Danru Xu

17 posts

Danru Xu banner
Danru Xu

Danru Xu

@Danrunnnn

PhD student in multimodal causal representation learning @INDE_LAB_AMS @UvA_Amsterdam

Amsterdam, The Netherlands Katılım Şubat 2022
121 Takip Edilen106 Takipçiler
Danru Xu retweetledi
Jiaqi Zhang
Jiaqi Zhang@JiaqiZhangVic·
📢 Excited to announce the #ICML2025 workshop on *Scaling Up Intervention Models (SIM)*! Let’s bring together state-of-the-art ideas on modeling novel interventions and distribution shifts. :) 🙌🏻 Submissions are welcome! Link: sites.google.com/view/sim-icml2…
Jiaqi Zhang tweet media
English
0
23
113
17K
Danru Xu retweetledi
Núria Armengol
Núria Armengol@NriaArmengol2·
Tired of causally confused agents when learning from offline datasets? We propose 🚣🏼‍♀️CAIAC🚣🏼‍♀️, a method for counterfactual data augmentation to improve the robustness of offline learning agents against extreme distributional shifts at test time. 🧵
English
1
14
63
5.5K
Danru Xu
Danru Xu@Danrunnnn·
☀️ ICML2024 ☀️ Tuesday 11:30-13:00 #2201 ❓Do you want to identify high-level causal variables from perceptual data under partial observable setup? 💡Here we focus on learning from unpaired observations from a dataset with an instance-dependent partial observability pattern.
Danru Xu tweet media
English
7
3
34
7.3K
Danru Xu
Danru Xu@Danrunnnn·
3️⃣Finally, we propose two methods that implement these theoretical results and validate their effectiveness with experiments on simulated data and image benchmarks.
English
0
0
1
212
Danru Xu
Danru Xu@Danrunnnn·
2️⃣We introduce two theoretical results for identifying causal variables up to permutation and element-wise transformation under partial observability. Both results leverage a sparsity constraint.
English
0
0
1
211
Danru Xu
Danru Xu@Danrunnnn·
1️⃣ We formalize the Unpaired Partial Observations setting for causal representation learning, where each partial observation captures only a subset of causal variables.
English
0
0
1
230
Danru Xu retweetledi
ELLIS Amsterdam
ELLIS Amsterdam@Ellis_Amsterdam·
We are excited to announce the newly created seminar series: 🚀Amsterdam Causality Meeting 🚀 📅 Monday October 9th, 15:00-18:00 📍 UvA Science Park room D1.114 🔗 amscausality.github.io Register for the Google Group here: amscausality@googlegroups.com
English
0
8
34
11.6K
Danru Xu retweetledi
CRL workshop at NeurIPS 2023
CRL workshop at NeurIPS 2023@crl_neurips2023·
🚨CFP #Causal #Representation #Learning @NeurIPSConf 2023 WS🚨 Do you have ideas on how to learn #causal representations from raw data, e.g. images, #abstract #macro variables or leverage #causality in #ML? Then submit a max 6 pg paper to our workshop crl-workshop.github.io
NeurIPS Conference@NeurIPSConf

Announcing the NeurIPS 2023 Workshops! We are excited to announce 58 accepted workshops that will take place in-person on December 15 and 16. Read our blog post for more details on workshops and our selection process this year: buff.ly/3ObArv5

English
1
19
36
37.1K

Keşfet

@Dingling_Yao @seblachap @PerouzT @JKugelgen @FrancescoLocat8 @saramagliacane @AmlabUva @luigigres