Boyuan Chen @BoyuanChen0 Twitter profile

Pinned Tweet

Boyuan Chen

3 months

Sometimes being a PhD student at MIT is like living in 22nd century. Here is my robot dog getting its daily dose of free food with me.

8

58

535

Last Seen Profiles

@Boonsch

@BBescty

@HacashDAO

@Chug_A_CAPS_Fan

@PraskVal

@CrimesReais

@banisgh

@baristiranb

@DamnLeo08

@MagnusSheffield

@JessNesling

@KriptosRamos

@ArmiesMagazine

@MasterRed1917

@Zfgym10

@FlogasIreland

@QuickFrostmoon

@Taeshon

@_minyami_

@TsarkovaTatiana

@XbYdtC6GSNdLjGk

@USCCB

@xuw3X4ktBUd5WIF

@B2rJb

@jjanetthew

@BN_Music

@LuarBatasanMY

@assdraft

@justgunmo

@ChaRiches

@Overlord_Potato

@ZEZO_CARTOONS

@hottakasum18585

@miyo78135174922

@CoachKiddGlass7

@c_nellyy

Boyuan Chen

@BoyuanChen0

1 month

I quit PhD (for a day) and opened a boba shop at @MIT - Generative Boba! It’s a huge success - right next to our office so all the AI researchers are enjoying it. Checkout our boba diffusion algorithm in the poster to understand why boba generation is so important to @MIT_CSAIL !

31

94

1K

Boyuan Chen

@BoyuanChen0

4 months

Introducing Spatial VLM, a Vision-Language Model with 3D Spatial Reasoning Capabilities by @GoogleDeepmind . We investigate to what extent synthetic data can help VLMs learn - 3D relationship - quantitative distance - CoT spatial reasoning - RL reward (1/6)

Spatial Visual Language Model

SpatialVLM: A visual language model that natively understand and reason about spatial relationships

spatial-vlm.github.io

9

51

373

Boyuan Chen

@BoyuanChen0

2 years

How can we ground large language models (LLM) with the surrounding scene for real-world robotic planning? Our work NLMap-Saycan allows LLMs to see and query objects in the scene, enabling real robot operations unachievable by previous methods. Link: 1/6

4

41

239

Boyuan Chen

@BoyuanChen0

3 months

My AI+robotics lecture at MIT is now public! Back in 2023 I talked about how video models will revolutionize robotics, and many other foundation models like LLMs. Now SORA arrives, definitely checkout my lecture on Foundation Models for Decision making at

3

40

202

Boyuan Chen

@BoyuanChen0

6 months

I am giving a guest lecture at MIT about "Foundation Models for Decision Making". My current plan is LLM (Saycan, RT2, Code as Policy, Toolformer etc) + Video Prediction (Unipy, Video Language Planning). Please let me know if you have additional suggestion!

15

10

123

Boyuan Chen

@BoyuanChen0

5 months

I am presenting my paper “RaMP: Self-Supervised Reinforcement Learning that Transfers using Random Features” at poster 1427 from 5-7pm at Neurips 2023! Don’t miss it! Website:

0

9

79

Boyuan Chen

@BoyuanChen0

4 months

Proudly announcing our ICLR publication by my first undergraduate mentee, Suning! DittoGym is a set of RL environments and algorithms for shape shifting robots like the Pokémon Ditto. Suning is interviewing for PhD admission right now. Don’t miss an amazing student like him!

Vincent Sitzmann

@vincesitzmann

4 months

Excited to introduce DittoGym @ ICLR, in which we study the control of a neat new kind of robot: soft shape-shifters! This is work done by @SuningHuan44558 during his visit at my group at MIT, jointly with my student @BoyuanChen0 ! Project page: 1/n

3

27

148

0

8

62

Boyuan Chen

@BoyuanChen0

16 days

It was a great time to host @DrJimFan in Boston! Had a lot of interesting discussions, and most importantly, a visit to my Generative Boba shop!

Sugandha Sharma

@sugsharma

16 days

Enjoyed the @NVIDIA - @MIT lunch meetup today w/ @DrJimFan ! I was representing both sides for the first time today🙂. Great reconnecting w/ these wonderful colleagues at MIT too! @BoyuanChen0 , @ZhutianYang_ , @avivnet @NishanthJKumar1 , @hyojinbahng , @haoshu_fang , @TheAndiPenguin

3

1

68

3

5

52

Boyuan Chen

@BoyuanChen0

1 month

Tying shoelaces is traditionally a hard problem for robotics. This seems like the first end-to-end policy to do it. This time Tony got us more generalizations in addition to generalizations. Cannot wait to see the tech report!

Tony Z. Zhao

@tonyzzhao

1 month

Introducing 𝐀𝐋𝐎𝐇𝐀 𝐔𝐧𝐥𝐞𝐚𝐬𝐡𝐞𝐝 🌋 - Pushing the boundaries of dexterity with low-cost robots and AI. @GoogleDeepMind Finally got to share some videos after a few months. Robots are fully autonomous filmed in one continuous shot. Enjoy!

56

333

1K

2

3

39

Boyuan Chen

@BoyuanChen0

11 months

Wow VLM is opening up a new world for motion planning! This work from my friend Wenlong has quite impressive results by leveraging foundational models.

Wenlong Huang

@wenlong_huang

11 months

How to harness foundation models for *generalization in the wild* in robot manipulation? Introducing VoxPoser: use LLM+VLM to label affordances and constraints directly in 3D perceptual space for zero-shot robot manipulation in the real world! 🌐 🧵👇

10

140

584

1

2

31

Boyuan Chen

@BoyuanChen0

3 months

While imitation learning has a leading edge in robotic manipulation, let’s not forget the works that uses videos models - to potentially achieve zero shot generalization. Dreamer and Unipy are my favorite works along this line.

5

2

27

Boyuan Chen

@BoyuanChen0

1 month

Llama 3 is trained with over 10 Million human-annotated examples - that's also my guess of how many diverse trajectories you need to collect to get a generalist GPT for robotics after large-scale pretraining.

2

26

Boyuan Chen

@BoyuanChen0

3 months

I have the same feeling. Always remember that GPT is not just a big model, but huge amount of diverse data. For robotics, people must leverage data of other forms as teleoping robot directly hardly scale up. Videos and VR of human activities will be my biggest bet.

Yuke Zhu

@yukez

3 months

We are unlikely to create an “ImageNet for Robotics”. In retrospect, ImageNet is such a homogeneous dataset. Labeled images w/ boxes. Generalist robot models will be fueled by the Data Pyramid, blending diverse data sources from web and synthetic data to real-world experiences.

6

31

238

0

3

21

Boyuan Chen

@BoyuanChen0

12 days

Our paper will be presented tomorrow at ICLR! Suning is my first undergrad mentee who is joining Stanford later this year, very proud of his work!

Suning Huang

@SuningHuan44558

12 days

Check out our DittoGym poster at Halle B #33 @ ICLR on Thursday from 10:45 AM to 12:45 PM. #ICLR2024 If you need your robot🤖 to flexibly retrieve a key🔑 when it has fallen into a narrow slot, be sure to explore our paper!

1

4

17

1

2

20

Boyuan Chen

@BoyuanChen0

3 months

RL has come a long way to locomotion. But it’s happening!

Xiaolong Wang

@xiaolonw

3 months

Let’s think about humanoid robots outside carrying the box. How about having the humanoid come out the door, interact with humans, and even dance? Introducing Expressive Whole-Body Control for Humanoid Robots: See how our robot performs rich, diverse,

94

214

1K

0

4

18

Boyuan Chen

@BoyuanChen0

2 months

It is the annual visit day time for grad school admits. If you have a hard time making your choice, maybe my blog will help you! Check out my post “best computer science schools ranked by boba” at

2

1

17

Boyuan Chen

@BoyuanChen0

3 months

Congratulations! Jim is doing a lot of fun research. Would highly recommend the team!

Jim Fan

@DrJimFan

3 months

Career update: I am co-founding a new research group called "GEAR" at NVIDIA, with my long-time friend and collaborator Prof. @yukez . GEAR stands for Generalist Embodied Agent Research. We believe in a future where every machine that moves will be autonomous, and robots and

241

471

4K

0

3

15

Boyuan Chen

@BoyuanChen0

1 month

@Ken_Goldberg @Stanford Unpopular opinion: I think the answer is obviously true. The more important question is “Can we collect LLM level of large data for robotics” because that’s what made robotics different.

2

1

15

Boyuan Chen

@BoyuanChen0

2 months

This is so exciting! I was watching NVIDIA Isaac gym and omniverse from the day it was announced during GTC. Now they are already used in cutting edge researches. Can’t wait to see GR00T change the way we work as well. BTW I really hope it will be open-sourced in the future.

Jim Fan

@DrJimFan

2 months

Today is the beginning of our moonshot to solve embodied AGI in the physical world. I’m so excited to announce Project GR00T, our new initiative to create a general-purpose foundation model for humanoid robot learning. The GR00T model will enable a robot to understand multimodal

197

1K

5K

1

2

14

Boyuan Chen

@BoyuanChen0

5 months

Pretty cool demo with a small number of demonstrations!

Zipeng Fu

@zipengfu

5 months

Introduce 𝐌𝐨𝐛𝐢𝐥𝐞 𝐀𝐋𝐎𝐇𝐀🏄 -- Learning! With 50 demos, our robot can autonomously complete complex mobile manipulation tasks: - cook and serve shrimp🦐 - call and take elevator🛗 - store a 3Ibs pot to a two-door cabinet Open-sourced! Co-led @tonyzzhao , @chelseabfinn

188

891

4K

0

2

12

Boyuan Chen

@BoyuanChen0

3 months

This is how you scale up

Cheng Chi

@chichengcc

3 months

Can we collect robot data without any robots? Introducing Universal Manipulation Interface (UMI) An open-source $400 system from @Stanford designed to democratize robot data collection 0 teleop -> autonomously wash dishes (precise), toss (dynamic), and fold clothes (bimanual)

42

342

2K

0

2

11

Boyuan Chen

@BoyuanChen0

6 months

@aryaman_pandya Yes. Will be available at

Robotic Manipulation, Fall 2023

www.youtube.com

2

11

Boyuan Chen

@BoyuanChen0

4 months

@GoogleDeepMind For more information, checkout out paper at Great thanks to my amazing host @xf1280 and collaborators @drzhuoxu @SeanKirmani @brian_ichter @peteflorence @DannyDriess @DorsaSadigh and Leo Guibas (6/6)

Spatial Visual Language Model

SpatialVLM: A visual language model that natively understand and reason about spatial relationships

spatial-vlm.github.io

0

1

11

Boyuan Chen

@BoyuanChen0

9 months

Check out this cool work from my group! Researcher can generate 3d scenes from single image via diffusing 2D novel views. However, it turns out you need a 3D structured forward model of you want high quality 3d scenes.

Vincent Sitzmann

@vincesitzmann

9 months

Introducing “Diffusion with Forward Models”, 𝗮 𝗺𝗼𝗱𝗲𝗹 𝘁𝗵𝗮𝘁 𝗰𝗮𝗻 𝗴𝗲𝗻𝗲𝗿𝗮𝘁𝗲 𝗱𝗶𝘃𝗲𝗿𝘀𝗲, 𝗿𝗲𝗮𝗹 𝟯𝗗 𝘀𝗰𝗲𝗻𝗲𝘀 𝗳𝗿𝗼𝗺 𝗮 𝘀𝗶𝗻𝗴𝗹𝗲 𝗶𝗺𝗮𝗴𝗲, 𝘁𝗿𝗮𝗶𝗻𝗲𝗱 𝘄𝗶𝘁𝗵 𝗶𝗺𝗮𝗴𝗲𝘀 𝘄/𝗼 𝗮𝗻𝘆 𝟯𝗗 𝗱𝗮𝘁𝗮! 1/n

14

97

486

0

10

Boyuan Chen

@BoyuanChen0

2 months

This clearly scale ups data collection for dexterous task. I am curious about how does the number of demo changes by moving from ego centric camera to point cloud. A lot of science can be done on top of this.

Chen Wang

@chenwang_j

2 months

Can we use wearable devices to collect robot data without actual robots? Yes! With a pair of gloves🧤! Introducing DexCap, a portable hand motion capture system that collects 3D data (point cloud + finger motion) for training robots with dexterous hands Everything open-sourced

21

131

624

1

2

9

Boyuan Chen

@BoyuanChen0

2 years

To that end, we propose NLMap to address two core problems 1) how to maintain open-vocabulary scene representations that are capable of locating arbitrary objects and 2) how to merge such representations within long-horizon LLM planners to imbue them with scene understanding. 3/

1

8

Boyuan Chen

@BoyuanChen0

10 months

This project fully shows the power and potential of AI agents. While I care more about real world robots, seeing such progress in AI agents is quite exciting. Definitely the next frontier of AI research.

0

8

Boyuan Chen

@BoyuanChen0

9 days

Just got the chance to read the paper, it’s great to have calibrated test and actually benchmark generalization

Xuanlin Li (Simon)

@XuanlinLi2

11 days

Scalable, reproducible, and reliable robotic evaluation remains an open challenge, especially in the age of generalist robot foundation models. Can *simulation* effectively predict *real-world* robot policy performance & behavior? Presenting SIMPLER!👇

3

24

121

1

0

10

Boyuan Chen

@BoyuanChen0

26 days

Congrats to Cameron and David! Flow map helps you get rid of the colmap bottleneck. BTW David writes beautiful code so you will definitely like his projects!

Vincent Sitzmann

@vincesitzmann

26 days

Introducing “FlowMap”, the first self-supervised, differentiable structure-from-motion method that is competitive with conventional SfM like Colmap! IMO this solves a major missing piece for internet-scale training of 3D Deep Learning methods. 1/n

11

99

602

0

1

8

Boyuan Chen

@BoyuanChen0

5 months

I have the exact same feeling. All 2d colorization looks good but 3d projection always disappoints me when I use these models for robotics tasks

Chonghyuk (Andrew) Song

@ndsong95

5 months

Somebody finally comparing monocular depth estimators the "correct" way: by unprojecting the predicted depth map into 3D points and seeing them from novel views. Marigold performs the best but the human reconstructions still appear a bit "slanted".

0

4

35

0

1

7

Boyuan Chen

@BoyuanChen0

4 months

@xf1280 30 years later it will be Fei twitting how important biking is to robotics

0

7

Boyuan Chen

@BoyuanChen0

1 year

In robotics, data problem is always much bigger than model problem. Glad to see that AI models trained from other sources can be applied to augment the precious data for robotics!

Fei Xia

@xf1280

1 year

Text-to-image generative models, meet robotics! We present ROSIE: Scaling RObot Learning with Semantically Imagined Experience, where we augment real robotics data with semantically imagined scenarios for downstream manipulation learning. Website: 🧵👇

18

180

862

0

1

7

Boyuan Chen

@BoyuanChen0

2 years

SayCan, a recent work, has shown that affordance functions can use used to allow LLM planners to understand what a robot can do from observed *state*. However, SayCan did not provide scene-scale affordance grounding, and thus cannot reason over what a robot can do in a *scene*.

1

7

Boyuan Chen

@BoyuanChen0

5 months

I am at @NeurIPSConf 2023 to present my reinforcement paper “Self-Supervised Reinforcement Learning that Transfers using Random Features”! Let’s catch up everyone!

0

7

Boyuan Chen

@BoyuanChen0

6 months

VoxPoser and NLMap-Saycan will also be mentioned!

1

0

6

Boyuan Chen

@BoyuanChen0

2 years

NLMap builds a natural language queryable scene representation with Visual Language models. An LLM-based object proposal module infers involved objects to query the representation for object availability and location. LLM planner then plans conditioned on such information. 4/6

1

6

Boyuan Chen

@BoyuanChen0

7 months

Maybe robotics will be solved by neither model-based nor imitation learning method, but rather a universal video prediction model!

Sherry Yang

@mengjiao_yang

7 months

Introducing Universal Simulator (UniSim), an interactive simulator of the real world. Interactive website: Paper:

32

246

1K

0

5

Boyuan Chen

@BoyuanChen0

14 days

My colleague Lirui is presenting his famous GemSim (avg score of 8) at ICLR 2024, check it out if you are at the conference! My own paper DittoGym is also accepted to ICLR but unfortunately I cannot attend due to visa issue - our friends will be presenting there!

Lirui Wang (Leroy)

@LiruiWang1

15 days

Excited to share my works on fleet learning, GenSim, PoCo will be presented in #ICLR in Vienna this week! This is my first ML conference in Europe. Look forward to meeting old and new friends in person!

1

5

13

0

1

6

Boyuan Chen

@BoyuanChen0

1 month

@KevinKaichuang @MIT @MIT_CSAIL Exactly why we need boba shop on campus. Checkout this too - Berkeley literally built their engineering building around a boba shop

1

0

6

Boyuan Chen

@BoyuanChen0

6 months

@UnitreeRobotics Still curious, is this RL controller or MPC? Some Stanford friend told me you guys use RL out of box. Is that true?

2

0

5

Boyuan Chen

@BoyuanChen0

1 month

@trishaepan @MIT @MIT_CSAIL It's actually a specialized boba cooker - it has mode for boba, sago, pudding, grass jelly and taro balls!

0

5

Boyuan Chen

@BoyuanChen0

2 years

We combine NLMap with SayCan to show new robotic capabilities NLMap enables in a real office kitchen. NLMap frees SayCan from a fixed list of objects, locations, or executable options. We show 35 tasks that cannot be unachieved by SayCan but is enabled by NLMap. 5/6

1

5

Boyuan Chen

@BoyuanChen0

5 months

@AntonObukhov1 Is this metric or relative depth?

1

0

4

Boyuan Chen

@BoyuanChen0

3 months

Find the recording here:

Boyuan Chen

@BoyuanChen0

3 months

My AI+robotics lecture at MIT is now public! Back in 2023 I talked about how video models will revolutionize robotics, and many other foundation models like LLMs. Now SORA arrives, definitely checkout my lecture on Foundation Models for Decision making at

3

40

202

0

1

5

Boyuan Chen

@BoyuanChen0

4 months

@GoogleDeepMind Is this gap due to the model itself or lack of relevant data? Our work on Spatial VLM answers this question by lifting 10M images into 3D object-centric point clouds in **metric scale**. We then synthesize 2B spatial reasoning Q&A pairs to finetune a multi-modal LLM. (3/6)

1

5

Boyuan Chen

@BoyuanChen0

4 months

@GoogleDeepMind It may surprise you that some of the best multi-modal LLMs struggle with basic spatial concepts like "left-right" or "above-below" in images. This is a stark contrast to humans, who have been intuitively navigating and reasoning about the 3D world since ancient times. (2/6)

1

2

5

Boyuan Chen

@BoyuanChen0

5 months

@zipengfu @tonyzzhao @chelseabfinn @StanfordAILab I cannot believe you rick rolled me

0

4

Boyuan Chen

@BoyuanChen0

6 months

Gensim got added to the list

0

4

Boyuan Chen

@BoyuanChen0

2 months

@svlevine @brian_ichter @chelseabfinn @lachygroom @hausman_k @QuanVng @SurajNair_1 Congratulations to the team! Be the OpenAi for robotics!

0

1

4

Boyuan Chen

@BoyuanChen0

2 years

Shout out to my collaborators on this project. @xf1280 , @brian_ichter , @Kanishka_Rao , @keerthanpg , Austin Stone, @ryoo_michael , and my internship host Daniel Kappler Project Website Link: Video: 6/6

0

1

4

Boyuan Chen

@BoyuanChen0

5 months

@perplexity_ai congrats!

1

0

2

Boyuan Chen

@BoyuanChen0

4 months

@GoogleDeepMind In fact, it's not just about qualitative relationships - it's about understanding qualitative relationships as well, be it distance or size, much like humans. When integrated with CoT, it also unlocks new potential in embodied AI such as a dense reward annotator for RL. (5/6)

1

4

Boyuan Chen

@BoyuanChen0

4 months

@peteflorence Probably latent space of videos. I strongly believe in video prediction

0

1

4

Boyuan Chen

@BoyuanChen0

2 months

@HarryXu12 @ARX_Zhang I guess that means I can afford one myself after my graduation, very nice

1

2

Boyuan Chen

@BoyuanChen0

4 months

@pabbeel @Google @YouTube My setup is 4K video downloader (probably cheaper than premium) + some JavaScript via temper monkey to block YouTube ADs

0

1

4

Boyuan Chen

@BoyuanChen0

3 months

@audrow I think humanoid is not the problem, overfitting demos are why people are frustrated when deploying papers to real world

1

4

Boyuan Chen

@BoyuanChen0

10 months

@hausman_k Hmm isn’t this still very high level? LLM definitely knows things like the robot needs to avoid collision, but not how. Would love to see VLMs make breakthroughs at low level policy.

1

0

4

Boyuan Chen

@BoyuanChen0

4 months

@GoogleDeepMind By scaling up on such synthetic data, Spatial VLM achieves state of the art performance in 3D spatial Q&A, multi-step spatial reasoning compared to the latest multi-modal LLMs, competitive VQA improvement, as well as as many other tasks we show in paper. (4/6)

1

4

Boyuan Chen

@BoyuanChen0

1 year

Super cool work from my friend Tony Zhao! I had the chance to play with an early version of it a year ago and it's super responsive!

Tony Z. Zhao

@tonyzzhao

1 year

Introducing ALOHA 🏖: 𝐀 𝐋ow-cost 𝐎pen-source 𝐇𝐀rdware System for Bimanual Teleoperation After 8 months iterating @stanford and 2 months working with beta users, we are finally ready to release it! Here is what ALOHA is capable of:

94

712

3K

1

3

Boyuan Chen

@BoyuanChen0

5 months

@yukez 🥺Cannot believe that the paper didn’t even mention NLMap(Open-Vocabulary Queryable Scene Representation for real world planning) , we are an early work cited by most of the papers in 4.C and despite the title of section is almost our paper name

0

2

Boyuan Chen

@BoyuanChen0

1 month

@IAmDougLewis @MIT @MIT_CSAIL Checkout my homepage for the blog!

0

3

Boyuan Chen

@BoyuanChen0

2 months

@hausman_k Congratulations! Humans need such effort to gain insights about foundation robot / world models.

0

2

Boyuan Chen

@BoyuanChen0

7 months

Congratulations! I’ve been following your excellent work in 3D generation. Hope you and your team will eventually get the financial return your talent deserves!

Hao Su

@haosu_twitr

7 months

📢Thrilled to announce sudoAI ( @sudoAI_ ), founded by a group of leading AI talents and me!🚀 We are dedicated to revolutionizing digital & physical realms by crafting interactive AI-generated 3D environments! Join our 3D Gen AI model waitlist today! 👉

14

102

429

0

3

Boyuan Chen

@BoyuanChen0

4 months

@1x_tech congratulations!

0

2

Boyuan Chen

@BoyuanChen0

1 month

@Boyiliee @MIT @MIT_CSAIL OMG I need this! Will definitely try to use a robot before I graduate!

0

1

2

Boyuan Chen

@BoyuanChen0

3 years

This is super cool!

0

2

Boyuan Chen

@BoyuanChen0

2 months

@HarryXu12 @ARX_Zhang Is the robot A1 or Go?

1

2

Boyuan Chen

@BoyuanChen0

2 months

@ARX_Zhang Two tips: 1. Meta quest is actually insanely capable too at 1/6 the price 2. Definitely try real time kernel for your Linux

1

0

2

Boyuan Chen

@BoyuanChen0

5 months

@audrow I think manufacturing represents an engineering challenge, but it’s nothing comparable to the challenge of embodied intelligence itself. Current definition of AGI seems to be narrowly focused on modalities where data is plentiful, while robot action data is nowhere close.

0

2

Boyuan Chen

@BoyuanChen0

5 months

My advisor Russ Tedrake will talk in the Foundation Model for Decision Making workshop today at Neurips 2023. Happening at 2:30-3:00 at E2!

Sherry Yang

@mengjiao_yang

5 months

FMDM workshop happening now in Hall E2 with @percyliang giving the first talk and a packed audience.

1

26

0

2

Boyuan Chen

@BoyuanChen0

4 months

@peteflorence Interesting question. If demonstrations are indeed diverse enough, aka with different objects and scenes, you should already see a lot generalization from 10M demos

1

0

2

Boyuan Chen

@BoyuanChen0

13 days

@mengjiao_yang @DrJimFan Congratulation @mengjiao_yang and @du_yilun

1

0

2

Boyuan Chen

@BoyuanChen0

1 month

@BenPielstick @tsarnick Don’t forget about the role of open sourcing of MIT mini cheetah project

0

1

2

Boyuan Chen

@BoyuanChen0

2 months

@chenwang_j @chichengcc @chris_j_paxton Ok given the 1X speed video it’s definitely teleop

0

1

2

Boyuan Chen

@BoyuanChen0

7 months

@Wenxuan_Zhou @davheld Congratulations Dr. Zhou!

0

2

Boyuan Chen

@BoyuanChen0

7 months

@zipengfu @UnitreeRobotics @StanfordAILab Wow is this controlled with RL?

1

0

1

Boyuan Chen

@BoyuanChen0

30 days

@_akhaliq Happy birthday!

0

1

Boyuan Chen

@BoyuanChen0

3 months

@UnitreeRobotics Is this real time video at 1X speed?

0

1

Boyuan Chen

@BoyuanChen0

2 months

@chichengcc @chris_j_paxton Hard to tell from an accelerated video. my feeling is the grasp and motion planning algorithms back from PR2 days can do this just fine. Would love to hear your opinion on the figure robot demo

2

0

1

Boyuan Chen

@BoyuanChen0

1 month

@KevinKaichuang @MIT @MIT_CSAIL Teaholic just opened next to Mulan, it’s good if you don’t mind walking a little bit!

0

1

Boyuan Chen

@BoyuanChen0

5 months

@ericjang11 @1x_tech Wow is this imitation learning or teleop？

0

Boyuan Chen

@BoyuanChen0

2 months

@AravSrinivas I wish chrome will support perplexity in search bar directly

0

1

Boyuan Chen

@BoyuanChen0

2 years

@pathak2206 Congratulations 🎉🎉

0

1

Boyuan Chen

@BoyuanChen0

6 months

@ZhaoMandi Hope you will get your visa soon!

0

1

Boyuan Chen

@BoyuanChen0

3 months

@tonyzzhao @GoogleDeepMind Nice work Tony!

0

1

Boyuan Chen

@BoyuanChen0

5 months

@rosstaylor90 Great explanation!

0

1

Boyuan Chen

@BoyuanChen0

2 months

@ylecun Do you think pixel is the correct space to train the dynamics part of video world models?

0

1

Boyuan Chen

@BoyuanChen0

5 months

@HaochenShi74 @YunzhuLiYZ congratulations!

0

1

Boyuan Chen

@BoyuanChen0

6 months

@Vardhan_Dongre LM-Nav and VLMaps will be mentioned along with NLMap-Saycan. Still thinking about CLIP-Fields as I wonder whether it will fit into the theme of "foundational models"

0

1

Boyuan Chen

@BoyuanChen0

6 months

@chenlin_meng @du_yilun Congratulations!

0

1