arXiv:2003.09971
공식 코드 · Papers with Code
A Better Variant of Self-Critical Sequence Training
원문 초록
In this work, we present a simple yet better variant of Self-Critical Sequence Training. We make a simple change in the choice of baseline function in REINFORCE algorithm. The new baseline can bring better performance with no extra cost, compared to the greedy decoding baseline.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Vision Matters: Simple Visual Perturbations Can Boost Multimodal Math Reasoning
ViCrit: A Verifiable Reinforcement Learning Proxy Task for Visual Perception in VLMs
Dense Retrievers Can Fail on Simple Queries: Revealing The Granularity Dilemma of Embeddings
DiscoVLA: Discrepancy Reduction in Vision, Language, and Alignment for Parameter-Efficient Video-Text Retrieval
Stepwise Decomposition and Dual-stream Focus: A Novel Approach for Training-free Camouflaged Object Segmentation
Document-Level Text Generation with Minimum Bayes Risk Decoding using Optimal Transport
토론
이 논문과 연결된 포럼 글이 아직 없습니다.