Saksham
@higgsboson.bsky.social
Interested in Improving Language Models, applying to PhD positions for Fall’25
Previously: Predoc at Microsoft PROSE
Currently: Zomato AI; using LMs for serving food
Previously: Predoc at Microsoft PROSE
Currently: Zomato AI; using LMs for serving food
Sorry, this isn’t something I was implying. I feel academia can also utilise some of the industry practices. I am sure that might be extremely challenging or some labs might already be working in that way.
December 26, 2024 at 4:59 PM
Sorry, this isn’t something I was implying. I feel academia can also utilise some of the industry practices. I am sure that might be extremely challenging or some labs might already be working in that way.
Interesting. In the industry for me, it’s not only close mentorship but the requirement to write good code for production. Also the reviews from peers and the need to do certain things through well maintained pipelines could lead to good programming fundamentals.
December 26, 2024 at 12:44 PM
Interesting. In the industry for me, it’s not only close mentorship but the requirement to write good code for production. Also the reviews from peers and the need to do certain things through well maintained pipelines could lead to good programming fundamentals.
After my fellowship I have also honed my engineering skills to deploy and train custom LLMs for production use-cases.
December 7, 2024 at 1:10 PM
After my fellowship I have also honed my engineering skills to deploy and train custom LLMs for production use-cases.
I have a publication at @icseconf.bsky.social I worked on personalizing decoder models with a single token. I also worked on a benchmark to evaluate how well LLMs comprehend code
arxiv.org/abs/2305.10530
huggingface.co/datasets/Hig...
arxiv.org/abs/2305.10530
huggingface.co/datasets/Hig...
Personalized action suggestions in low-code automation platforms
Automation platforms aim to automate repetitive tasks using workflows, which start with a trigger and then perform a series of actions. However, with many possible actions, the user has to search for ...
arxiv.org
December 7, 2024 at 1:10 PM
I have a publication at @icseconf.bsky.social I worked on personalizing decoder models with a single token. I also worked on a benchmark to evaluate how well LLMs comprehend code
arxiv.org/abs/2305.10530
huggingface.co/datasets/Hig...
arxiv.org/abs/2305.10530
huggingface.co/datasets/Hig...
I have always been confused about what grounding actually means.
November 21, 2024 at 3:49 AM
I have always been confused about what grounding actually means.