A new pathway to generative artificial intelligence by minimizing the maximum entropy
원문 초록
Generative artificial intelligence revolutionized society. Current models are trained by minimizing the distance between the produced data and the training set. Consequently, development is plateauing as they are intrinsically data-hungry and challenging to direct during the generative process. To overcome these limitations, we introduce a paradigm shift through a framework where we do not fit the training set but find the most informative yet least noisy representation of the data simultaneously minimizing the entropy to reduce noise and maximizing it to remain unbiased via adversary training. The result is a general physics-driven model, which is data-efficient and flexible, permitting to control and influence the generative process. Benchmarking shows that our approach outperforms variational autoencoders. We demonstrate the methods effectiveness in generating images, even with limited training data, and its unprecedented capability to customize the generation process a posteriori without any fine-tuning or retraining
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Multi-Head Recurrent Memory Agents
MMAO-Dyn: A Metabolic Multi-Agent Optimizer for Dynamic Optimization
단순할수록 좋을 때: 중세 라틴어 필사본을 위한 번역 파이프라인 평가
When Simpler Is Better: Evaluating Translation Pipelines for Medieval Latin Manuscripts
URSA: 실용적 역합성 평가를 위한 화학 인식 벤치마크
URSA: Chemistry-Aware Benchmark for Utilitarian Retrosynthesis Assessment
Forethought: 신경기호 프리미티브 프로그래밍을 통한 검증 가능한 추론
Forethought: Verifiable Reasoning from Neurosymbolic Primitive Programming
GaP: 변동적 자동화 태스크를 위한 그래프-as-정책 멀티 에이전트 자기학습 하네스
GaP: A Graph-as-Policy Multi-Agent Self-Learning Harness For Variational Automation Tasks
토론
이 논문과 연결된 포럼 글이 아직 없습니다.