@AbishKamran
Abish Kamran
@AbishKamran
Web Developer | AI/ML Enthusiast
Joined January 2023
About
Nothing here yet.
Available for
Nothing here yet.
Abish Kamran's blogs
Recently published
Deeper Transformers Are Forgetting What They Learned. MoDA Is the Fix.
Mar 25 · 18 min read · Papers I'm Reading — Issue #03 Paper: Mixture-of-Depths Attention (MoDA) arXiv: 2603.15619 | cs.LG Authors: Lianghui Zhu, Yuxin Fang, Bencheng Liao et al. — Huazhong University of Science & Technolo
Join discussion
Your Language Model Has Feelings About Your Text — And It Shows Up in the Attention Geometry
Mar 13 · 16 min read · Papers I'm Reading — Issue #02 Paper: Emotion is Not Just a Label: Latent Emotional Factors in LLM Processing arXiv: 2603.09205 | cs.CL / cs.AI / cs.LG Authors: Benjamin Reichman, Adar Avasian, Samu
Join discussion
Quantum Physics Just Showed Up in a Language Model. Here's What's Actually Going On.
Mar 10 · 10 min read · AI Research Papers I'm Reading— Issue #01 Paper: Quantum Inspired Self-Attention In A Large Language Model - arXiv:2603.03318 - TL;DR - Researchers have taken an existing language model called GPT-1
Join discussion
