Image de couverture de livre

Towards Theoretical Understandings of Self-Consuming Generative Models

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Fu, Shi, Zhang, Sen, Wang, Yingjie, Tian, Xinmei, Tao, Dacheng
Format:	Preprint
Publié:	2024
Sujets:	Machine Learning Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

A Theoretical Perspective: How to Prevent Model Collapse in Self-consuming Training Loops
par: Fu, Shi, et autres
Publié: (2025)

A Theoretical Survey on Foundation Models
par: Fu, Shi, et autres
Publié: (2024)

InfoRM: Mitigating Reward Hacking in RLHF via Information-Theoretic Reward Modeling
par: Miao, Yuchun, et autres
Publié: (2024)

Drawback of Enforcing Equivariance and its Compensation via the Lens of Expressive Power
par: Chen, Yuzhu, et autres
Publié: (2025)

Why Self-Rewarding Works: Theoretical Guarantees for Iterative Alignment of Language Models
par: Fu, Shi, et autres
Publié: (2026)

Offline Behavior Distillation
par: Lei, Shiye, et autres
Publié: (2024)

CoVeR: Conformal Calibration for Versatile and Reliable Autoregressive Next-Token Prediction
par: Chen, Yuzhu, et autres
Publié: (2025)

Self-Correcting Self-Consuming Loops for Generative Model Training
par: Gillman, Nate, et autres
Publié: (2024)

Neuron-level Balance between Stability and Plasticity in Deep Reinforcement Learning
par: Lan, Jiahua, et autres
Publié: (2025)

HRP: High-Rank Preheating for Superior LoRA Initialization
par: Chen, Yuzhu, et autres
Publié: (2025)

Continual Learning on Graphs: Challenges, Solutions, and Opportunities
par: Zhang, Xikun, et autres
Publié: (2024)

Efficient Differentiable Causal Discovery via Reliable Super-Structure Learning
par: Ma, Pingchuan, et autres
Publié: (2026)

Image Captions are Natural Prompts for Text-to-Image Models
par: Lei, Shiye, et autres
Publié: (2023)

Continual Task Learning through Adaptive Policy Self-Composition
par: Hu, Shengchao, et autres
Publié: (2024)

Towards Understanding Deep Learning Model in Image Recognition via Coverage Test
par: Li, Wenkai, et autres
Publié: (2025)

Towards Understanding Text Hallucination of Diffusion Models via Local Generation Bias
par: Lu, Rui, et autres
Publié: (2025)

Adaptive Defense against Harmful Fine-Tuning for Large Language Models via Bayesian Data Scheduler
par: Hu, Zixuan, et autres
Publié: (2025)

Prompt Tuning with Diffusion for Few-Shot Pre-trained Policy Generalization
par: Hu, Shengchao, et autres
Publié: (2024)

When and How Human Curation Backfires: Preference Alignment under Multi-Model Self-Consuming Loop
par: Zhang, Yang, et autres
Publié: (2026)

Revisiting Plasticity in Visual Reinforcement Learning: Data, Modules and Training Stages
par: Ma, Guozheng, et autres
Publié: (2023)

A Step Back: Prefix Importance Ratio Stabilizes Policy Optimization
par: Lei, Shiye, et autres
Publié: (2026)

Offline Behavioral Data Selection
par: Lei, Shiye, et autres
Publié: (2025)

Toward a Unified Geometry Understanding: Riemannian Diffusion Framework for Graph Generation and Prediction
par: Gao, Yisen, et autres
Publié: (2025)

Towards Theoretical Understanding of Transformer Test-Time Computing: Investigation on In-Context Linear Regression
par: Chen, Xingwu, et autres
Publié: (2025)

Towards General-Purpose Model-Free Reinforcement Learning
par: Fujimoto, Scott, et autres
Publié: (2025)

A Theoretical Understanding of Gradient Bias in Meta-Reinforcement Learning
par: Feng, Xidong, et autres
Publié: (2021)

Physics-Guided Multimodal Transformers are the Necessary Foundation for the Next Generation of Meteorological Science
par: Han, Jing, et autres
Publié: (2025)

Intra-Trajectory Consistency for Reward Modeling
par: Zhou, Chaoyang, et autres
Publié: (2025)

Specialization after Generalization: Towards Understanding Test-Time Training in Foundation Models
par: Hübotter, Jonas, et autres
Publié: (2025)

Improving Large Language Models with Concept-Aware Fine-Tuning
par: Chen, Michael K., et autres
Publié: (2025)

Theoretical Modeling of Large Language Model Self-Improvement Training Dynamics Through Solver-Verifier Gap
par: Sun, Yifan, et autres
Publié: (2025)

Towards Unraveling and Improving Generalization in World Models
par: Fang, Qiaoyi, et autres
Publié: (2024)

Factorize to Generalize: Retrieval-Guided Invariant-Dynamic Decomposition for Time Series Forecasting
par: Chi, Jinjin, et autres
Publié: (2026)

Distillation Traps and Guards: A Calibration Knob for LLM Distillability
par: Zhan, Weixiao, et autres
Publié: (2026)

MOSS: Self-Evolution through Source-Level Rewriting in Autonomous Agent Systems
par: Cai, Qianshu, et autres
Publié: (2026)

FreDF: Learning to Forecast in the Frequency Domain
par: Wang, Hao, et autres
Publié: (2024)

RL-STaR: Theoretical Analysis of Reinforcement Learning Frameworks for Self-Taught Reasoner
par: Chang, Fu-Chieh, et autres
Publié: (2024)

Why Representation Engineering Works: A Theoretical and Empirical Study in Vision-Language Models
par: Tian, Bowei, et autres
Publié: (2025)

SWAP: Towards Copyright Auditing of Soft Prompts via Sequential Watermarking
par: Yang, Wenyuan, et autres
Publié: (2025)

Principled Understanding of Generalization for Generative Transformer Models in Arithmetic Reasoning Tasks
par: Xu, Xingcheng, et autres
Publié: (2024)