VideoSearch-R1: Iterative Video Retrieval and Reasoning via Soft Query Refinement
VideoSearch-R1 is an agentic framework that iteratively retrieves videos and refines search queries using continuous latent space refinement and policy optimization for improved vi…
Hugging Face · Daily Papers
·Seohyun Lee, Seoung Choi
·
·▲ 11 upvotes
Este artigo está em destaque na seleção diária de papers do Hugging Face, curada pela comunidade de pesquisa em IA.
Autores: Seohyun Lee, Seoung Choi, Dohwan Ko, Jongha Kim, Hyunwoo J. Kim
- 11 upvotes da comunidade
- Temas: video retrieval, intra-video reasoning, inter-video reasoning, temporal grounding, agentic framework, Soft Query Refinement
Resumo
Resumo original (em inglês), extraído do paper:
VideoSearch-R1 is an agentic framework that iteratively retrieves videos and refines search queries using continuous latent space refinement and policy optimization for improved video moment retrieval and temporal grounding.Onde ler
// relacionados
Leia também
Editorial
Claude Sonnet 5: a Anthropic aposta que o modelo do meio faz o trabalho do topo
Blog
Google’s AI buildout drove 37% increase in electricity use in 2025
Blog
OpenAI reportedly offers the Trump administration a five percent stake in the company
Blog