Danru Xu

PhD student in multimodal causal representation learning @INDE_LAB_AMS @UvA_Amsterdam

[Danru Xu @Danrunnnn]

🎉 Excited to share that our paper “A Sparsity Principle for Partially Observable Causal Representation Learning” was accepted to ICML 2024!

Joint work with a group of great researchers @Dingling_Yao @seblachap @PerouzT @JKugelgen @FrancescoLocat8 @saramagliacane

[Danru Xu @Danrunnnn]

Paper: https://t.co/HipKN5VHZC
Poster: https://t.co/N3ZYM0a8c6
Code: https://t.co/ekI6bjMa0A

📑Joint work with amazing researchers: @seblachap @saramagliacane

[Danru Xu @Danrunnnn]

🏝️AISTATS2026🏝️

Saturday 15:00-18:00 #48

❓Do you want to identify high-level causal variables from perceptual data without any auxiliary/group variable and intervention?

💡 Here we focus on causal variables follow a potentially degenerate Gaussian mixture model.

[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: https://t.co/yLFz3yFOpK

[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. 🧵

[Danru Xu @Danrunnnn]

Paper: https://t.co/F4gk0Q8YvS
Poster: https://t.co/lRJj4dPKFU
Code: https://t.co/La9XvM0U9s

[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 @Danrunnnn]

📝👥 Joint work with a group of great researchers @Dingling_Yao @seblachap @PerouzT @JKugelgen @FrancescoLocat8 @saramagliacane

[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.

[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.

[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.

[Sara Magliacane hiring PhDs at UvA @saramagliacane]

Exciting @AmlabUva seminar by @luigigres (Copenhagen Causality Lab) on "Representation Learning with Orthogonal Coordinate Transformations" today at @UvA_Amsterdam - what insights does #causality provide for generative models with provable guarantees?

[Danru Xu @Danrunnnn]

#ICLR24 Welcome to check out our multi-view CRL work ✨

When: Friday 10:45-12:45 CEST
Where: Hall B
Number: 194

[Dingling Yao @Dingling_Yao]

✨ ICLR2024 Spotlight ✨

Still want to identify causal variables in a partially observed setup?

🦥 We present a unified framework for studying the identifiability of representations learned from simultaneously, partially observed views, such as different data modalities.

🍍

[Danru Xu @Danrunnnn]

@effyli4 @Dingling_Yao @seblachap @PerouzT @JKugelgen @FrancescoLocat8 @saramagliacane Thanks Effy!

[Danru Xu @Danrunnnn]

🎉 Excited to share that our paper “A Sparsity Principle for Partially Observable Causal Representation Learning” was accepted to ICML 2024!

Joint work with a group of great researchers @Dingling_Yao @seblachap @PerouzT @JKugelgen @FrancescoLocat8 @saramagliacane

[Danru Xu @Danrunnnn]

@YujiaZheng9 @Dingling_Yao @seblachap @PerouzT @JKugelgen @FrancescoLocat8 @saramagliacane Thanks Yujia!

[Danru Xu @Danrunnnn]

@erkankkarabulut @Dingling_Yao @seblachap @PerouzT @JKugelgen @FrancescoLocat8 @saramagliacane Thanks Erkan!

[Danru Xu @Danrunnnn]

@SGrafberger @Dingling_Yao @seblachap @PerouzT @JKugelgen @FrancescoLocat8 @saramagliacane Thanks Stefan!

[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

🔗 https://t.co/2Tf4u6mBB6

Register for the Google Group here: [email protected]

[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 https://t.co/Mv9YKl9Y7W