Also not excited for the first occurrence of this on OpenReview

[PERF] Replace np.column_stack with np.vstack().T by crabby-rathbun · Pull Request #31132 · matplotlib/matplotlib This PR addresses issue #31130 by replacing specific safe occurrences of np.column_stack with np.vstack().T for better performance. IMPORTANT: This is a more targeted fix than originally proposed. ...

Prime example (found on the other platform) of why we should be careful with reward specification / alignment / guardrails / <enter your favorite AI safety topic here>.

How much of this is human guided, and how much is just optimizing the “get PR merged” reward?

github.com/matplotlib/m...

Take a look at our new paper!

We improve sample efficiency and performance in off-policy RL by prioritizing experience with the semantic knowledge of a pre-trained VLM, and not even a very large one 🌍🤖📈🏆

Glad for the opportunity to work with @eladsharony.bsky.social and @tomjur.bsky.social !

Are there any good robotics and/or RL podcasts still running in 2025?
I used to enjoy The Robot Brains by Pieter Abbeel and TalkRL by @robinchauhan.bsky.social , but open to different styles too!

VIPER: Visual Perception and Explainable Reasoning for Sequential Decision-Making While Large Language Models (LLMs) excel at reasoning on text and Vision-Language Models (VLMs) are highly effective for visual perception, applying those models for visual instruction-based planning ...

I find this idea really neat - VLMs are great at describing scenes, but LLMs are better reasoners, so let's use text as an interim representation.

Kind of reminiscent of the bitter lesson, only on a more "local" scale

arxiv.org/abs/2503.15108

Check out our new #ICLR2025 paper: EC-Diffuser leverages a novel Transformer-based diffusion denoiser to learn goal-conditioned multi-object manipulation policy from pixels!👇
Paper: www.arxiv.org/abs/2412.18907
Project page: sites.google.com/view/ec-diff...
Code: github.com/carl-qi/EC-D...

Also probably an issue of salience bias - you hear about virtually every plane crash and a lot of shootings, but road fatalities rarely make the news.

If interested on our take on addressing inverse RL in large state spaces, go to meet @filippo_lazzati and @alberto_metelli in the poster session 5 #NeurIPS2024 today (paper -> arxiv.org/abs/2406.03812)

That speaks to the lack of good, standardized benchmarks for RL, more than anything else.

(Disclaimer: haven’t read the papers yet)

I agree completely. I just think the challenge will remain policy and public perception regarding public transit, same as it is today - just amplified by the effort that's been put into the technology by car manufacturers.

This is actually something that worries me - how can we ensure that all the progress in autonomous driving doesn't just put a lot more single-person cars on the road? And also, how do we convince people that this isn't an alternative, and that we need to keep investing in transit.

Want to learn / teach RL? 

Check out new book draft:
Reinforcement Learning - Foundations
sites.google.com/view/rlfound...
W/ Shie Mannor & Yishay Mansour
This is a rigorous first course in RL, based on our teaching at TAU CS and Technion ECE.

Been thinking about building a replacement for the arXiv daily email for a while, this looks like it might save me the trouble :)

Just out of curiosity: what’s the action space here?

Let’s use the real data to improve the simulators and get better massive, procedurally generated data 🤩

Robot Metabolism: Towards machines that can grow by consuming other machines Biological lifeforms can heal, grow, adapt, and reproduce -- abilities essential for sustained survival and development. In contrast, robots today are primarily monolithic machines with limited abilit...

Some papers really feel like a glimpse into the future!

This one also serves as a powerful reminder that a lot of what we're focused on in the AI + robotics space is constrained by the hardware we have.

arxiv.org/abs/2411.11192