Image de couverture de livre

Beyond the Black Box: Identifiable Interpretation and Control in Generative Models via Causal Minimality

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Kong, Lingjing, Xie, Shaoan, Chen, Guangyi, Sun, Yuewen, Song, Xiangchen, Xing, Eric P., Zhang, Kun
Format:	Preprint
Publié:	2025
Sujets:	Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Advancing Reasoning in Diffusion Language Models with Denoising Process Rewards
par: Xie, Shaoan, et autres
Publié: (2025)

Partial Identifiability for Domain Adaptation
par: Kong, Lingjing, et autres
Publié: (2023)

Learning by Analogy: A Causal Framework for Composition Generalization
par: Kong, Lingjing, et autres
Publié: (2025)

Towards Understanding Extrapolation: a Causal Lens
par: Kong, Lingjing, et autres
Publié: (2025)

SmartCLIP: Modular Vision-language Alignment with Identification Guarantees
par: Xie, Shaoan, et autres
Publié: (2025)

A Dialogue between Causal and Traditional Representation Learning: Toward Mutual Benefits in a Unified Formulation
par: Li, Yan, et autres
Publié: (2026)

CaRiNG: Learning Temporal Causal Representation under Non-Invertible Generation Process
par: Chen, Guangyi, et autres
Publié: (2024)

Learning Discrete Concepts in Latent Hierarchical Models
par: Kong, Lingjing, et autres
Publié: (2024)

Selection, Reflection and Self-Refinement: Revisit Reasoning Tasks via a Causal Lens
par: Deng, Yunlong, et autres
Publié: (2025)

Causal Representation Learning from Multimodal Biomedical Observations
par: Sun, Yuewen, et autres
Publié: (2024)

Counterfactual Generation with Identifiability Guarantees
par: Yan, Hanqi, et autres
Publié: (2024)

Towards Identifiability of Hierarchical Temporal Causal Representation Learning
par: Li, Zijian, et autres
Publié: (2025)

LLM Interpretability with Identifiable Temporal-Instantaneous Representation
par: Song, Xiangchen, et autres
Publié: (2025)

Position: Mechanistic Interpretability Should Prioritize Feature Consistency in SAEs
par: Song, Xiangchen, et autres
Publié: (2025)

Causal Temporal Representation Learning with Nonstationary Sparse Transition
par: Song, Xiangchen, et autres
Publié: (2024)

Causal Representation Learning from Multiple Distributions: A General Setting
par: Zhang, Kun, et autres
Publié: (2024)

Towards Self-Refinement of Vision-Language Models with Triangular Consistency
par: Deng, Yunlong, et autres
Publié: (2025)

Controllable Video Generation with Provable Disentanglement
par: Shen, Yifan, et autres
Publié: (2025)

On the Identification of Temporally Causal Representation with Instantaneous Dependence
par: Li, Zijian, et autres
Publié: (2024)

On the Parameter Identifiability of Partially Observed Linear Causal Models
par: Dong, Xinshuai, et autres
Publié: (2024)

Causal Representation Learning from General Environments under Nonparametric Mixing
par: Ng, Ignavier, et autres
Publié: (2026)

Temporally Disentangled Representation Learning under Unknown Nonstationarity
par: Song, Xiangchen, et autres
Publié: (2023)

Beyond the Black Box: Interpretability of LLMs in Finance
par: Tatsat, Hariom, et autres
Publié: (2025)

Multimodal LLMs under Pairwise Modalities
par: Li, Yan, et autres
Publié: (2026)

Emerging Synergies in Causality and Deep Generative Models: A Survey
par: Zhou, Guanglin, et autres
Publié: (2023)

Nonparametric Identification of Latent Concepts
par: Zheng, Yujia, et autres
Publié: (2025)

Score-based Greedy Search for Structure Identification of Partially Observed Linear Causal Models
par: Dong, Xinshuai, et autres
Publié: (2025)

Reflection-Window Decoding: Text Generation with Selective Refinement
par: Tang, Zeyu, et autres
Publié: (2025)

Controllable Abstraction in Summary Generation for Large Language Models via Prompt Engineering
par: Song, Xiangchen, et autres
Publié: (2025)

Beyond the Black Box: Interpretability of Agentic AI Tool Use
par: Tatsat, Hariom, et autres
Publié: (2026)

Nonstationary Time Series Forecasting via Unknown Distribution Adaptation
par: Li, Zijian, et autres
Publié: (2024)

Revitalizing Black-Box Interpretability: Actionable Interpretability for LLMs via Proxy Models
par: Liu, Junhao, et autres
Publié: (2025)

From Black-Box to White-Box: Control-Theoretic Neural Network Interpretability
par: Moon, Jihoon
Publié: (2025)

SEDGE: Structural Extrapolated Data Generation
par: Zhang, Kun, et autres
Publié: (2026)

Beyond Black-Box AI: Interpretable Hybrid Systems for Dementia Care
par: Kang, Matthew JY, et autres
Publié: (2025)

Beyond Black Boxes: Enhancing Interpretability of Transformers Trained on Neural Data
par: Freeman, Laurence, et autres
Publié: (2025)

Integrating White and Black Box Techniques for Interpretable Machine Learning
par: Vernon, Eric M., et autres
Publié: (2024)

Generative Framework for Personalized Persuasion: Inferring Causal, Counterfactual, and Latent Knowledge
par: Zeng, Donghuo, et autres
Publié: (2025)

Generalized and Personalized Federated Learning with Black-Box Foundation Models via Orthogonal Transformations
par: Kong, Eun Gyung, et autres
Publié: (2025)

Beyond Black-Box Labels: Interpretable Criteria for Diagnosing Subjective NLP Tasks
par: Rair, Nisrine, et autres
Publié: (2026)