Skip to yearly menu bar Skip to main content

Workshop

Scaling Up Intervention Models

Jiaqi Zhang ⋅ Jialin Yu ⋅ Niki Kilbertus ⋅ Cheng Zhang ⋅ Caroline Uhler ⋅ Ricardo Silva

Project Page [ OpenReview]

Abstract

Machine learning and AI have long been concerned about modeling how an agent can change the world around it. However, intervening in the physical world takes effort, leading to sparsity of evidence and the corresponding gaps of credibility when an agent considers carrying out previously unseen actions. Making the most of sparse data within a combinatorial explosion of possible actions, dose levels, and waiting times requires careful thinking, akin to efforts for introducing more compositionality principles into machine learning (Andreas, 2019). The goal of this workshop is to bring together state-of-the-art ideas on how to predict effects of novel interventions and distribution shifts by exploiting original ways of composing evidence from multiple data-generation regimes.

Video

Chat is not available.

Schedule

Timezone: Asia/Seoul

1:00 AM

Opening Remarks

Video

1:10 AM

Text-based Causal Experiments via LLMs

Video

1:40 AM

Generative AI and Virtual Cells for Drug Response Modeling

Video

2:10 AM

From Causal Models to AI Safety Guarantees

Video

2:40 AM

Can Large Language Models Help Experimental Design for Causal Discovery?

Video

2:55 AM

CausalPFN: Amortized Causal Effect Estimation via In-Context Learning.

Video

3:10 AM

Coffee Break

3:30 AM

Poster Session

4:20 AM

Lunch Break

5:30 AM

Scaling data and models: compositional generalisation and active learning in the age of foundation models

Video

6:00 AM

Learning Causality in Open-ended World by Active Intervention

Video

6:30 AM

Causal representation learning and causal generative AI

Video

7:00 AM

Amortized Active Generation of Pareto Sets.

Video

7:15 AM

Competing Event Models: Next Event Prediction Under Interventions.

Video

7:30 AM

Coffee Break

7:50 AM

Poster Session

8:30 AM

Panel discussion

Video

9:00 AM

Closing Remarks

Video

A Meta-Learning Approach to Causal Inference

Dragos Cristian Manta ⋅ Philippe Brouillard ⋅ Dhanya Sridhar

Competing Event Models: Next Event Prediction Under Interventions

Yoav Wald ⋅ Xiang Gao ⋅ Rajesh Ranganath

Learning to Adapt: Self-Supervised Representations for Robust Contextual Bandits

Janos Horvath

TrialCalibre: A Fully Automated Causal Engine for RCT Benchmarking and Observational Trial Calibration

Amir Habibdoust Lafmajani ⋅ Xing Song

Prompt Optimization with Logged Bandit Data

Haruka Kiyohara ⋅ Daniel Cao ⋅ Yuta Saito ⋅ Thorsten Joachims

Towards Causal Representation Learning with Observable Sources as Auxiliaries

Kwonho Kim ⋅ Heejeong Nam ⋅ Inwoo Hwang ⋅ Sanghack Lee

OOD Detection with Relative Angles

Berker Demirel ⋅ Marco Fumero ⋅ Francesco Locatello

Multi-Objective-Guided Discrete Flow Matching for Controllable Biological Sequence Design

Tong Chen ⋅ Yinuo Zhang ⋅ Sophia Tang ⋅ Pranam Chatterjee, PhD

Steering LLM Reasoning Through Bias-Only Adaptation

Viacheslav Sinii ⋅ Alexey Gorbatovski ⋅ Artem Cherepanov ⋅ Boris Shaposhnikov ⋅ Nikita Balagansky ⋅ Daniil Gavrilov

Bidding for Influence: Auction-Driven Diffusion Image Generation

Lillian Sun ⋅ Henry Huang ⋅ Fucheng Zhu ⋅ Giannis Daras ⋅ Constantinos Daskalakis

SOAPIA: Siamese-Guided Generation of Off Target-Avoiding Protein Interactions with High Target Affinity

Sophia Vincoff ⋅ Oscar Davis ⋅ Ismail Ceylan ⋅ Alexander Tong ⋅ Joey Bose ⋅ Pranam Chatterjee, PhD

Deep RL Inventory Management with Supply and Capacity Risk Awareness

Defeng Liu ⋅ Carson Eisenach

Amortized Active Generation of Pareto Sets

Daniel Steinberg ⋅ Asiri Wijesinghe ⋅ Rafael Oliveira ⋅ Piotr Koniusz ⋅ Cheng Soon Ong ⋅ Edwin V. Bonilla

Markov-Boundary Consistent Feature Attribution

Mateusz Gajewski ⋅ Mateusz Olko ⋅ Mikołaj Morzy ⋅ Piotr Sankowski

Quantized Disentanglement: A Practical Approach

Vitória Barin-Pacela ⋅ Kartik Ahuja ⋅ Simon Lacoste-Julien ⋅ Pascal Vincent

Thompson Sampling in Function Spaces via Neural Operators

Rafael Oliveira ⋅ Xuesong Wang ⋅ Kian Ming Chai ⋅ Edwin V. Bonilla

Equipping Graphical Models with Interventions and Interactions Simultaneously

James Enouen ⋅ Angela Zhou ⋅ Yan Liu

An Object-Attribute Decoupled Approach for Learning Disentangled Representation for Image and Video Analysis

Sanket Sanjaykumar Gandhi ⋅ Atul ⋅ Samanyu Mahajan ⋅ Rushil Gupta ⋅ Vishal Sharma ⋅ Arnab Mondal ⋅ Rohan Paul ⋅ Parag Singla

MorphGen: Controllable and Morphologically Plausible Generative Cell-Imaging

Berker Demirel ⋅ Marco Fumero ⋅ Theofanis Karaletsos ⋅ Francesco Locatello

The Third Pillar of Causal Analysis? A Measurement Perspective on Causal Representations

Dingling Yao ⋅ Shimeng Huang ⋅ Riccardo Cadei ⋅ Kun Zhang ⋅ Francesco Locatello

Estimating Interventional Distributions with Uncertain Causal Graphs through Meta-Learning

Anish Dhir ⋅ Cristiana Diaconu ⋅ Valentinian Lungu ⋅ James Requeima ⋅ Richard E Turner ⋅ Mark van der Wilk

scDataset: Scalable Data Loading for Deep Learning on Large-Scale Single-Cell Omics

Davide DAscenzo ⋅ Sebastiano Cultrera di Montesano

Do-PFN: In-Context Learning for Causal Effect Estimation

Jake Robertson ⋅ Arik Reuter ⋅ Siyuan Guo ⋅ Noah Hollmann ⋅ Frank Hutter ⋅ Bernhard Schölkopf

Estimating Causal Effects in Gaussian Linear SCMs with Finite Data

Aurghya Maiti ⋅ Prateek Jain

Estimating treatment effects in networks using domain adversarial learning

Daan Caljon ⋅ Jente Van Belle ⋅ Wouter Verbeke

Enhancing Math Reasoning in Small-sized LLMs via Preview Difficulty-Aware Intervention

xinhan di ⋅ JoyJiaoW

LLMs Struggle to Perform Counterfactual Reasoning with Parametric Knowledge

Khurram Yamin ⋅ Gaurav Ghosal ⋅ Bryan Wilder

Noise Tolerance of Distributionally Robust Learning

Ramzi Dakhmouche ⋅ Ivan Lunati ⋅ Hossein Gorji

Network System Forecasting Despite Topology Perturbation

Ramzi Dakhmouche ⋅ Ivan Lunati ⋅ Hossein Gorji

Towards Robust Causal Effect Identification beyond Markov Equivalence

Kai Teh ⋅ Kayvan Sadeghi ⋅ Terry Soo

Keep the Alignment, Skip the Overhead: Lightweight Instruction Alignment for Continually Trained LLMs

Ishan Jindal ⋅ Badrinath chandana ⋅ Pranjal Bharti ⋅ Lakkidi Vinay ⋅ SACHIN SHARMA

Robust estimation of heterogeneous treatment effects in randomized trials leveraging external data

Rickard K.A. Karlsson ⋅ Piersilvio De Bartolomeis ⋅ Issa Dahabreh ⋅ Jesse H. Krijthe

Learning Treatment Representations for Downstream Instrumental Variable Regression

Shiangyi Lin ⋅ Hui Lan ⋅ Vasilis Syrgkanis

Can Large Language Models Help Experimental Design for Causal Discovery?

Junyi Li ⋅ Yongqiang Chen ⋅ Chenxi Liu ⋅ Qianyi Cai ⋅ Tongliang Liu ⋅ Bo Han ⋅ Kun Zhang ⋅ Hui Xiong

Discovering Hierarchical Latent Capabilities of Language Models via Causal Representation Learning

Jikai Jin ⋅ Vasilis Syrgkanis ⋅ Sham Kakade ⋅ Hanlin Zhang

Off-Policy Learning for Diversity-aware Candidate Retrieval in Two-stage Decisions

Haruka Kiyohara ⋅ Rayhan Khanna ⋅ Thorsten Joachims

CausalPFN: Amortized Causal Effect Estimation via In-Context Learning

Vahid Balazadeh ⋅ Hamidreza Kamkari ⋅ Valentin Thomas ⋅ Benson Li ⋅ Junwei Ma ⋅ Jesse Cresswell ⋅ Rahul G. Krishnan

Multi-Objective-Guided Generative Design of mRNA with Therapeutic Properties

Sawan Patel ⋅ Sophia Tang ⋅ Yinuo Zhang ⋅ Pranam Chatterjee, PhD ⋅ Sherwood Yao

Faithfulness and Intervention-Only Causal Discovery

Bijan Mazaheri ⋅ Jiaqi Zhang ⋅ Caroline Uhler

Failure Modes of LLMs for Causal Reasoning on Narratives

Khurram Yamin ⋅ Shantanu Gupta ⋅ Gaurav Ghosal ⋅ Zachary Lipton ⋅ Bryan Wilder