Proud of my team members who won the 1st place of two tracks in the RoCo Challenge at #IROS2026 in Pittsburgh! Robotic Collaborative Assembly Challenge (rocochallenge.github.io/RoCo…) includes challenging tasks like industrial board and brick assembly on bimanual and tactile-aware setups with 55 registered teams from 8+ countries. In addition to days of hard work via onsite hackathon, the winning point also resides in our recent work at BAIR Center for Humanoid Intelligence (HIC) leveraging simulation, which will be released in the future. Kudos to the team Jinzhong Gu, Max Wang, @FanXu22, Xingjian Wang, @MutianShen, @jiakai_chen3, Xinyi Cao, Jingdong Zhou, Chenrui Tie, Haoran Lu, Shuo Yin, from @berkeley_ai and MSC Lab at UC Berkeley, with nice guidance from @warshallrho and Masayoshi Tomizuka! Kudos to the team Jinzhong Gu, Max Wang, @, Xingjian Wang, e organizers @RuixuanLiu_, Haichao Liu, @ZiweiWangNTU and @ChangliuL!@

Meet FINGR: a dexterous hand that solves a 2×2 Rubik’s Cube with continuous finger tricks. Here’s how we got the fingers to work together. 🧵

Presenting research from @berkeley_ai Humanoid Intelligence Center. DexTacWAM: A Visuo-Tactile World-Action Model for Dexterous Manipulation.🖐️🤖 Dexterous manipulation requires touch, yet multi-finger tactile data remain scarce and expensive to collect at scale. Through continual vision-to-touch learning, DexTacWAM adapts a pretrained video world model into a visuo-tactile world model for predictive multi-finger contact modeling and action generation. Across six contact-rich dexterous manipulation tasks, DexTacWAM achieves the highest score on every task, averaging 70.6 vs. 38.0 for the strongest baseline. 🔬 Why not simply inject tactile features into the action policy? With the same multi-finger tactile encoder, policy architecture, and training procedure, replacing the tactile world-model latent with direct tactile features drops the 4-task mean from 74.7 to 26.6. Takeaway: the benefit does not come simply from providing tactile observations to the policy, but from making multi-finger contact evolution part of the predicted world state. All code, model weights, and datasets are now open-sourced! 🌐 Project: dextacwam.github.io/ 📄 Paper: arxiv.org/abs/2609.24976 💻 Code: github.com/dextacwam/DexTacW… 🤗 Weights&Data: huggingface.co/collections/J… Author List: @Jensen_Yuan, @zekaiw04, @sbn_epiphany Haoran Lu, @trevordarrell, @Ismini_L, @Wei_ZHAN_