We sadly found out our CTM paper (ICLR24) was plagiarized by TCD! It's unbelievable😢—they not only stole our idea of trajectory consistency but also comitted 'verbatim plagiarism,' literally copying our proofs word for word! Please help me spread this.

Happy to see many ICLR24 works push the sota of vision-language robot manipulation on the CALVIN benchmark! A common trend of these works, SuSIE, RoboFlamingo and GR-1, is the use of large scale video generative pre-training 📺🕹️
Updated leaderboard: calvin.cs.uni-freiburg.de

🚀 I can genuinely say that #ICLR24 ICLR 2024 was the best conference I have attended so far. It was incredible to share our research with such a distinguished audience and engage in great discussions, especially with all the awesome people from the #TabularData community! (1/4)

ICLR24 Spotlight: To train general-purpose SSL models, it's important to measure the quality of representations during training. But how can we do this w/o downstream labels?
We propose a new label-free metric to eval SSL models, called Linear Discrimination Analysis Rank(LiDAR)

I will be presenting Symphony, a simple yet effective E(3)-equivariant autoregressive model for 3D molecular generation at #ICLR24 ! Poster Location: Halle B #6 at 4:30 PM in Halle B!

#ICLR24 How do LLM-agents respond to dynamically changing environments characterized by unexpected events?

Introducing 🕵️HAZARD Challenges🕵️, a new embodied AI benchmark designed to assess decision-making capabilities in dynamic situations!

vis-www.cs.umass.edu/hazard

Ever wanted to rewire a graph but you couldn't decide on what heuristic to use👀? Fear not! Our #ICLR24 PR-MPNN method eliminates the need to ask ChatGPT for a list of interesting graph properties and learns how to automatically do rewiring in an end-to-end manner 🤯. 🧵 1/n

#ICLR24 🚀🚀 Introduce DIFFTACTILE, A physics-based differentiable tactile simulation system designed to enhance contact-rich robotic manipulation with dense and physically accurate tactile feedback!

👉👉Project page: difftactile.github.io
✅✅ Code: github.com/Genesis-Embodi…

#ICLR24 Introduce ThinShellLab:

- A fully differentiable simulator for robotic interactions with diverse thin-shell materials possessing varying material properties.

- Mastering thin-shell manipulation becomes easy in both simulation and the real world!

vis-www.cs.umass.edu/ThinShellLab

Will present a new speech SSL encoder, 𝙈𝙍-𝙃𝙪𝘽𝙀𝙍𝙏, at #ICLR24 today!

⏰5/9 (Thu): 16:30-18:30 @ Hall B, #62 (Spotlight)
📃Multi-resolution HuBERT: Multi-resolution Speech Self-Supervised Learning with Masked Unit Prediction
openreview.net/forum?id=kUuKF…

Check more details👇

Learning to design protein-protein interactions with enhanced generalization ICLR24'
- PPIRef, the largest and non-redundant dataset of 3D protein–protein interactions,
- PPIformer, a new SE(3)- equivariant model generalizing across diverse protein-binder variants.
- Finetune

ICLR 2024 論文読み会
面白そう

lycorptech-jp.connpass.com/event/316850/ #iclr24_reading

6月4日(火)19:00より機械学習分野の国際会議「ICLR 2024」で発表された論文の読み会を開催します。
登壇者が注目した論文をピックアップしてLT形式で発表します。学生/社会人問わず興味のある方でしたらどなたでも参加可能ですので、お気軽にご登録ください！ #iclr24_reading
lycorptech-jp.connpass.com/event/316850/

🥳 #DragonDiffusion [ICLR24, spotlight] Codes are released in github.com/MC-E/DragonDif…

It supports various fine-grained image editing tasks.

Thanks to coauthors: chong mou, Ying Shan 😀

Hello, #ICLR24 in Vienna, Austria! 🇦🇹🌄

I can’t wait to share our *developing* #PhD work to understand the changing global climate & disaster risks using time-series EO 🛰️ & AI at the 2nd ML4RS workshop on May 11th. #DRR AI for Environmental Risks CDT

See you at ICLR24, Vienna!

Flying Nightjet to Vienna #ICLR24
🤖🇦🇹🌚🌃🚂🚃🚃🚃💨🌃

#ICLR24 will be fun they said

#ICLR24
We proposed FourTran, a very sample-efficient 3D manipulation pick-place model.

1. It can learn a nontrivial 3D policy with less than 10 demos.
2. It represents 3D action distribution in Fourier Space.

Check it in the Poster Session 4 at 4:30 PM Vienna time (10:30 EDT)

#iclr24 pear review has started.