Zi Wang, Ph.D.
@ziwphd
Followers
1K
Following
340
Media
21
Statuses
104
Research Scientist @ Google DeepMind. CS PhD @ MIT CSAIL. Opinions my own. https://t.co/UJRqylN2Df
Cambridge, MA
Joined September 2013
RT @GoogleResearch: Meet Zi Wang & Meera Hahn who will be at the #ICML2025 Google booth at 9:30am to demo a novel AI agent for text-to-imag….
0
9
0
RT @NithishKannen: Say hi 👋to @ziwphd ,@MeeraHahn, @_beenkim, Wenjun Zeng and Rich Galt at #ICML2025 if you're interested in learning more….
arxiv.org
User prompts for generative AI models are often underspecified, leading to a misalignment between the user intent and models' understanding. As a result, users commonly have to painstakingly...
0
4
0
Our work on proactive text-to-image agents – enabling them to ask for clarification and share their understanding – has been accepted at #ICML2025! So proud of the team's efforts. See you in Vancouver! 🙌.
Check out our tech report on proactive T2I agents that ask clarification questions to reduce uncertainty!. With this agent, we obtain 2 times higher VQAScore in just 5 turns!🤯 We've open-sourced our agent code powered by #Gemini @GoogleDeepMind! 🚀. Code:
1
7
20
RT @NithishKannen: Proactive T2I Agents is accepted to #ICML2025 🚀. We show it is possible to significantly improve multimodal generation (….
0
5
0
RT @GeminiApp: 📣 Deep Research is now powered by Gemini 2.5 Pro, our most intelligent AI model. ✨. This upgraded Deep Research is now even….
0
467
0
Thrilled and grateful for the invitation from @HDRUNDP to share our research on proactive AI. Such a valuable opportunity to discuss its potential impact on creating beneficial AI for all - insights that hopefully resonate with the UN Human Development Report!.
We are grateful to @ziwphd of @GoogleDeepMind for sharing insights from her research on proactive agents for more accessible and inclusive human-#AI co-creation and its broader implications for creating beneficial AI that serves a diverse global community.
0
3
13
RT @GoogleDeepMind: Gemini 2.0 is now available to everyone. ✨. ⚡ Start using an updated 2.0 Flash in @Google AI Studio, @GoogleCloud’s #Ve….
0
382
0
RT @NithishKannen: Check out our tech report on proactive T2I agents that ask clarification questions to reduce uncertainty!. With this ag….
0
22
0
RT @GoogleDeepMind: Today, we’re announcing Veo 2: our state-of-the-art video generation model which produces realistic, high-quality clips….
0
1K
0
RT @jasonbaldridge: Whisk is a really fun and compelling new way to prompt our Imagen 3 model. You upload images that have subject, scene o….
0
1
0
RT @ariel_anders: After two incredible years at Waymo, this Thursday will be my last day. I'm excited to start a new adventure! If you know….
0
2
0
#neurips Bayesian Decision-making and Uncertainty workshop happening now at East Room 8 now! @NeurIPSConf We thank @Meta and @Google for the generous sponsorship for supporting student travel!
1
5
6
Many thanks to @MeeraHahn , Wenjun Zeng, Nithish Kannen, Rich Galt, Kartikeya Badola, @_beenkim for making this happen! Stay tuned for code release!.
0
1
5
Tired of endless prompt tweaking? We've released a tech report on proactive text-to-image agents powered by #Gemini @GoogleDeepMind! Our agents ask clarifying questions and use belief graphs to understand what you really want.
1
5
17
RT @bankes_william: It was a really amazing experience to present a poster at #NeurIPS2024. Lot's of interesting questions on potential app….
0
3
0
RT @ilijabogunovic: Had a great discussion about our REDUCER paper at #NeurIPS2024. Kudos to @bankes_william and @ziwphd for their incredib….
0
2
0
#NeurIPS2024 Today, I'll present HyperBO at East Exhibit Hall A-C #4206 on behalf on collaborators @GoogleDeepMind and @bankes_william @ilijabogunovic will present REDUCR for robust data downsampling at #1904. See you there!.
0
0
9