Daohan Lu

22 posts

Daohan Lu banner
Daohan Lu

Daohan Lu

@fred_lu_443

PhD Student at NYU @NYU_Courant

New York, NY Katılım Temmuz 2022
129 Takip Edilen152 Takipçiler
Sabitlenmiş Tweet
Daohan Lu
Daohan Lu@fred_lu_443·
Despite impressive visuals, current video world models that only generate a single agent’s perspective aren’t modeling a complete world. The complex behaviors that arise from real or virtual worlds do not happen in a vacuum. They arise from interactions among many agents. Instead of modeling a one-agent island, let’s try modeling a multi-agent planet. This led to our project, Solaris [1/9]
English
1
14
78
5.8K
Daohan Lu retweetledi
Ying Wang
Ying Wang@yingwww_·
What is a good latent space for world modeling and planning? 🤔 Inspired by the perceptual straightening hypothesis in human vision, we introduce temporal straightening to improve representation learning for latent planning. 📑: agenticlearning.ai/temporal-strai…
Ying Wang tweet media
English
29
131
781
239.2K
Daohan Lu retweetledi
Daohan Lu retweetledi
Peter Tong
Peter Tong@TongPetersb·
Train Beyond Language. We bet on the visual world as the critical next step alongside and beyond language modeling. So, we studied building foundation models from scratch with vision. We share our exploration: visual representations, data, world modeling, architecture, and scaling behavior! [1/9]
Peter Tong tweet media
English
35
221
1.1K
216.6K
Daohan Lu
Daohan Lu@fred_lu_443·
[10/9] Solaris is our first foray into multi-agent world modeling. While we saw some interesting and surprising findings, it is more so a solid foundation to enable deeper and further experimentation. I’m particularly excited about the complex multi-agent behaviors and phenomena that emerge from learning on open & dynamic multiplayer environments!
English
0
0
3
143
Daohan Lu
Daohan Lu@fred_lu_443·
Despite impressive visuals, current video world models that only generate a single agent’s perspective aren’t modeling a complete world. The complex behaviors that arise from real or virtual worlds do not happen in a vacuum. They arise from interactions among many agents. Instead of modeling a one-agent island, let’s try modeling a multi-agent planet. This led to our project, Solaris [1/9]
English
1
14
78
5.8K
Daohan Lu retweetledi
Shusheng Yang
Shusheng Yang@shushengyang·
Working on Cambrian-S has been a genuinely meaningful learning experience. ❤️ I am grateful to all my amazing collaborators throughout this long journey, especially @jihanyang13, @_ellisbrown, @PinzhiHuang, Zihao Yang, Yue Yu, @TongPetersb, @ZihanZheng71803, Yifan Xu, Muhan Wang, and @fred_lu_443 (also our amazing director‼️). ☺️Thanks to @sainingxie for continuously encouraging us to explore the unknown, pursue crazy ideas, and play the infinite game! 🥰And thanks to all supervisors @sainingxie, @drfeifei, @ylecun for guiding us through the maze. 🌕Mission never ends. Let’s keep building supersensing for superintelligence. 🧵[n/n]
English
0
1
10
558
Daohan Lu retweetledi
Edwin Huang
Edwin Huang@PinzhiHuang·
@sainingxie told us to ONLY work on "crazy ideas." Almost a year ago, we started Cambrian-S because "Supersensing" sounded super crazy. This crazy idea kept me awake and caffeinated for months. Today, all that work is live: Cambrian-S is here. So grateful to have built this alongside this incredible team. Please take a look here. Hope you find this idea crazy as well! Website: cambrian-mllm.github.io/cambrian-s/ Github: github.com/cambrian-mllm/… arXiv: @sainingxie" target="_blank" rel="nofollow noopener">arxiv.org/abs/2511.04670…
Saining Xie@sainingxie

Introducing Cambrian-S it’s a position, a dataset, a benchmark, and a model but above all, it represents our first steps toward exploring spatial supersensing in video. 🧶

English
1
4
29
3.2K
Daohan Lu
Daohan Lu@fred_lu_443·
Behind Cambrian-S are the passionate researchers that drive it. This video is a presentation, but more so representation. I shot the short as an ode to the very humans behind, and these unique, surprising spaces and memories that are we. Please enjoy! May the experiment go on--
Saining Xie@sainingxie

Introducing Cambrian-S it’s a position, a dataset, a benchmark, and a model but above all, it represents our first steps toward exploring spatial supersensing in video. 🧶

English
0
7
24
5.5K
Daohan Lu retweetledi
Yucen Lily Li
Yucen Lily Li@yucenlily·
In our new ICML paper, we show that popular families of OOD detection procedures, such as feature and logit based methods, are fundamentally misspecified, answering a different question than “is this point from a different distribution?” arxiv.org/abs/2507.01831 [1/7]
English
4
49
239
48.3K
Andrew Gordon Wilson
Andrew Gordon Wilson@andrewgwils·
I'm now a Full Professor! I'm very grateful to my students, postdocs, mentors, colleagues, family, and many others. Your support means a lot. I'm so proud of what we've built together, and look forward to the next chapter!
English
77
8
706
44.7K