Sammy Joe Christen
@sammy_j_c
Followers
381
Following
303
Media
12
Statuses
111
Postdoctoral Researcher @Disney | former PhD Student @ait_eth at ETH Zurich | AI research intern @AIatMeta | intern @NVIDIA AI Robotics Lab
Joined January 2012
A model that generates hand-object interactions based on text prompts!. I'm happy to share our @SIGGRAPHAsiapaper “DiffH2O: Diffusion-Based Synthesis of Hand-Object Interactions from Textual Descriptions”.
2
17
70
RT @OHilliges: Sadly, I am no longer a professor at ETH (@eth_en) due to very severe #longCovid and #MECFS.
0
133
0
If you are at #RSS2025, check out our workshop on Generative AI for Human-Robot Interaction. We have a stacked lineup of speakers and panelists!.
Interested in how generative AI can be used for human-robot interaction?. We’re organizing the 2nd Workshop on Generative AI for Human-Robot Interaction (GenAI-HRI) at #RSS2025 in LA — bringing together the world's leading experts in the field. The workshop is happening on Wed,
4
4
11
📢 Interested in generating realistic hand motions from text prompts?. If you are at CVPR this week, come check out our paper LatentHOI, a method that uses latent diffusion and generalizes well to unseen object geometry!. 📍 Poster Session 4, #155 .📅 Saturday.
Want to generate realistic hand–object manipulations for unseen objects?. Check out our new paper: "LatentHOI: On the Generalizable Hand Object Motion Generation with Latent Hand Diffusion". Appearing at #CVPR2025 in Nashville!
1
2
15
RT @IlirAliu_: A robot hand grasp over 500 totally new objects without fail? Zero-shot, single-view & super reliable .⬇️ + Paper. Grasping….
0
95
0
RT @Hui_Zhang_eth: Want to grasp almost "anything" with a dexterous hand? Our recent work, RobustDexGrasp, makes it possible. Trained entir….
0
21
0
📢 Taking a single image of a human grasping an object and having real robot hands grasp the object accordingly?. Such one-shot functional grasping is now possible with FunGrasp, published in RA-L! Happy to finally have transferred our method D-Grasp to the real world 🥳.
🎉 Excited to share that FunGrasp has been accepted to RA-L!.We will present it at #IROS2025 in Hangzhou. See you there!.
0
1
5
RT @liangpan_t: This year, an important mission is to let simulated humanoids solve long-term manipulation tasks in challenging dynamic, cl….
0
129
0
RT @NVIDIARobotics: 🚨Introduced at #GTC25: Newton is an open-source extensible physics engine being developed by NVIDIA, @GoogleDeepMind, a….
0
262
0
RT @Wanyue__Z: 🚀 Check out our #CVPR2025 paper BimArt! 👐🔧.We generate 3D bimanual interactions with articulated objects by:.✅ Predicting co….
0
26
0
RT @xu_sirui: Interested in:.✅Humanoids mastering scalable motor skills for everyday interactions.✅Whole-body loco-manipulation w/ diverse….
0
46
0
RT @jiaman01: 🤖 Introducing Human-Object Interaction from Human-Level Instructions! First complete system that generates physically plausib….
0
112
0
RT @jinkuncao: Our NeurIPS work Omnigrasp's poster session will be at this Friday!. 11 a.m. PST — 2 p.m. PSTEast Exhibit Hall A-C #4108. Fe….
0
4
0
Interested in making image latent diffusion models more efficient? Check out Morteza's NeurIPS paper!.
Excited to present our recent work "LiteVAE: Lightweight and Efficient Variational Autoencoders for Latent Diffusion Models" next week at #NeurIPS2024. Please join us at our poster session next Thursday (December 12th) from 11:00 - 14:00 at East Exhibit Hall A-C #2604. 👇🧵.
0
0
1
RT @3DVconf: #3DV2025AMA Fourth guest on the Ask Me Anything series:. Jia-Bin Huang @jbhuang0604 from University of Maryland & Meta! Jia-B….
0
7
0
Check out Marcel's amazing talk and synthetic dataset! Given 3 photos from your cell phone, you can synthesize high-quality novel views 🤯.
Yesterday, we presented Cafca---our latest work on casual few-shot face captures---at @SIGGRAPHAsia in Tokyo. Check out our talk:. We release a dataset of 1.7 Mio. multi-view, multi-environment, multi-expression face images for research.
0
0
2
We also provide detailed textual descriptions for the popular GRAB (@omidtaherii) dataset! . Project Page: Paper: Great collaboration with: @hampaliS, Fadime Sener, Edoardo Remelli, @tomhodan, Eric Sauser, Shugao Ma, Bugra Tekin
0
0
4
The core idea is to employ a two-stage diffusion approach that splits generation into grasping and interaction, and use a compact representation that couples hand and objects. Given a single prompt, our model generates diverse outputs, even on unseen object geometry.
1
0
2
Teaching dexterous robotic hands to grasp like humans is one of the holy grails in robotics. In this project, we take a step towards achieving this goal! Our method enables functional grasping of unseen objects from single images of human grasps.
People grasp objects with different poses for different tasks. Can dexterous robots possess similar functional grasping capabilities? Our recent work FunGrasp enables this for various unseen objects, diverse task-specific poses, and different robot hands.
0
0
6
RT @3DVconf: #3DV2025AMA Third guest on the Ask Me Anything series: . Noah Snavely @Jimantha from Cornell & Google DeepMind! 🌟. 🕒 You have….
0
6
0