Robin Walters

90 posts

Robin Walters

Robin Walters

@RobinSFWalters

Asst. Prof. at Khoury College of CS at Northeastern

Boston, MA Katılım Şubat 2020
199 Takip Edilen484 Takipçiler
Robin Walters retweetledi
Marco Pacini
Marco Pacini@MarcoPacini4·
Our paper "On Universality of Deep Equivariant Networks" will appear at ICLR 2026. We show that appropiate depth or readout layers are enough to reach universality up to the separation constraint imposed by the architecture, e.g., WL for IGNs. arxiv.org/abs/2510.15814
English
3
13
121
7.9K
Robin Walters retweetledi
GRaM Workshop at ICLR 2026
GRaM Workshop at ICLR 2026@GRaM_org_·
📢The second edition of ✨GRaM workshop✨ is here this time at #ICLR26. 🌟Submit your exciting works in Geometry-grounded representations. We welcome submissions in multiple tracks i.e. 📄 Proceedings 📝extended abstract 👩‍🏫Tutorial/blogpost as well as an exciting challenge!
GRaM Workshop at ICLR 2026 tweet media
English
1
22
41
11.8K
Robin Walters retweetledi
Haibo Zhao
Haibo Zhao@ZhaoHaibo47588·
Excited to share our #ICML2025 paper, Hierarchical Equivariant Policy via Frame Transfer. Our Frame Transfer interface imposes high-level decision as a coordinate frame change in the low-level, boosting sim performance by 20%+ and enabling complex manipulation with 30 demos.
English
2
12
46
4.9K
Robin Walters retweetledi
Bo Zhao
Bo Zhao@BoZhao__·
When and why are neural network solutions connected by low-loss paths? In our #ICML2025 paper, we show that mode connectivity often arises from symmetries—transformations of parameters that leave the network’s output unchanged. Paper: arxiv.org/abs/2505.23681 (1/6)
Bo Zhao tweet media
English
11
29
201
17K
Robin Walters retweetledi
Boston Symmetry Group
Boston Symmetry Group@bostonsymmetry·
Save the date -- Boston Symmetry Day 2025 will be held on March 31st, at Northeastern University! Speakers and sponsors to be announced in the coming weeks, but you can expect another great lineup of talks, networking, and posters. We'll see you there!
Boston Symmetry Group tweet media
English
0
5
16
1.7K
Robin Walters retweetledi
Bo Zhao
Bo Zhao@BoZhao__·
What can we learn from neural network model weights? Join us for the Weight Space Learning Workshop at #ICLR2025! @iclr_conf 📄Accepting extended abstracts & full papers 🗓️Submission Deadline: Feb 4, 2025 🔗weight-space-learning.github.io
Bo Zhao tweet media
English
0
8
40
4.5K
Robin Walters retweetledi
Dian Wang
Dian Wang@Dian_Wang_·
Honored to receive my first best paper nomination from @corl_conf! Had such a great time at #CoRL2024, huge thanks to the organizing committee and all my co-authors: Steve, David, @tarikkelestemur, @HaojieHuang13, @ZhaoHaibo47588, Mark, JW, @RobinSFWalters, @RobotPlatt!
Dian Wang tweet mediaDian Wang tweet mediaDian Wang tweet mediaDian Wang tweet media
Dian Wang@Dian_Wang_

Introducing Equivariant Diffusion Policy, a novel sample efficient BC algorithm based on equivariant diffusion. Our method leverages the symmetry in policy denoising to boost learning — needing 5x less training data in sim and mastering complex tasks in real-world with <60 demos.

English
14
6
89
9.8K
Robin Walters retweetledi
Haojie Huang
Haojie Huang@HaojieHuang13·
Generate the goal state and then infer the manipulation pick-place action. Feel free to check poster session 4 at #36 for details.
Helping Hands Lab @ Northeastern@HelpingHandsLab

#CoRL2024 IMAGINATION POLICY: Using Generative Point Cloud Models for Learning Manipulation Policies Led by @HaojieHuang13. A key-frame multi-task policy can generate key poses (imagine) and do manipulation precisely with sample efficiency. Presenting at Poster Session 4.

English
0
4
4
942
Robin Walters retweetledi
Helping Hands Lab @ Northeastern
Helping Hands Lab @ Northeastern@HelpingHandsLab·
#CoRL2024 IMAGINATION POLICY: Using Generative Point Cloud Models for Learning Manipulation Policies Led by @HaojieHuang13. A key-frame multi-task policy can generate key poses (imagine) and do manipulation precisely with sample efficiency. Presenting at Poster Session 4.
Helping Hands Lab @ Northeastern tweet media
English
1
9
18
4.9K
Robin Walters retweetledi
Dian Wang
Dian Wang@Dian_Wang_·
#CoRL2024 Looking forward to presenting Equivariant Diffusion Policy at Oral Session 1 on Nov 6 and Poster Session 2 on Nov 7! Also checkout equidiff.github.io for the paper and code.
Helping Hands Lab @ Northeastern@HelpingHandsLab

#CoRL2024 Equivariant Diffusion Policy Led by @Dian_Wang_. A sample efficient BC algorithm based on equi diffusion. It leverages symmetry to boost learning with 5x less training data and mastering complex tasks with <60 demos. Presenting at Oral Session 1 and Poster Session 2.

English
0
6
53
4.3K
Robin Walters retweetledi
Boce Hu
Boce Hu@boce_hu·
Grasp detection is crucial for robotic manipulation but remains challenging in SE(3). We introduce our #CoRL2024 paper: OrbitGrasp, an SE(3)-equivariant grasp learning framework using spherical harmonics for 6-DoF grasp detection. 🌐 orbitgrasp.github.io
English
4
33
126
19.8K
Robin Walters retweetledi
Evangelos Chatzipantazis
Evangelos Chatzipantazis@EChatzipantazis·
Join us on Monday October. 14th at 2pm (UTC+4) in #IROS2024 Workshop on Equivariant Robotics. A great lineup of keynote speakers will discuss how symmetry penetrates each and every subfield of robotics. Website and Zoom Link: equirob2024.github.io
Evangelos Chatzipantazis tweet media
English
1
9
25
3.1K
Robin Walters retweetledi
Dian Wang
Dian Wang@Dian_Wang_·
Introducing Equivariant Diffusion Policy, a novel sample efficient BC algorithm based on equivariant diffusion. Our method leverages the symmetry in policy denoising to boost learning — needing 5x less training data in sim and mastering complex tasks in real-world with <60 demos.
English
2
44
232
36.6K
Robin Walters
Robin Walters@RobinSFWalters·
It's interesting that the much higher dimensional problem of point cloud generation leads to be better performance in the low dimensional problem of finding the best SE(3) pose. It might be point clouds have more geometric structure or another victory for overparameterization.
Haojie Huang@HaojieHuang13

Excited to publish our recent work - Imagination Policy: Using Generative Point Cloud Models for Learning Manipulation Policies! It generated the imagination of the key-frame actions and achieved very high sample efficiency. Project Website: haojhuang.github.io/imagine_page/

English
0
1
11
687
Robin Walters retweetledi
Haojie Huang
Haojie Huang@HaojieHuang13·
Excited to publish our recent work - Imagination Policy: Using Generative Point Cloud Models for Learning Manipulation Policies! It generated the imagination of the key-frame actions and achieved very high sample efficiency. Project Website: haojhuang.github.io/imagine_page/
English
4
11
45
6K
Robin Walters
Robin Walters@RobinSFWalters·
The reviewing quality was exceptional. Thank you to our fantastic reviewers!
Sharvaree Vadgama@SharvVadgama

@GRaM_workshop decisions are out now! Woohoo! 🎉🎉 What a delight it was to read your 🌟brilliant papers 🌟! We are thrilled to announce that we now have some great accepted extended abstracts and wonderful full papers accepted in the proceedings track to be published in PMLR.

English
0
1
8
963

Keşfet

@iclr_conf @GRaM_org_ @Dian_Wang_ @_davidklee @HengT0812 @XupengZ @HaojieHuang13 @RobotPlatt