Simra Shahid
@its_sshahid
AI Researcher at Microsoft | ex-Adobe
We need to talk about Shark Tank India. I think the controversy and memes around sharks are obscuring the show's potential! #SharkTankIndia #InnovationForEveryone #startupindia linkedin.com/posts/simrasha…
This is going front and center on my desk!! Done > Perfect. The ‘shouldn’t this be done this way?’ crowd might lose sleep over this one 😂
My daily reminder
We asked 28 industry professionals about prompt engineering practices for deployment. Most of them spend a lot of time correcting overlooked instructions, leading to inconsistent outputs through trial and error. @ishikaajoshii & I built a tool to streamline this.
#IUI2025 Acceptance Announcement 🧐 Are all your instructions in the prompt being following by the language model? Which instructions are failing more than others? 👉 Introducing CoPrompter! 🧵
📢Thrilled to introduce the #VirtualLab: a team of AI scientist agents (AI chemist, AI reviewer...). Virtual Lab is led by an AI professor w/ feedback from human scientist. The Lab created new nanobodies that we experimentally validated to bind to recent #covid variants🚀🧵
Meet Context Autopilot It learns like you, thinks like you, and uses tools like you. With SoTA context understanding, it's capable of most information work today. Watch it beat a team of industry experts:
This is the best paper written so far about the impact of AI on scientific discovery
At @COLM_conf this week, check out our paper (presented by @CarlEdwards_NLP) on LLM-based drug synergy hypothesis generation. Predicting synergistic combination therapies given specific tumor information, and generating/retrieving drugs optimized to synergize in the context of…
I'm excited to see how our work on research ideation with analogous facets and idea novelty evaluation will continue to evolve! It was a great experience collaborating with the team. @marissa_rad @Hoper_Tom @dsweld @Siangliulue @rayrayfok
Our new human-AI scientific ideation system with LLMs. One thing I'm excited about here is our continued work on improving novelty assessment with retrieval-augmented LLMs, in a way that helps not only LLMs, but also humans, to better assess novelty of LLM-generated ideas. It's…
Looking for a better way to brainstorm research ideas? Scideator is a versatile tool that uses retrieval-augmented LLMs to help researchers generate, evaluate, and improve novel ideas.
Can recombining aspects of analogous papers and your own interests help you find your next research project? Introducing Scideator 🧪💡, a mixed-initiative tool for scientific ideation that works with you to generate ideas 🔀 and evaluate/improve their novelty 🔍.
📢📢#AAAI24 Announcement Paper #13746 Introducing Counterfactually Aware Fair InferencE (CAFIE), plug-and-play, inference-time framework, to generate fair and equitable outputs. Wonderful collaboration w @PragyanB, @JandialSurgan, @Simcyy, @ShazF, @KbalajiTweets, and @sbhatia_
[CL] All Should Be Equal in the Eyes of Language Models: Counterfactually Aware Fair Text Generation P Banerjee, A Java, S Jandial, S Shahid, S Furniturewala, B Krishnamurthy, S Bhatia [Adobe] (2023) arxiv.org/abs/2311.05451 - Proposes CAFIE, a framework to generate fair text…
Our work "HyHTM - Hyperbolic Geometry based Hierarchical Topic Model" is accepted at the Findings of #ACL2023! Kudos to my co-authors Tanay Anand, Nikitha Srikanth, @sbhatia_, @NikaashPuri, @KbalajiTweets. #ACL2023 #NLProc
It feels surreal and is an absolute honor to be nominated for Adobe's Outstanding Young Engineer Award! I wanted to take this opportunity to thank everyone who helped me achieve this milestone in the attached post. linkedin.com/pulse/adobes-o…
5 women led tech #startups were provided #incubation support through #AICTE in Carleton University Canada, who returned and shared their experience & conviction to create #employment opportunity to our youth says Prof. Anil D. Sahasrabudhe, Chairman, AICTE facebook.com/anil.sahasrabu…