So grateful for the outstanding honorable mention at the main conference for motion attribution as well as a best paper award at f2s workshop for our most recent work on memory for world models❤️
Both works ask a similar question: how can we better compress and control the temporal information that shapes a video model’s behavior.
What a week! I learned a lot from the community. Excited for what’s next in world models 🥰
#ICML2026
🏆Announcing the #ICML2026 Awards! 🏆
Including Outstanding Papers (research paper & position paper, winner & honorable mentions) and the Test of Time Award!
Check out the blog post for all winners (or read on), laudatio, & description of the processes.
https://t.co/jiUEsUpxws
生成型データセット蒸留に関する以下の論文(主著:M2 李 銘卓)が国際論文誌 IEEE Open Journal of Signal Processing(IF=2.7)に採択されました!意味的情報を考慮した Semantic-aware Sampling(SAS)により,生成型データセット蒸留におけるサンプリング過程を高度化しています.
Mingzhuo Li et al., “SAS: Semantic-aware sampling for generative dataset distillation,” IEEE OJSP, 2026.
本研究はトロント大学・東京大学との共同研究であり,ICIP 2026にても発表予定です.
🚀 Code released for “Predictive but Not Plannable: RC-aux for Latent World Models”.
RC-aux adds lightweight reachability correction to latent world models,improving planning without changing the LeWM backbone.
🔗 https://t.co/onf53Epy2q
#WorldModels#RobotLearning
The formulation here is neat: selecting data from a large training set is a non-stationary control problem, since sample utility changes as the model learns. Data Agent handles this with a lightweight PPO policy and modular rewards.
Excited to share that Data Agent has been accepted to #icml2026@icmlconf
🎉 Data Agent asks: Can a model learn which data it needs during training?
Highlights:
✅ Modular reward designs
✅ Very lightweight agent
✅ Plug-and-play across vision models and LLMs
some news: I’ve joined OpenAI.
After wrapping up my PhD in Robotics, I’m excited to keep working toward AGI in the physical world.
exciting journey ahead :)