Lightnews — Scholar-powered news

Jorge Mendez-Mendez @jmendezm.bsky.social · 6d

Maybe "correcting" wasn't the right word. The TAMP system tells the LLM what the mistakes were (e.g., a precondition wasn't met or an object couldn't be placed) and asks the LLM to generate a new plan, in a loop.

1

Jorge Mendez-Mendez @jmendezm.bsky.social · 6d

The verdict? LLMs can't replace TAMP systems yet, especially for long-horizon, geometrically constrained tasks.

They are more promising as fast "idea generators", where a formal planner verifies their output.

Paper: arxiv.org/abs/2510.001...
Code & Data: github.com/jorge-a-mend...

1

Jorge Mendez-Mendez @jmendezm.bsky.social · 6d

More counter-intuitive insight: giving the LLM more information can hurt performance!

When the prompt included geometric details, the LLM made more PDDL errors. The extra info "distracts" the model from the logical constraints. Are these systems sensitive to prompt engineering!

1 1

Jorge Mendez-Mendez @jmendezm.bsky.social · 6d

Key finding: LLMs can solve many TAMP problems but lag behind engineered planners.

"Thinking" isn't always better! Non-reasoning LLMs outperformed reasoning ones.

Why? It's more efficient for the LLM generate plans quickly and have a formal TAMP system verify and correct them.

2 1

Jorge Mendez-Mendez @jmendezm.bsky.social · 6d

Can Large Language Models solve complex robotics problems with intricate geometric constraints? 🤖

Excited to share our preprint, "A Systematic Study of Large Language Models for Task and Motion Planning With PDDLStream"!

16 LLM planners using Gemini, 4950 TAMP problems.

🧵👇

2 2 9

Jorge Mendez-Mendez @jmendezm.bsky.social · Aug 5

I will be at @rl-conference.bsky.social this week. If you're around and would like to chat about lifelong learning, robotics, or abstractions, say hi!

bsky.app

Jorge Mendez-Mendez @jmendezm.bsky.social · Aug 5

I am looking forward to @collasconf.bsky.social next week, where I will be presenting my work and vision for lifelong robot learning through modularity.

collasconf.bsky.social @collasconf.bsky.social · Aug 5

🎉 Announcing the winners of the #CoLLAs2025 Early-Career Spotlight Program!

These rising stars are pushing the boundaries of lifelong & continual learning, adaptation, and embodied AI.

👇 A thread introducing their work & talks.

#AI #MachineLearning #ContinualLearning #LifelongLearning

2

Jorge Mendez-Mendez @jmendezm.bsky.social · Jul 27

Looking forward to seeing folks at @collasconf.bsky.social in Philly in a couple of weeks!

collasconf.bsky.social @collasconf.bsky.social · Jul 27

📢 2 weeks until #CoLLAs2025!

Here’s what you need to make the most of it

🗓 Program: lifelong-ml.cc/Conferences/...

✅ Papers: lifelong-ml.cc/Conferences/...

📍 Venue: lifelong-ml.cc/Conferences/...

🔗 Info & registration: lifelong-ml.cc/Conferences/...

#AI #ML #ContinualLearning #LifelongLearning

CoLLAs

Collas

lifelong-ml.cc

2

Reposted by Jorge Mendez-Mendez

collasconf.bsky.social @collasconf.bsky.social · Jul 27

📢 2 weeks until #CoLLAs2025!

Here’s what you need to make the most of it

🗓 Program: lifelong-ml.cc/Conferences/...

✅ Papers: lifelong-ml.cc/Conferences/...

📍 Venue: lifelong-ml.cc/Conferences/...

🔗 Info & registration: lifelong-ml.cc/Conferences/...

#AI #ML #ContinualLearning #LifelongLearning

CoLLAs

Collas

lifelong-ml.cc

2 3

Jorge Mendez-Mendez @jmendezm.bsky.social · Apr 15

Submit your tutorial proposal or topic/presenter suggestions to [email protected] by April 30!

collasconf.bsky.social @collasconf.bsky.social · Apr 15

📢 Extended Deadline for Tutorials 📢

You now have until April 30, 2025 (AoE) to submit your tutorial proposals on continual learning, LLMs, neuroscience-inspired AI & more.

🔗 lifelong-ml.cc

💡 Suggest a topic: [email protected]

#AI #MachineLearning #ContinualLearning #CallForTutorials

CoLLAs

Collas

lifelong-ml.cc

1 2

Jorge Mendez-Mendez @jmendezm.bsky.social · Dec 16

Broadcasting at its finest

3

Jorge Mendez-Mendez @jmendezm.bsky.social · Dec 6

I'll be at @neuripsconf.bsky.social #NeurIPS2024 next week for workshops and am looking to recruit PhD students for Fall '25. I'm generally interested in lifelong learning, robotics, and RL. If you'll be around and are interested in working with me, please send a note in Whova to meet up!

12

Jorge Mendez-Mendez @jmendezm.bsky.social · Dec 4

I'm curious what the gap would be for getting this running with other platforms. Your thread seems to suggest it's fairly flexible and could be used with other 6-DoF mobile manipulators?

1 3

Jorge Mendez-Mendez @jmendezm.bsky.social · Dec 4

This looks awesome! Maybe I should consider a Stretch as my starter robot for my lab. 🤔

2 2

Reposted by Jorge Mendez-Mendez

Reinforcement Learning Conference @rl-conference.bsky.social · Dec 2

The call for papers for RLC is now up! Abstract deadline of 2/14, submission deadline of 2/21!
Please help us spread the word.
rl-conference.cc/callforpaper...

RLJ | RLC Call for Papers

rl-conference.cc

1 18 54

Jorge Mendez-Mendez @jmendezm.bsky.social · Dec 2

We did spend a few weeks on deep RL. OOD and continual learning for sure will be there. What are some good reads for uncertainty quantification?

1 2

Jorge Mendez-Mendez @jmendezm.bsky.social · Dec 2

I'm wrapping up my Deep Learning course this Thursday with a lecture titled "The future of deep learning". What topics should make it in there? (I want to do very little of "the state-of-the-art of deep learning" and much more "things that don't yet work but some believe will be game-changing".)

3 2 12

Reposted by Jorge Mendez-Mendez

collasconf.bsky.social @collasconf.bsky.social · Nov 28

📢 Exciting News! The Fourth Conference on Lifelong Learning Agents (CoLLAs 2025) will be held at the University of Pennsylvania (@Penn) in Philadelphia, USA 🇺🇸

🗓️ Important Dates:

Abstract Deadline: Feb 21, 2025
Submission Deadline: Feb 26, 2025
Conference Dates: Aug 11 - Aug 14, 2025 1/

2 1

Reposted by Jorge Mendez-Mendez

Ramon Astudillo @ramon-astudillo.bsky.social · Nov 19

I did a starter pack of people in New York (City) working on ML/AI. Please distribute and feel free to self nominate!

go.bsky.app/BoEtagz

41 19 84

Jorge Mendez-Mendez @jmendezm.bsky.social · Nov 30

🙋‍♂️ I'm on the Island, if you're counting that.

1

Reposted by Jorge Mendez-Mendez

ericeaton.bsky.social @ericeaton.bsky.social · Nov 28

New feed on continual learning, lifelong learning, and related ML topics: bsky.app/profile/did:...

I hope you find it useful. Please let me know if you notice it is missing any posts, so that I can adjust the regular expression.

1 7

Jorge Mendez-Mendez @jmendezm.bsky.social · Nov 26

It's almost time for #NeurIPS2024! I'll be there for workshops (and I'll be giving a talk at the Scalable Continual Learning workshop: sites.google.com/view/continu...). If you'll be around and want to chat, please reach out!

Scalable Continual Learning

Abstract

sites.google.com

1 3 12

Jorge Mendez-Mendez @jmendezm.bsky.social · Nov 26

To clarify, this starter pack is for lifelong learning of the *machine* variety.

1

Jorge Mendez-Mendez @jmendezm.bsky.social · Nov 25

I work on embodied lifelong learning; would you mind adding me? Also, I made a related started pack for lifelong/continual learning: go.bsky.app/QXGY1iT. There may be some more folks there that are relevant!

2

Jorge Mendez-Mendez @jmendezm.bsky.social · Nov 25

That may be true. Normalizing high-quality non-anonymous criticism of all (not just powerful) people in our field would be a positive. I still wonder if many junior folks would shy away from writing highly critical reviews knowing that their name would be visible later.

1