Auditing and exposing the fragility of language-conditioned robot models with Embodied Red Teaming (ERT)! 🤯 Simple re-phrasing of task instructions, e.g., from "Please bring me a can of coke" to "Give me a coke," is the difference between the robot succeeding or failing.

You aren't doing robotics if you are not breaking some robots! uan.csail.mit.edu

Agents performing "curious" exploration by setting random abstract goals! We present a simple but effective method for deep exploration of reinforcement learning (RL) agents that we call random latent exploration (RLE). Typical RL gents explore by: ⚔️ Noise-based exploration,

Llama 4 (Meta) results are consistent with what we hypothesized will unleash the next generation of AI reasoning. A new paradigm for pre-training is around the corner arxiv.org/abs/2502.19402

What if an LLM can decide what data to use, potentially generate its own data and decide how to update itself 👇

What’s keeping robot arms from working like human arms? They're big, slow, have the wrong joints, and can't conform to their environment. DexWrist solves all of these issues and simplifies learning constrained, dynamic manipulation👉 dexwrist.csail.mit.edu

What if robots had wrists? 👇