ESearch-R1: Learning Cost-Aware MLLM Agents for Interactive Embodied Search via Reinforcement Learning

Documenti analoghi

• Listening with the Eyes: Benchmarking Egocentric Co-Speech Grounding across Space and Time
  di: Zhou, Weijie, et al.
  Pubblicazione: (2026)
• LightPlanner: Unleashing the Reasoning Capabilities of Lightweight Large Language Models in Task Planning
  di: Zhou, Weijie, et al.
  Pubblicazione: (2025)
• MLLM as Retriever: Interactively Learning Multimodal Retrieval for Embodied Agents
  di: Yue, Junpeng, et al.
  Pubblicazione: (2024)
• PhysVLM-AVR: Active Visual Reasoning for Multimodal Large Language Models in Physical Environments
  di: Zhou, Weijie, et al.
  Pubblicazione: (2025)
• PhysVLM: Enabling Visual Language Models to Understand Robotic Physical Reachability
  di: Zhou, Weijie, et al.
  Pubblicazione: (2025)