Efficient training of neural networks is difficult. Our second Connectionism post introduces Modular Manifolds, a theoretical step toward more stable and performant training by co-designing neural net optimizers with manifold constraints on weight matrices.…
I saw a live demo of DRP a few months back—truly impressive. Collision-free motion generation is such a core capability for embodied agents, and DRP nails it. Excited to see how this advances even more complex robotics challenges!
I saw a live demo of DRP a few months back—truly impressive. Collision-free motion generation is such a core capability for embodied agents, and DRP nails it. Excited to see how this advances even more complex robotics challenges!
Ever wish a robot could just move to any goal in any environment—avoiding all collisions and reacting in real time?
🚀Excited to share our #CoRL2025 paper, Deep Reactive Policy (DRP), a learning-based motion planner that navigates complex scenes with moving obstacles—directly…
Self-Questioning Language Models: LLMs that learn to generate their own questions and answers via asymmetric self-play RL.
There is no external training data – the only input is a single prompt specifying the topic.
I joined Skild AI late last year and we've been making swift progress towards more general robots!
To record these videos we took the robot around town to locations it had never seen before with no prior preparation or planning.
I joined Skild AI late last year and we've been making swift progress towards more general robots!
To record these videos we took the robot around town to locations it had never seen before with no prior preparation or planning.
Modern AI is confined to the digital world.
At Skild AI, we are building towards AGI for the real world, unconstrained by robot type or task — a single, omni-bodied brain. Today, we are sharing our journey, starting with early milestones, with more to come in the weeks ahead.…
We’ve been building quietly — starting tomorrow, we go live.
Here’s a teaser of what we did before Skild AI. It has shaped what’s coming next.
07/29. Stay tuned.
🚨 The era of infinite internet data is ending, So we ask:
👉 What’s the right generative modelling objective when data—not compute—is the bottleneck?
TL;DR:
▶️Compute-constrained? Train Autoregressive models
▶️Data-constrained? Train Diffusion models
Get ready for 🤿 1/n
🧠With the shift in humanoid control from pure RL to learning from demonstrations, we take a step back to unpack the landscape.
🔗breadli428.github.io/post/lfd/
🚀Excited to share our blog post on Feature-based vs. GAN-based Learning from Demonstrations—when to use which, and why it…
Everyone knows action chunking is great for imitation learning. It turns out that we can extend its success to RL to better leverage prior data for improved exploration and online sample efficiency! colinqiyangli.github.io/qc/
The recipe to achieve this is incredibly simple. 🧵 1/N
How can we unlock generalized reasoning?
⚡️Introducing Energy-Based Transformers (EBTs), an approach that out-scales (feed-forward) transformers and unlocks generalized reasoning/thinking on any modality/problem without rewards.
TLDR:
- EBTs are the first model to outscale the…
TRI's latest Large Behavior Model (LBM) paper landed on arxiv last night! Check out our project website: toyotaresearchinstitute.github.io/lbm1/
One of our main goals for this paper was to put out a very careful and thorough study on the topic to help people understand the state of the…
Your bimanual manipulators might need a Robot Neck 🤖🦒
Introducing Vision in Action: Learning Active Perception from Human Demonstrations
ViA learns task-specific, active perceptual strategies—such as searching, tracking, and focusing—directly from human demos, enabling robust…
(1/n) Since its publication in 2017, PPO has essentially become synonymous with RL. Today, we are excited to provide you with a better alternative - EPO.
Training robots for the open world needs diverse data
But collecting robot demos in the wild is hard!
Presenting DexWild
🙌🏕️ Human data collection system that works in diverse environments, without robots
💪🦾 Human + Robot Cotraining pipeline that unlocks generalization
🧵👇
24K Followers 387 FollowingCo-Founder & CEO @SkildAI, Faculty @CarnegieMellon.
PhD @UCBerkeley.
I study topics in AI (machine learning, robotics & computer vision).
47 Followers 140 FollowingPhD Student @Yale | Prev: MS in Robotics @Penn @GRASPlab, BS in Mechanical Engineering @RPI | Research interests focus on spatial AI & robotics.
543K Followers 24K FollowingThe best from ML/AI community | Ex-Microsoft, Rackspace, Fast Company | Wrote eight books about the future | Silicon Valley robots, holodecks, BCIs, & startups.
457 Followers 949 FollowingRobotics AI Engineer at Skild AI | UCSD | UT Austin PhD dropout | I tweet about robotic learning, neuroscience and Football.
102 Followers 107 FollowingCommitted to the bit a bit too hard
All opinions expressed are those of the little green smurf living inside my head
MTS @SkildAI, prev. Cal 3x
1K Followers 973 FollowingIncoming Assistant Professor @UTCompSci, Senior Researcher @togethercompute, PhD @UCBerkeley. Working on building cooler things with fewer cost 😊
20K Followers 100 FollowingMember of Technical Staff at Anthropic AlphaGo, AlphaZero, MuZero, AlphaCode, AlphaTensor, AlphaProof Gemini RL Prev Principal Research Engineer at DeepMind
4K Followers 371 FollowingResearch Scientist at BIGAI, Director of Center for Embodied AI and Robotics. Ph.D. in Statistics from @UCLA. Former intern at @DeepMind and @MetaAI.
1.4M Followers 1K FollowingBuilding @EurekaLabsAI. Previously Director of AI @ Tesla, founding team @ OpenAI, CS231n/PhD @ Stanford. I like to train large deep neural nets.
3K Followers 440 FollowingIncoming Assistant Professor at Harvard and Kempner Institute. Postdoc at UC Berkeley. Former Ph.D. student at Cornell Tech. https://t.co/LyIdb5HmM9
45K Followers 1K FollowingCTO at @Databricks and CS prof at @UCBerkeley. Working on data+AI, including @ApacheSpark, @DeltaLakeOSS, @MLflow, https://t.co/94gROE5Xa0. https://t.co/nmRYAKG0LZ
13K Followers 441 FollowingBuilding next-gen AI at @thinkymachines. Past: Founding team @MistralAI, RS at Facebook AI Research. Ph.D. @SCSatCMU, BTech @iitbombay CS.
457 Followers 949 FollowingRobotics AI Engineer at Skild AI | UCSD | UT Austin PhD dropout | I tweet about robotic learning, neuroscience and Football.
102 Followers 107 FollowingCommitted to the bit a bit too hard
All opinions expressed are those of the little green smurf living inside my head
MTS @SkildAI, prev. Cal 3x
1K Followers 973 FollowingIncoming Assistant Professor @UTCompSci, Senior Researcher @togethercompute, PhD @UCBerkeley. Working on building cooler things with fewer cost 😊