TL;DR
The proposed ICRL-SM, a novel method for Implicit Causal Representation Learning from soft interventions using a causal mechanism switch variable, demonstrates strong results on both synthetic benchmarks and real-world image datasets, highlighting the potential of ICRL-SM to bridge the gap between theoretical identifiability and practical applicability.
Causal representation learning aims to discover robust features by exploiting the causal structure underlying data generation. Existing methods require specifying the causal structure a priori, yet different structures demand fundamentally incompatible invariance constraints, and misspecification leads to representatio...
Supervised causal discovery learns to infer causal structure for a new dataset from training datasets paired with structural labels. These training pairs are typically simulated, making the simulator both a source of supervision and a carrier of assumptions about causal graphs, mechanisms, and noise. Understanding the...
A closed-loop prior selection framework is proposed that casts prior injection as a budget-constrained optimization over a candidate prior pool and shows that the use of LLM causal priors stops being manual trial and error and becomes an empirically verifiable selection problem.
Root cause analysis (RCA) is a critical problem in many real-world scenarios. RCA enables the identification of faulty or failing mechanisms in a system by comparing anomalous observations with corresponding reference (i.e., regular) observations. However, existing approaches rely either on heuristic methods or on cond...
Causal foundation models are pretrained neural networks that estimate causal quantities, such as the average treatment effect, on entirely new datasets using in-context learning without requiring model updates.
Multimodal large language models often capture visual-linguistic correlations but struggle to predict how local visual interventions propagate and affect downstream answers. We introduce InfluenceField, an intervention-aware latent field inserted between the visual encoder and language decoder. It lifts patch features...
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
