Manaswi Saha
@manaswisaha
Followers
1K
Following
4K
Media
74
Statuses
1K
HCI Research Scientist @Accenture Labs | PhD @uwcse | AI, AR, #a11y, urbantech | Prev: Google PhD Fellow, @ADSKresearch, @MSFTResearch, @AdobeResearch, @umdcs
San Francisco, CA
Joined January 2010
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 and talk video links below.
Ever feel lost in jargon while watching technical videos - and stuck trying to find clear, timely help? Check out our work at #CHI2025 on how real-time AI systems can bridge knowledge gaps without overwhelming users!
1
0
1
RT @ryosuzk: 🏆 #UIST2024 We won the Best Paper Award for Augmented Physics! . Huge congratulations to @adigunturu @nandizhang_ @Freya_Wyy @….
0
91
0
RT @AnhongGuo: 📢📢 I'm recruiting 2 PhD students this cycle to join the UMich Human-AI Lab, focusing on AI & Accessibility, and multimodal A….
0
70
0
RT @uwcse: Congratulations to @UW @uwengineering #UWAllen alum Nicola Dell (Ph.D., '15), now a faculty member at Cornell University, on her….
0
10
0
Very well deserved! I love the problem of live descriptions for the blind while making it adaptive to the sound environment! . Special interest to me as it combines the vision from my past internship work at @MSFTResearch and my current work on Audio AR at @Accenture Labs! 👏👏👏.
Our work WorldScribe led by @RueiChe on generating context-aware live visual descriptions has received 🏆✨ Best Paper Award ✨ at #UIST2024!! . Check out our new video below, and details in the thread!. Here is what NotebookLM thought about it:
1
0
13
RT @jvitak: Saw this new article @UpolEhsan shared and wanted to reshare a GoogleDoc I started last year on responding to common qualitativ….
0
26
0
We talk about a future where task guidance can be seen as a multimodal conversation where the system augments their auditory space with continuous task guidance based on the visual input coming from the scene: the future towards hands-free, eyes-free interaction. Check it out!.
0
0
0
Our specific application focus is for physical task guidance contexts where a user’s visual space is busy and we need to leverage their other senses, in this case, auditory feedback.
1
0
0
#CHI2025 writers working on papers related to Situated Conversational Agents and Audio-based AR Systems, here is our recent CUI’24 paper talking about nextgen of CAs that handle non-text inputs and outputs eg., video-to-audio. Might be relevant to some!.
2
1
19
RT @HariSubramonyam: If you are a current HCI student in the US with experience in AR/VR software development and interested in accessibili….
0
24
0
RT @projsidewalk: Huge news: using Project Sidewalk and steadfast community advocacy, Chicago's Ward 3 is fixing some high-priority sidewal….
0
2
0
RT @HariSubramonyam: 📢#CHI2024 Paper: Using tools like ChatGPT can feel like the Hot-or-Cold guessing game, finding the right prompt to get….
0
31
0
RT @MajeedKazemi: How can we design "pedagogical" LLM-powered coding assistants?. Check out our conditionally accepted #CHI2024 paper, intr….
0
14
0
RT @vsetlur: We are still looking for research interns for summer 2024. I am specifically in need of candidates who have an NLP + visual an….
0
25
0
All translations were done by native speakers from the wonderful volunteer community! . Users have mapped and assessed over 10.4k miles, contributing 900k labels and nearly 600k validations. Very happy to see my dissertation project grow to this scale! 😇.
2
0
3
.@projsidewalk, my PhD dissertation project, now deployed in 20 cities across 7 countries in the world, including the US, Mexico, Ecuador, Netherlands, Switzerland, NZ, and Taiwan, supporting 5 languages: English, Spanish, Dutch, Chinese, and German!. #a11y #research #impact
2
1
68