Kicking off #RLC2025 with our Workshop on Programmatic Reinforcement Learning! This workshop explores how programmatic representations can improve interpretability, generalization, efficiency, and safety in RL.

If you are interested in 3D/4D/Video models, join us tomorrow (10/20) at the #ICCV #Wild3D workshop (Rm 312)! We have an amazing set of all-star speakers! It will be fun! :) @QianqianWang5 @AnpeiC @Jimantha Andrea Vedaldi @angelaqdai @JunGao33210520 @georgiagkioxari

My slide:

Excited to give a talk on "Imitation Learning with Diffusion Models" at the Embedded Vision Workshop, #ICCV2025! I’ll discuss how diffusion models can enhance imitation learning, building on our papers presented at NeurIPS, ICML, and ICLR. 🕘 Oct 19th, 13:45-14:15 📍 Room 316A

How can we help *any* image-input policy generalize better? 👉 Meet PEEK 🤖 — a framework that uses VLMs to decide *where* to look and *what* to do, so downstream policies — from ACT, 3D-DA, or even π₀ — generalize more effectively! 🧵

Messing around with the new Sora app from OpenAI 👀 wild stuff

LoRA makes fine-tuning more accessible, but it's unclear how it compares to full fine-tuning. We find that the performance often matches closely---more often than you might expect. In our latest Connectionism post, we share our experimental results and recommendations for LoRA.

Humanoids were supposed to dance with K-pop stars at the @corl_conf banquet—but they couldn’t even stand up. I found that motivating. Robot learning folks, let’s push harder! #CoRL2025

The field of robotics is undergoing a historic revolution right now. I’ve spent the last year thinking about how to mentally model the breakneck progress in robotics + AI. With the help of mascots like “The AGI Bro”, we can try to sift through the noise 🧵

The first universal 3D robot viewer for the browser… load URDF, MJCF, or USD in seconds. No installs. No setup. Developer Victor Oldensand has built Mechaverse, a universal 3D robotics viewer that works on desktop and even mobile (if your phone is strong enough). No installs.

Consider submitting your work to our @corl_conf workshop on "Resource-Rational Robot Learning" by August 18! Workshop web page: https://t.co/25HLJgqppX

@ellisk_kellis @white_martha @yayitsamyzhang @SheilaMcIlraith @tydsh Wentao Yuan @TonyWentaoYuan talks about “An API for the Physical World”

@ellisk_kellis @white_martha @yayitsamyzhang @SheilaMcIlraith Yuandong Tian @tydsh talks about “Leveraging Symbolic Solvers For Better Reasoning Capabilities”

Happening now at #RLC2025. Join us if you’re interested in program, agents and RL.

@ellisk_kellis @white_martha @yayitsamyzhang Sheila McIlraith @SheilaMcIlraith talks about “Programmatic Reward Models: Exploiting reward function structure to help agents learn, plan, and remember”

@ellisk_kellis @white_martha Amy Zhang @yayitsamyzhang talks about “Leveraging Programmatic Structure in Reinforcement Learning”

@ellisk_kellis @white_martha

@ellisk_kellis @white_martha Spotlight presentations

@ellisk_kellis Martha White @white_martha talks about “Planning with Options, with speculations on intersections with programmatic RL”

Kevin Ellis @ellisk_kellis talks about “Learning how the world works by writing code”