iiinova — where your digital self keeps evolving

Cathy Wu @cathywu.bsky.social · 08/04/2026

Huge thanks to MIT JTL-Transit Lab for their leadership in forming this program, and for the contributing mentors from my group: Han Zheng Jung-Hoon Cho Yining Ma Wenbin Ouyang Tianyue Zhou

020

Cathy Wu @cathywu.bsky.social · 08/04/2026

Interviews will be held from April 18 to 30, and the program will run from late May to early September. More information and application can be found here, including mentors and specific research topic areas from my group: www.wucathy.com/prospective/

110

Cathy Wu @cathywu.bsky.social · 08/04/2026

Past participants have contributed to impactful research projects across urban systems, operations research, machine learning, and generative AI, with outcomes including top publications and admission to leading graduate programs.

110

Cathy Wu @cathywu.bsky.social · 08/04/2026

This summer program brings together faculty and mentors across MIT, UF, and Northeastern to support students interested in transportation, urban planning, machine learning, generative AI, and optimization for complex systems. The program will be held online and is completely free of charge.

120

Cathy Wu @cathywu.bsky.social · 08/04/2026

I am happy to announce that for the first time my group is participating in the MIT-UF-NEU 2026 Joint Summer Research Camp. Applications are open until April 17. More info in thread and here: www.wucathy.com/prospective/

111

Cathy Wu @cathywu.bsky.social · 27/03/2026

This wouldn't have been possible without an amazing team. Huge shoutout to Han Zheng (lead author), Yining Ma, Brandon Araki, Jingkai Chen, and Symbotic! #DeepRL #Robotics #WarehouseAutomation #AI

010

Cathy Wu @cathywu.bsky.social · 27/03/2026

Deep RL learns high-level right-of-way priorities, while a fast search solver takes care of low-level path planning. This prevents gridlock on the warehouse floor, achieving ~25% more throughput than hand-crafted rules.

100

Cathy Wu @cathywu.bsky.social · 27/03/2026

If pure AI or pure search isn't working for you, consider learning-guided optimization! This approach combines the best of both worlds; our most recent work demonstrates this for coordinating agents in warehouse robotics.

130

Reposted by Cathy Wu

David Zipper @davidzipper.bsky.social · 17/03/2026

MIT prof @cathywu.bsky.social suspected that nav apps inaccurately calculate “time to arrive,” esp re: parking. In a new paper, she and colleagues built a model to direct urban drivers to garages that best balance proximity and likelihood of an open spot. Result: Drivers could save up to 35 min.

news.mit.edu

Parking-aware navigation system could prevent frustration and emissions

By minimizing the need to drive around looking for a parking spot, this technique can save drivers up to 35 minutes — and give them a realistic estimate of total travel time.

1395

Cathy Wu @cathywu.bsky.social · 23/02/2026

Great fun (and great exercise) this morning with Omar shoveling out the driveway. * Sorry to explain the reference, but friends will know that I've been very interested in eco-driving and its policy implications. news.mit.edu/2025/eco-dri...

news.mit.edu

Eco-driving measures could significantly reduce vehicle emissions

Implementing co-driving techniques, like the use of intelligent speed controls to mitigate congestion at traffic lights, can significantly reduce intersection carbon dioxide emissions without impactin...

000

Cathy Wu @cathywu.bsky.social · 23/02/2026

What's an energy-efficient way to shovel snow? Introducing eco-shoveling*, a two-stage technique to handle snow accumulation, while conserving energy in preparation for more shoveling later... Built to withstand three winter storms.

110

Cathy Wu @cathywu.bsky.social · 22/02/2026

Yeah I think it varies based on context, like big city vs suburbia.

000

Cathy Wu @cathywu.bsky.social · 22/02/2026

Did something happen to the “my bangers” feed of your top bluesky posts? Is there an alternative?

100

Reposted by Cathy Wu

David Zipper @davidzipper.bsky.social · 20/02/2026

New research from @cathywu.bsky.social et al. confirms something I've long suspected: Navigation apps could save their users a lot of time — and tilt travel decisions toward transit and biking — if they showed users how long it takes to find parking.

news.mit.edu

Parking-aware navigation system could prevent frustration and emissions

By minimizing the need to drive around looking for a parking spot, this technique can save drivers up to 35 minutes — and give them a realistic estimate of total travel time.

1130183

Cathy Wu @cathywu.bsky.social · 19/02/2026

That's an interesting suggestion!

010

Cathy Wu @cathywu.bsky.social · 19/02/2026

Our resulting paper, Probability-Aware Parking Selection, shows that doing so can improve travel time estimates, save drivers time by routing them to parking, and make for fairer comparisons across transportation modes! And this work is featured today on the MIT Home Page!

191

Cathy Wu @cathywu.bsky.social · 19/02/2026

Have you noticed how navigation apps include walking & waiting for public transit, but excludes parking & walking for driving? After being late a few times 😅, we finally did. We got curious: what if these apps account for parking?

67934

Cathy Wu @cathywu.bsky.social · 03/02/2026

Please share with anyone who might be a great fit!

000

Cathy Wu @cathywu.bsky.social · 03/02/2026

Join us in our mission to use 𝗔𝗜/𝗠𝗟 𝘁𝗼 𝘁𝗮𝗰𝗸𝗹𝗲 𝗵𝗮𝗿𝗱 𝗼𝗽𝘁𝗶𝗺𝗶𝘇𝗮𝘁𝗶𝗼𝗻 𝗽𝗿𝗼𝗯𝗹𝗲𝗺𝘀 and to enable 𝗯𝗲𝘁𝘁𝗲𝗿, 𝗲𝘃𝗶𝗱𝗲𝗻𝗰𝗲-𝗱𝗿𝗶𝘃𝗲𝗻 𝗱𝗲𝗰𝗶𝘀𝗶𝗼𝗻𝘀 𝗶𝗻 𝗿𝗲𝗮𝗹-𝘄𝗼𝗿𝗹𝗱 𝘀𝗼𝗰𝗶𝗼𝘁𝗲𝗰𝗵𝗻𝗶𝗰𝗮𝗹 𝘀𝘆𝘀𝘁𝗲𝗺𝘀. 🗓️ Applications are reviewed 𝗼𝗻 𝗮 𝗿𝗼𝗹𝗹𝗶𝗻𝗴 𝗯𝗮𝘀𝗶𝘀, starting immediately. 🔗 Details + how to apply: cathywu.github.io/prospective

cathywu.github.io

Prospective Members

Faster, evidence-based decisions for sociotechnical systems

100

Cathy Wu @cathywu.bsky.social · 03/02/2026

📣 𝗣𝗼𝘀𝘁𝗱𝗼𝗰 𝗼𝗽𝗲𝗻𝗶𝗻𝗴𝘀 𝗶𝗻 𝗺𝘆 𝗴𝗿𝗼𝘂𝗽! I’m looking to hire 𝟭–𝟮 𝗽𝗼𝘀𝘁𝗱𝗼𝗰𝘀 to work with us across the group’s research areas, including: 🤖 Deep reinforcement learning 🚦 Traffic modeling & control 🧠 Neural combinatorial optimization

cathywu.github.io

Prospective Members

Faster, evidence-based decisions for sociotechnical systems

1107

Reposted by Cathy Wu

Jack Stilgoe @jackstilgoe.bsky.social · 05/09/2025

I'm gearing up for next week's Hype Studies conference in Barcelona, so I'm thinking about this stuff a lot. @davekarpf.bsky.social makes some great points here, but there's a 'Yes and...'

davekarpf.substack.com

Tesla's Roadmap to Nowhere

I'll give him this: Elon Musk has a solid grasp of futurity-as-PR.

1195

Cathy Wu @cathywu.bsky.social · 29/08/2025

Yeah, same deal with navigating a city thanks to google maps

110

Cathy Wu @cathywu.bsky.social · 19/08/2025

I think it goes beyond cost. There’s also talent and the know-how to adapt & implement the tech. For example, I don’t think the public sector has caught up on the last bunch of waves of tech yet, despite it getting commoditized. In general, I think it’s the rich getting richer phenomenon.

110

Cathy Wu @cathywu.bsky.social · 18/08/2025

I've been struggling with this since realizing that the rich and powerful get first dibs on new tech. The only way I've been able to resolve the issue for myself is to deliberately work on applications for the public interest.

190

Cathy Wu @cathywu.bsky.social · 18/08/2025

do you mean cost-benefit of research that's already done?

100

Cathy Wu @cathywu.bsky.social · 18/08/2025

We should be asking ourselves more what research should be done vs what research can be done

1256

Cathy Wu @cathywu.bsky.social · 12/08/2025

🔥 New workshop at @neuripsconf.bsky.social! DiffCoALG bridges the gap between classic algorithms & differentiable learning. Think: LLM reasoning, routing, SAT, MIP — neurally optimized. 📌 Submit by Aug 22! 🤖🧠 🔗 sites.google.com/view/diffcoa... #NeurIPS2025

sites.google.com

DiffCoALG@NeurIPS 2025

About this Workshop Combinatorial algorithms are fundamental across a wide range of domains, owing to their ability to model optimization and decision-making tasks under complex constraints. These alg...

1104

Cathy Wu @cathywu.bsky.social · 11/08/2025

This work would not have been possible without lead author @vindulaj.bsky.social and collaborators Baptiste Freydt, Ao Qu, Cameron Hickert, Edgar Sanchez, Catherine Tang, Mark Taylor, Blaine Leonard, as well as the financial support of UDOT, NSF, and Amazon AWS, and support from MIT SuperCloud.

030

Cathy Wu @cathywu.bsky.social · 11/08/2025

Website: vindulamj.github.io/eco-drive/ Published paper: www.sciencedirect.com/science/arti... Pre-print: arxiv.org/abs/2408.05609

160

Cathy Wu @cathywu.bsky.social · 11/08/2025

This project was 4 years in the making and it's finally out! We found that controlling vehicle speeds to mitigate traffic across a city can cut carbon emissions between 11 and 22 percent. To do this, we used deep reinforcement learning to optimize one million eco-driving scenarios. 🚗🤖🧠

15217

Reposted by Cathy Wu

MIT CEE @mitcee.bsky.social · 11/08/2025

A new study led by Prof. Cathy Wu and colleagues reveals that eco-driving measures, such as dynamically adjusting vehicle speeds to reduce stopping and excessive acceleration, can cut carbon emissions between 11 and 22 percent. news.mit.edu/2025/eco-dri...

news.mit.edu

Eco-driving measures could significantly reduce vehicle emissions

Implementing co-driving techniques, like the use of intelligent speed controls to mitigate congestion at traffic lights, can significantly reduce intersection carbon dioxide emissions without…

022

Cathy Wu @cathywu.bsky.social · 05/08/2025

We’ve got an awesome workshop tomorrow at RLC on real-world RL! Also, I’m moderating the panel, so let me know if you have questions about applying RL. 🤖🧠🤖

030

Reposted by Cathy Wu

Reinforcement Learning Conference @rl-conference.bsky.social · 25/06/2025

Propose some socials for RLC! Research topics, affinity groups, niche interests, whatever comes to mind! rl-conference.cc/call_for_soc...

rl-conference.cc

RLC Call for Workshops

0118

Reposted by Cathy Wu

Nathan Lambert @natolambert.bsky.social · 23/06/2025

Trying to make Ai2 so effective that people start seriously referring to us as "American DeepSeek" 🙏 lots of hard work to do.

3251

Reposted by Cathy Wu

Eugene Vinitsky 🍒 @eugenevinitsky.bsky.social · 21/06/2025

Hiring a postdoc to scale up and deploy RL-based planning onto some self-driving cars! We'll be building on arxiv.org/abs/2502.03349 and learn what the limits and challenges of RL planning are. Shoot me a message if interested and help spread the word please! Full posting to come in a bit.

arxiv.org

Robust Autonomy Emerges from Self-Play

Self-play has powered breakthroughs in two-player and multi-player games. Here we show that self-play is a surprisingly effective strategy in another domain. We show that robust and naturalistic drivi...

36025

Cathy Wu @cathywu.bsky.social · 13/06/2025

I’ll consider it! Been meaning to start a blog and maybe this is just the push I needed!

030

Cathy Wu @cathywu.bsky.social · 09/06/2025

This is soooooo fun and so blazingly fast.

000

Cathy Wu @cathywu.bsky.social · 04/06/2025

I found this insightful and wonder what you think: “If the objective of meta-science is to determine what are the good ways to perform science, it immediately runs into a major methodological hurdle: it is necessarily going to beg the question.”

120

Cathy Wu @cathywu.bsky.social · 04/06/2025

Feeling like a fish learning about water. Insightful thread

020

Cathy Wu @cathywu.bsky.social · 04/06/2025

#metasci or should I say meta metascience

030

Cathy Wu @cathywu.bsky.social · 04/06/2025

I’m incredibly happy to have found metascience bluesky. Science is messy and beautiful, and there is a group of people thinking hard about how and why.

1191

Cathy Wu @cathywu.bsky.social · 03/06/2025

I’m pretty shocked. I was just appointed to a serve on a standing committee in April. TRB has definitely helped me find my footing in the field.

060

Reposted by Cathy Wu

Carole Voulgaris @voulgaris.bsky.social · 02/06/2025

Organizations and conferences that have the potential to partially fill the void left by TRB (a thread):

61911

Cathy Wu @cathywu.bsky.social · 02/06/2025

I would be remiss not to mention RERITE (www.rerite.org) - which was in the process of integrating into the TRB committee structure

rerite.org

REproducible Research In Transportation Engineering (RERITE) Working Group

020