Manaswi Saha
@manaswisaha.bsky.social
HCI Research Scientist @ Accenture Labs | CSE PhD from UW | AI, AR, #a11y, urbantech | Prev: Google PhD Fellow, Autodesk Research, Microsoft Research, Adobe Research, UMD CS
Website: https://manaswisaha.github.io/
Twitter: https://x.com/manaswisaha
Website: https://manaswisaha.github.io/
Twitter: https://x.com/manaswisaha
Pinned
Manaswi Saha
@manaswisaha.bsky.social
· Apr 30
Exploring the Design Space of Real-time LLM Knowledge Support Systems: A Case Study of Jargon Explanations | Proceedings of the 2025 CHI Conference on Human Factors in Computing Systems
You will be notified whenever a record that you have chosen has been cited.
dl.acm.org
Exciting new work from Accenture Labs led by my summer intern on designing LLM-enabled systems for real-time knowledge assistance!
#CHI2025 in-person attendees: Join the first remote paper session on "Narratives and AI Support" -- May 1, 9 AM
Paper: dl.acm.org/doi/10.1145/...
#LLM #AI #Assistants
#CHI2025 in-person attendees: Join the first remote paper session on "Narratives and AI Support" -- May 1, 9 AM
Paper: dl.acm.org/doi/10.1145/...
#LLM #AI #Assistants
Latest work from my team at Accenture Labs around #EmpathicAI and #neurocinematics. We studied the feasibility of using neurotech with facial expression tracking to assess audience reactions during movie watching.
medium.com/@adolfo.rami...
medium.com/@adolfo.rami...
What We Say, Think, and Feel: AI & Biosensing’s Transformative Capabilities for Creators
Co-Authors: Manaswi Saha, Mirjana Spasojevic, Asher Naghi, KellyGlass
medium.com
September 2, 2025 at 6:53 PM
Latest work from my team at Accenture Labs around #EmpathicAI and #neurocinematics. We studied the feasibility of using neurotech with facial expression tracking to assess audience reactions during movie watching.
medium.com/@adolfo.rami...
medium.com/@adolfo.rami...
Latest work at Accenture Labs in our ongoing research on *Personalized AI-driven Tools for Knowledge Support in Cross-Domain Settings* #CSCW2025. We explore emerging themes on interaction models for #LLM-driven interfaces, personalized AI assistance, and #FutureOfWork w/ #AI
arxiv.org/abs/2411.09969
arxiv.org/abs/2411.09969
Steering AI-Driven Personalization of Scientific Text for General Audiences
Digital media platforms (e.g., science blogs) offer opportunities to communicate scientific content to general audiences at scale. However, these audiences vary in their scientific expertise, literacy...
arxiv.org
August 21, 2025 at 6:46 PM
Latest work at Accenture Labs in our ongoing research on *Personalized AI-driven Tools for Knowledge Support in Cross-Domain Settings* #CSCW2025. We explore emerging themes on interaction models for #LLM-driven interfaces, personalized AI assistance, and #FutureOfWork w/ #AI
arxiv.org/abs/2411.09969
arxiv.org/abs/2411.09969
Reposted by Manaswi Saha
#CHI2025
As we rely on AI for decision-making support, how will our independent decision-making skills be affected? Prior work shows people’s decision-making skills often fail to improve or may even erode when they rely on AI for decision-support, even when the AI provides informative explanations.
As we rely on AI for decision-making support, how will our independent decision-making skills be affected? Prior work shows people’s decision-making skills often fail to improve or may even erode when they rely on AI for decision-support, even when the AI provides informative explanations.
April 30, 2025 at 2:41 AM
#CHI2025
As we rely on AI for decision-making support, how will our independent decision-making skills be affected? Prior work shows people’s decision-making skills often fail to improve or may even erode when they rely on AI for decision-support, even when the AI provides informative explanations.
As we rely on AI for decision-making support, how will our independent decision-making skills be affected? Prior work shows people’s decision-making skills often fail to improve or may even erode when they rely on AI for decision-support, even when the AI provides informative explanations.
Exciting new work from Accenture Labs led by my summer intern on designing LLM-enabled systems for real-time knowledge assistance!
#CHI2025 in-person attendees: Join the first remote paper session on "Narratives and AI Support" -- May 1, 9 AM
Paper: dl.acm.org/doi/10.1145/...
#LLM #AI #Assistants
#CHI2025 in-person attendees: Join the first remote paper session on "Narratives and AI Support" -- May 1, 9 AM
Paper: dl.acm.org/doi/10.1145/...
#LLM #AI #Assistants
Exploring the Design Space of Real-time LLM Knowledge Support Systems: A Case Study of Jargon Explanations | Proceedings of the 2025 CHI Conference on Human Factors in Computing Systems
You will be notified whenever a record that you have chosen has been cited.
dl.acm.org
April 30, 2025 at 7:20 AM
Exciting new work from Accenture Labs led by my summer intern on designing LLM-enabled systems for real-time knowledge assistance!
#CHI2025 in-person attendees: Join the first remote paper session on "Narratives and AI Support" -- May 1, 9 AM
Paper: dl.acm.org/doi/10.1145/...
#LLM #AI #Assistants
#CHI2025 in-person attendees: Join the first remote paper session on "Narratives and AI Support" -- May 1, 9 AM
Paper: dl.acm.org/doi/10.1145/...
#LLM #AI #Assistants
Reposted by Manaswi Saha
📢 HUGE NEWS! Project Sidewalk just crossed 1.1 MILLION manual sidewalk accessibility annotations across 21,000+ km of streets! 🎉 (1,163,413 labels to be exact!). To celebrate and help others build on our work, we have posted a sidewalk feature/barrier dataset to @hf.co huggingface.co/projectsidew...
April 23, 2025 at 1:19 PM
📢 HUGE NEWS! Project Sidewalk just crossed 1.1 MILLION manual sidewalk accessibility annotations across 21,000+ km of streets! 🎉 (1,163,413 labels to be exact!). To celebrate and help others build on our work, we have posted a sidewalk feature/barrier dataset to @hf.co huggingface.co/projectsidew...