Identifiability is proven for recurrent nonlinear switching dynamical systems under flexible assumptions, and ΩSDS is introduced as a flow-based estimator that improves disentanglement and forecasting over VAE-based methods.
hub
Proceedings of the IEEE , volume=
11 Pith papers cite this work. Polarity classification is still indexing.
11
Pith papers citing it
hub tools
citation-role summary
method 1
citation-polarity summary
years
2026 11roles
method 1polarities
use method 1representative citing papers
NoisyCausal benchmark tests LLMs on causal reasoning with structured noise, and a modular LLM-plus-causal-graph framework outperforms baselines while generalizing to Cladder.
NEO is a probabilistic neural model that induces compositional programs as a learned Language of Thought from non-textual observations and executes them via a shared transition model to enable explanation-driven generalization.
PerturbedVAE disentangles perturbation-specific signals from invariant gene expression structure to recover causal representations and improve out-of-distribution prediction in single-cell perturbation modeling.
Ada-Diffuser is a causal diffusion model that jointly learns observed interaction structure and underlying latent dynamics from minimal observations for adaptive planning and policy learning.
MOSAIC recovers identifiable latent variables and their sparse associated observations in scientific time series by combining temporal causal representation learning with support recovery through a sparse additive decoder.
Unsupervised embedding proxies for social constructs are non-identified mixtures of target and confounders, so the Construct Validity Protocol plus Counterfactual Neutralization are required to turn them into defensible measures.
CausalMix fits a causal model on 512 runs of a 0.5B model to estimate CATE, then extrapolates optimal mixtures for an 800K data pool applied to 7B and 4B models, outperforming RegMix.
ERPPO adds a DSA-based ambiguity estimator to MAPPO and switches between L1 and L2 entropy regularization to improve exploration and stability in non-stationary multi-dimensional observations.
Absorber LLM introduces causal synchronization to absorb context into parameters for memory-efficient long-context LLM inference while preserving causal effects.
Causality resolves trade-offs in trustworthy AI by treating them as invariance conflicts under different data-generating process changes.
citing papers explorer
-
End-to-End Identifiable and Consistent Recurrent Switching Dynamical Systems
Identifiability is proven for recurrent nonlinear switching dynamical systems under flexible assumptions, and ΩSDS is introduced as a flow-based estimator that improves disentanglement and forecasting over VAE-based methods.
-
NoisyCausal: A Benchmark for Evaluating Causal Reasoning Under Structured Noise
NoisyCausal benchmark tests LLMs on causal reasoning with structured noise, and a modular LLM-plus-causal-graph framework outperforms baselines while generalizing to Cladder.
-
Learning to Theorize the World from Observation
NEO is a probabilistic neural model that induces compositional programs as a learned Language of Thought from non-textual observations and executes them via a shared transition model to enable explanation-driven generalization.
-
What Makes a Representation Good for Single-Cell Perturbation Prediction?
PerturbedVAE disentangles perturbation-specific signals from invariant gene expression structure to recover causal representations and improve out-of-distribution prediction in single-cell perturbation modeling.
-
Ada-Diffuser: Latent-Aware Adaptive Diffusion for Decision-Making
Ada-Diffuser is a causal diffusion model that jointly learns observed interaction structure and underlying latent dynamics from minimal observations for adaptive planning and policy learning.
-
MOSAIC: Module Discovery via Sparse Additive Identifiable Causal Learning for Scientific Time Series
MOSAIC recovers identifiable latent variables and their sparse associated observations in scientific time series by combining temporal causal representation learning with support recovery through a sparse additive decoder.
-
The Proxy Presumption: From Semantic Embeddings to Valid Social Measures
Unsupervised embedding proxies for social constructs are non-identified mixtures of target and confounders, so the Construct Validity Protocol plus Counterfactual Neutralization are required to turn them into defensible measures.
-
CausalMix: Data Mixture as Causal Inference for Language Model Training
CausalMix fits a causal model on 512 runs of a 0.5B model to estimate CATE, then extrapolates optimal mixtures for an 800K data pool applied to 7B and 4B models, outperforming RegMix.
-
ERPPO: Entropy Regularization-based Proximal Policy Optimization
ERPPO adds a DSA-based ambiguity estimator to MAPPO and switches between L1 and L2 entropy regularization to improve exploration and stability in non-stationary multi-dimensional observations.
-
Absorber LLM: Harnessing Causal Synchronization for Test-Time Training
Absorber LLM introduces causal synchronization to absorb context into parameters for memory-efficient long-context LLM inference while preserving causal effects.
-
Trustworthy AI Suffers from Invariance Conflicts and Causality is The Solution
Causality resolves trade-offs in trustworthy AI by treating them as invariance conflicts under different data-generating process changes.