Mohd Sanad Zaki Rizvi

422 posts

Mohd Sanad Zaki Rizvi

Mohd Sanad Zaki Rizvi

@sanad_maker

M.S. Thesis @ U. of Edinburgh | Previously: Google Research India, Microsoft Research India | #nlproc #NLU #AI | Thoughts my own

India 加入时间 Nisan 2015
1.8K 关注418 粉丝
置顶推文
Mohd Sanad Zaki Rizvi
Mohd Sanad Zaki Rizvi@sanad_maker·
Our paper - "GCM: A Toolkit for Generating Synthetic Code-mixed Text" has been accepted at the 16th Conference of European Chapter of the Association for Computational Linguistics @eaclmeeting in the demo paper track.
English
2
0
14
0
Mohd Sanad Zaki Rizvi
Mohd Sanad Zaki Rizvi@sanad_maker·
@Im_IrushiK I am guessing here but AWS like IaaS would be existing then. And Perl and PHP has been used for making websites and servers even Facebook started with PHP. Why do you need Docker or Kubernetes when you can build your own IaaS? And migrations/deployment can be done manually.
English
0
0
0
139
Irushi
Irushi@Im_IrushiK·
How did Elon Musk launch SpaceX in 2002 without Kubernetes, Docker or GitHub Actions?
Irushi tweet media
English
39
10
308
32.2K
Mohd Sanad Zaki Rizvi
Mohd Sanad Zaki Rizvi@sanad_maker·
🔍 Key takeaways: ✅ Faithful decoding + ReAct = better answer accuracy & recall across datasets. ✅ Thought-Action-Observation flows improve with these decoders. ✅ DoLa decoder on HotpotQA? Answer F1 ↑ 13.1 points! 📈 Better decoding = more reliable LLMs! 💡 2\n
English
1
0
2
79
Mohd Sanad Zaki Rizvi
Mohd Sanad Zaki Rizvi@sanad_maker·
🚀 New ArXiv paper alert! By combining agentic frameworks (ReAct) with smart decoders (DeCoRe, DoLa, CAD), we boost factual accuracy in complex reasoning tasks —reducing those annoying hallucinations! 🔥 🔗 Paper: arxiv.org/abs/2503.23415 1\n
English
1
5
9
644
Mohd Sanad Zaki Rizvi
Mohd Sanad Zaki Rizvi@sanad_maker·
I’m thrilled to share that I’ve graduated with Distinction from the M.S. Speech & Language Processing (NLP & AI) program at The University of Edinburgh @EdinburghNLP (1/n)
Mohd Sanad Zaki Rizvi tweet media
English
7
0
17
270