saikiranpennam
Message
Empirical ML researcher with 2 peer-reviewed publications and active research in mechanistic interpretability and AI safety across cross-modal systems. Hands-on experience designing end-to-end evaluation pipelines from experimental design and adversarial stress-testing through quantitative write-up with a track record of independently scoping experiments and delivering reproducible...
1
Hi, I am an aspiring AI researchers in the current LLMs, and my current interests include hallucinations, residual streams, geometry and architectural design of such autoregressive models. I have explored alternatives to attention heads (FNet, MLP Mixers, MAMBA, etc) but found out that the tokens and other earlier layers of the transformers didn't matter much with alternatives. So, I got interested in asking the question - "where does structure, geometry live in the architectural that can produce better and effective outputs?", that's when I found residual... (read more)