#Travel# | 🌃🍲 Old #Guangzhou# Charm! #Haizhu# South Road in #Yuexiu# District bridges centuries of trade, from Song Dynasty shipping to Qing Dynasty dried seafood markets. By night, its 1930s arcades glow as locals gather at Linji Congee Shop (since 1978) for authentic, slow-simmered comfort food tucked away from the modern skyscrapers. cr: IP Guangdong Creator 叶文浩 Enjoy the charm of old Guangzhou: #ChinaTravel# #CantoneseFood# #Guangdong# #China#

#Science# | 🦖🥚 Urban Dinosaur Discovery! Well-preserved dinosaur egg fossils have been discovered in #Haizhu# District, marking a rare find within #Guangzhou#'s bustling urban center. First spotted by a resident, the Late Cretaceous fossils have been transferred to the city's geological survey institute for 3D scanning and age dating. They will eventually be exhibited to showcase the PRD's ancient, lush prehistoric ecosystem. Have a look😮: #DinosaurFossils# #Paleontology# #Guangdong# #China#

NEW RESEARCH: Robot hands can now spin pens! This project involves @Ying_yyyyyyyy, @HaozhiQ, @Junwang_048, @JitendraMalikCV, and others A four-fingered Allegro Hand (16 DoF) learnt to spin pen-like objects in-hand for continuous revolutions, deployed on proprioception alone (a 30-step window of joint positions and previous targets, no vision, no touch). The recipe is three stages: 1. An oracle RL policy is trained in sim with privileged information. 2. Rolled out in sim and its action sequences are replayed open-loop on the real hand to harvest the ones that happen to work. 3. A proprioceptive student, behavior-cloned from the oracle in sim, is then fine-tuned on those real successes. It exists because the group's usual teacher-student distillation (DAgger) fails on this task, and because direct sim-to-real fails outright. From UC San Diego, CMU and UC Berkeley (Jun Wang, Ying Yuan, Haichuan Che, Haozhi Qi, Yi Ma, Jitendra Malik, Xiaolong Wang). A proprioception-only policy cannot even converge in simulation (it drops the pen in the first few steps); a vision/tactile policy learns fine in sim but the real pen oscillates so much that the image distribution shifts and it collapses to 90 degrees then drops (rotation pinned at 1.57 rad, 0 percent success on 7 of 10 objects). So vision and touch were dropped not as useless but because their sim-to-real gap is larger than proprioception's, while proprioception alone is too weak to learn the skill. Replaying the oracle's action sequence open-loop never needs a sensorimotor policy to survive transfer! More real demonstrations overfit rather than generalize. Going from 45 to 75 demos without sim pretraining lifts a training object (A: 53.7 to 76.7 percent) but barely moves or even hurts unseen objects (F: 16.4 to 15.0). Sim pretraining buys the generalization that raw real demos cannot. The entire real-world dataset is 45 trajectories (15 each on 3 objects, "fewer than 50"), and they were harvested for free. The oracle is replayed open-loop on the real hand and a trial is kept only if the object rotates more than a full revolution; no teleoperation, no human demos. Sim is cheap too: the oracle is 500M steps, under a day on one GPU. A dynamic, contact-rich skill bootstrapped from under 50 real rollouts. The sharpest stated lesson is that the pure physics gap survives even after you remove vision and touch, and domain randomization alone cannot bridge it. Pen spinning is dynamic and contact-rich enough to break the randomize-and-transfer playbook that carried this group's own earlier cube and sphere rotation work (the Hora lineage). The takeaway is that for these tasks the sim-to-real burden has to move off the fragile learned policy and onto a robust open-loop action replay. Also worth mentioning imho: the control frequency is not high enough to catch a fast-falling pen, and the shifting center of mass destabilizes the grasp.