When building a world model, a common assumption is that the environment has a single, unchanging underlying causal rule, like applying Newton's laws to every situation. However, in truly open-ended environments, the apparent causal mechanism may drift over time because the agent continually encounters novel contexts and operates within a limited observational window. This brings about a problem that, when building a world model, even subtle shifts in policy or environment states can alter the very observed causal mechanisms. In this work, we introduce the Meta-Causal Graph as world models for open-ended environments, a minimal unified representation that efficiently encodes the transformation rules governing how causal structures shift across different latent world states. A single Meta-Causal Graph is composed of multiple causal subgraphs, each triggered by meta state, which is in the latent state space. Building on this representation, we introduce a Causality-Seeking Agent whose objectives are to (1) identify the meta states that trigger each subgraph, (2) discover the corresponding causal relationships by agent curiosity-driven intervention policy, and (3) iteratively refine the Meta-Causal Graph through ongoing curiosity-driven exploration and agent experiences. Experiments on both synthetic tasks and a challenging robot arm manipulation task demonstrate that our method robustly captures shifts in causal dynamics and generalizes effectively to previously unseen contexts.

Concept-based models are an emerging paradigm in deep learning that constrains the inference process to operate through human-interpretable variables, facilitating explainability and human interaction. However, these architectures, on par with popular opaque neural models, fail to account for the true causal mechanisms underlying the target phenomena represented in the data. This hampers their ability to support causal reasoning tasks, limits out-of-distribution generalization, and hinders the implementation of fairness constraints. To overcome these issues, we propose Causally reliable Concept Bottleneck Models (C2BMs), a class of concept-based architectures that enforce reasoning through a bottleneck of concepts structured according to a model of the real-world causal mechanisms. We also introduce a pipeline to automatically learn this structure from observational data and unstructured background knowledge (e.g., scientific literature). Experimental evidence suggests that C2BMs are more interpretable, causally reliable, and improve responsiveness to interventions w.r.t.

When applicants get rejected by a high-stakes algorithmic decision system, recourse explanations provide actionable suggestions for applicants on how to change their input features to get a positive evaluation. A crucial yet overlooked phenomenon is that recourse explanations are performative: When many applicants act according to their recommendations, their collective behavior may shift the data distribution and, once the model is refitted, also the decision boundary. Consequently, the recourse algorithm may render its own recommendations invalid, such that applicants who make the effort of implementing their recommendations may be rejected again when they reapply. In this work, we formally characterize the conditions under which recourse explanations remain valid under their own performative effects. In particular, we prove that recourse actions may become invalid if they are influenced by or if they intervene on non-causal variables. Based on this analysis, we caution against the use of standard counterfactual explanation and causal recourse methods, and instead advocate for recourse methods that recommend actions exclusively on causal variables.

Human-in-the-loop (HIL) imitation learning enables agents to learn complex behaviors safely through real-time human intervention. However, existing methods struggle to efficiently leverage agent-generated data due to dynamically evolving trajectory distributions and imperfections caused by human intervention delays, often failing to faithfully imitate the human expert policy. In this work, we propose Faithful Dynamic Imitation Learning (FaithDaIL) to address these challenges. We formulate learning from human intervention as an online non-convex problem and employ dynamic regret minimization to adapt to the shifting data distribution and track high-quality policy trajectories. To ensure faithful imitation of human expert despite training on mixed agent and human data, we introduce an unbiased imitation objective and achieve it by weighting the behavior distribution relative to the human expert's as a proxy reward. Extensive experiments on MetaDrive and CARLA driving benchmarks demonstrate that FaithDaIL achieves state-ofthe-art performance in safety and task success with significantly reduced human intervention data compared to prior HIL baselines.

Graphical models have been widely used as parsimonious encoders of assumptions of the underlying causal system and provide a basis for causal inferences. Models encoding stronger constraints tend to require higher expressive power, which are also harder, and sometimes impossible to empirically falsify. In this paper, we introduce two new collections of distributions that include counterfactual quantities which are experimentally accessible under counterfactual randomizations. Correspondingly, we define two new classes of graphical models for encoding empirically testable constraints in these distributions. We further present a sound and complete calculus, based on counterfactual calculus, which licenses inferences in these two new models with rules that are within the empirically falsifiable boundary. Finally, we formulate a hierarchy over several graphical models based on the constraints they encode and study the fundamental trade-off between the expressive power and empirical falsifiability of different models across the hierarchy.

We investigate the robustness of Large Language Models (LLMs) to structural interventions by deleting and swapping adjacent layers during inference. Surprisingly, models retain 72-95\% of their original top-1 prediction accuracy without any fine-tuning. We find that performance degradation is not uniform across layers: interventions to the early and final layers cause the most degradation, while the model is remarkably robust to dropping middle layers. This pattern of localized sensitivity motivates our hypothesis of four stages of inference, observed across diverse model families and sizes: (1) detokenization, where local context is integrated to lift raw token embeddings into higher-level representations; (2) feature engineering, where task-and entity-specific features are iteratively refined; (3) prediction ensembling, where hidden states are aggregated into plausible next-token predictions; and (4) residual calibration, where irrelevant features are suppressed to finalize the output distribution. Synthesizing behavioral and mechanistic evidence, we provide a hypothesis for interpreting depth-dependent computations in LLMs.

Most counterfactual inference frameworks traditionally assume acyclic structural causal models (SCMs), i.e. directed acyclic graphs (DAGs).

This position paper argues that there is an urgent need to restructure markets for the information that goes into AI systems. Specifically, producers of information goods (such as journalists, researchers, and creative professionals) need to be able to collectively bargain with AI product builders in order to receive reasonable terms and a sustainable return on the informational value they contribute. We argue that without increased market coordination or collective bargaining on the side of these primary information producers, AI will exacerbate a large-scale "information market failure" that will lead not only to undesirable concentration of capital, but also to a potential "ecological collapse" in the informational commons. On the other hand, collective bargaining in the information economy can create market frictions and aligned incentives necessary for a pro-social, sustainable AI future. We provide concrete actions to support a coalition-based approach to achieve this goal. For example, researchers and developers can establish technical mechanisms such as federated data management tools and explainable data value estimation techniques to inform and facilitate collective bargaining in the information economy. Additionally, regulatory and policy interventions may be introduced to support trusted data intermediary organizations representing guilds or syndicates of information producers.

Times series foundation models (TSFMs) have emerged as a promising paradigm for time series analyses and forecasting, showing remarkable generalization performance across different domains. Despite the efforts made on hallucinations of foundation models, hallucinations of TSFMs have been underexplored in existing literature. In this paper, we formally define TSFM hallucinations in the zero-shot forecasting setting by examining whether a generated forecast exhibits different dynamics from those of the context. Our study reveals that TSFM hallucinations are associated with the loss of context information in hidden states during forward propagation. As such, we propose a methodology to identify signal subspaces of TSFMs and magnify the information through intervention. Experiments demonstrate that our proposed intervention approach effectively mitigates hallucinations and improves forecasting performance. The signal strength measure computed from signal subspaces shows strong predictive power of hallucinations and forecasting performance of the model. Our work contributes to deeper understanding of TSFM trustworthiness that could foster future research in this direction.

Language and vision-language models have shown impressive performance across a wide range of tasks, but their internal mechanisms remain only partly understood. In this work, we study how individual attention heads in text-generative models specialize in specific semantic or visual attributes. Building on an established interpretability method, we reinterpret the practice of probing intermediate activations with the final decoding layer through the lens of signal processing. This lets us analyze multiple samples in a principled way and rank attention heads based on their relevance to target concepts. Our results show consistent patterns of specialization at the head level across both unimodal and multimodal transformers. Remarkably, we find that editing as few as 1% of the heads, selected using our method, can reliably suppress or enhance targeted concepts in the model output.