 The hybrid loss function in particular helped close the gap between majority and minority classes!
We also performed ablation studies to break down each component’s contribution and the results consistently validated our design choices.
This framework isn't just for Arabic it offers a generalizable path for improving multi-label emotion classification in other low-resource languages and domains.
Big thanks to my co-authors: Muhammad Azeem Aslam, Wang Jun, Nisar Ahmed, Li Yanan, Hu Hongfei, Wang Shiyu, and Xin Liu!
Would love to hear your thoughts on this work! 👇
Improving Arabic Multi-Label Emotion Classification using Stacked Embeddings and Hybrid Loss Function (2410.03979)
In this work, we tackle some major challenges in Arabic multi-label emotion classification especially the issues of class imbalance and label correlation that often hurt model performance, particularly for minority emotions.
Our approach:
Stacked contextual embeddings from fine-tuned ArabicBERT, MarBERT, and AraBERT models.
A meta-learning strategy that builds richer representations.
A hybrid loss function combining class weighting, label correlation matrices, and contrastive learning to better handle class imbalances.
🧠 Model pipeline: stacked embeddings → meta-learner → Bi-LSTM → fully connected network → multi-label classification.
🔍 Extensive experiments show significant improvements across Precision, Recall, F1-Score, Jaccard Accuracy, and Hamming Loss.
🌟 The hybrid loss function in particular helped close the gap between majority and minority classes!
We also performed ablation studies to break down each component’s contribution and the results consistently validated our design choices.
This framework isn't just for Arabic it offers a generalizable path for improving multi-label emotion classification in other low-resource languages and domains.
Big thanks to my co-authors: Muhammad Azeem Aslam, Wang Jun, Nisar Ahmed, Li Yanan, Hu Hongfei, Wang Shiyu, and Xin Liu!
Would love to hear your thoughts on this work! 👇
liked
a
dataset
3 days ago
upvoted
a
paper
3 days ago
reacted to
shekkizh's
post with ❤️
5 days ago
Post
1839
Think AGI is just around the corner? Not so fast.
When OpenAI released its Computer-Using Agent (CUA) API, I happened to be playing Wordle 🧩 and thought, why not see how the model handles it?
Spoiler: Wordle turned out to be a surprisingly effective benchmark.
So Romain Cosentino Ph.D. and I dug in and analyzed the results of several hundred runs.
🔑 Takeaways
1️⃣ Even the best computer-using models struggle with simple, context-dependent tasks.
2️⃣ Visual perception and reasoning remain major hurdles for multimodal agents.
3️⃣ Real-world use cases reveal significant gaps between hype and reality. Perception accuracy drops to near zero by the last turn 📉
🔗 Read our arxiv article for more details https://www.arxiv.org/abs/2504.15434
When OpenAI released its Computer-Using Agent (CUA) API, I happened to be playing Wordle 🧩 and thought, why not see how the model handles it?
Spoiler: Wordle turned out to be a surprisingly effective benchmark.
So Romain Cosentino Ph.D. and I dug in and analyzed the results of several hundred runs.
🔑 Takeaways
1️⃣ Even the best computer-using models struggle with simple, context-dependent tasks.
2️⃣ Visual perception and reasoning remain major hurdles for multimodal agents.
3️⃣ Real-world use cases reveal significant gaps between hype and reality. Perception accuracy drops to near zero by the last turn 📉
🔗 Read our arxiv article for more details https://www.arxiv.org/abs/2504.15434
- 3 replies
updated
a
dataset
5 days ago
liked
a
model
7 days ago
updated
a
Space
11 days ago
upvoted
an
article
12 days ago
Article
Introducing the Open Chain of Thought Leaderboard
•
33
upvoted
a
collection
12 days ago
liked
2
datasets
12 days ago
updated
a
dataset
13 days ago
published
a
Space
14 days ago
upvoted
an
article
19 days ago
Article
Arabic Leaderboards: Introducing Arabic Instruction Following, Updating AraGen, and More
By
and 5 others
•
•
16
published
an
article
21 days ago
Article
Arabic Leaderboards: Introducing Arabic Instruction Following, Updating AraGen, and More
By
and 5 others
•
•
16
upvoted
a
collection
23 days ago