Detecting hidden confounding is crucial for reliable causal analysis from observational data, directly determining which downstream causal inference method to be deployed. Inspired by the theory of higher-order regression, recent sample-efficient hypothesis testing strategies overcome the restrictive requirement of mul...
Yi-Kai Chen, Hao-Tian Wang, Yunxin Mao et al.· Proceedings of the Thirty-Fi...· 0 citations
Diffusion Language Models (DLMs) have attracted significant attention for their strong reasoning ability. However, under a bidirectional attention mechanism, DLMs operate over an exponentially large exploration space compared to autoregressive models (ARMs), making it challenging to focus on reasoning-guiding tokens un...
Dian Jin, Kai-Rong Han, Bao-Hong Li et al.· 0 citations
Structural causal models for time series recover contemporaneous and lagged effects, but most methods require complete observation windows and become misspecified when samples are missing. We introduce ITSY, the first continuous-optimization method for causal discovery from irregular time series under a linear model. I...
Wen-Bo Xu, Yue He, Yun-Hai Wang et al.· 0 citations
Traditional search engines struggle to synthesize fragmented information for complex queries, while generative AI search engines face challenges in relevance, comprehensiveness, and presentation. To address these limitations, we introduce Xinyu AI Search, a novel system that incorporates a query-decomposition graph to...
Bo Tang, Junyi Zhu, Ang Li et al.· Proceedings of the 32nd ACM...· 0 citations
StablePFN is proposed, a novel tabular foundation model that integrates explicit causal awareness with stable predictive modeling and significantly outperforms state-of-the-art baselines in cross-environment prediction settings, particularly in challenging high-bias scenarios.
Zheng Guan, Yikang Chen, Hao Qian et al.· Proceedings of the 32nd ACM...· 0 citations
DAG-FM is proposed, a novel foundation model architecture that amortizes causal discovery and introduces Mixture-of-Leaf-Experts (MoLE) to handle diverse and unknown Functional Causal Model (FCM) assumptions in real-world scenarios.
