Yunlong Song
@realyunlong
Followers
697
Following
496
Media
6
Statuses
68
Thank you all.
Congratulations to my student Yunlong Song @realyunlong for successfully defending his Ph.D. in “Learning Robot Control: From #ReinforcementLearning to #DifferentiableSimulation”! Many thanks to the external reviewers Yuke Zhu @yukez from the U. of Texas at Austin, Marco Hutter
3
1
71
RT @theo_gervet: We started Genesis AI to solve general-purpose robotics and unlock unlimited physical labor. We’re backed by $105M from @….
0
24
0
RT @gs_ai_: Today, We’re launching Genesis AI — a global physical AI lab and full-stack robotics company — to build generalist robots and u….
0
86
0
RT @zhou_xian_: We’re excited to finally share what we’ve been assembling over the past few months!. This is a field full of excitement and….
0
28
0
Swarm navigation at 20 m/s with no communication, no state estimation, & on a $21 computer? .This paper combines deep learning + differentiable sim for zero-shot sim-to-real flight. It is an underrated breakthrough. Paper: #naturemachineintelligence
6
52
232
Amazing achievement!.
🔥Best Paper Award at #ICRA2025 .Thrilled to share that our paper MAC-VO has been awarded the 𝘽𝙚𝙨𝙩 𝘾𝙤𝙣𝙛𝙚𝙧𝙚𝙣𝙘𝙚 𝙋𝙖𝙥𝙚𝙧 𝘼𝙬𝙖𝙧𝙙 and the 𝘽𝙚𝙨𝙩 𝙋𝙖𝙥𝙚𝙧 𝘼𝙬𝙖𝙧𝙙 𝙤𝙣 𝙍𝙤𝙗𝙤𝙩 𝙋𝙚𝙧𝙘𝙚𝙥𝙩𝙞𝙤𝙣!. Check our project:
1
0
0
RT @davsca1: We are hiring multiple PhD students and Postdocs: Are you ready to take your research career to the n….
0
46
0
Very insightful talk. I am sure many of the findings are also related to robotics. For example, the idea of knowledge storage and extraction is akin to robot skills learning and task adaptation. Then, what is the universal law for robot pertaining and fine-tuning?.
If you're attending ICML 2024, join my 2-hour tutorial on Monday July 22 to explore the Physics of Language Model - all 6 parts. Visit: and it will be live-streamed on Zoom. BONUS: this is the premiere of Part 2.1 + 2.2, don't miss out! #ICML2024 #MetaAI
0
0
10
Great workshop. Highly recommended.
Yunlong Song gave a great lightning talk on optimal control, reinforcement learning, and differentiable simulation!
0
0
6
I will present my research on reinforcement learning, optimal control, and differentiable simulation tomorrow at several workshops. Also, don’t miss out the opportunity to see live drone racing demos.
Meet us this week at #RSS2024 at #TUDelft! We will present several papers on perception, learning, SLAM, and control at the main conference and workshops! Plus, we will give a live #droneracing #demo on Tuesday and Wednesday from 12:00 to 13:30! Full list with times, rooms, and
1
0
15
RT @RSSPioneers: Happy Friday, robotics researchers!. We are 2 weeks away from the #RSSPioneers2024 workshop! Research statements for this….
0
12
0
Replay Buffer is a key component in off-policy training. Do you know that you can also used past experiences to design an Initial State Buffer, through self supervised learning. It can dramatically improve exploration!.
Check out our #ICRA2024 paper "Contrastive Initial State Buffer for Reinforcement Learning," which tackles the sample inefficiency in #ReinforcementLearning head-on. Code released! We introduce an approach agnostic to the underlying RL algorithm: the Contrastive Initial State
1
0
11
Actor-Critic Model Predictive Control extends the capabilities of standard MPC by incorporating learning mechanisms that allow for the direct optimization of complex, task-level objectives.
Check out our #ICRA2024 paper "Actor-Critic Model Predictive Control." Model-free #reinforcementlearning (RL) is known for its strong task performance and flexibility in optimizing general reward formulations. On the other hand, #ModelPredictiveControl (MPC) benefits from
3
1
12
If you are attending #IROS2023, join our workshop on Learning Robot Super Autonomy, in which I will talk about our latest findings in comparing Reinforcement learning and optimal control. Room: 330B, Time: 12:00 pm.Program:
0
2
10
I have officially started my visit at Biomimetic Robotics Lab led by Prof. Sangbae Kim at #MIT. Looking forward to push the limit of vision-based legged locomotion.
3
0
51
There are certain golas you cannot achieve, no matter how hard you try. Turns out that you are just optimizing the wrong optimization objective.
0
0
5
RT @_bbelousov: I am organizing a challenge at @IJCAIconf this year! 👇 . Submit your favorite algorithms online Le….
0
4
0
RT @keenanwyrobek: 1/10 .@MarkRober spent the last 2 months traveling the world to tell @zipline's story. This is what he found. [Mark’s fu….
0
29
0