Search papers, labs, and topics across Lattice.
This paper introduces EAGLE-360, an innovative framework for active visual search in 360掳 environments that addresses the limitations of Multimodal Large Language Models (MLLMs) in modeling panoramic properties. By leveraging global priors and adapting a coordinate-shifting positional encoding mechanism, EAGLE-360 enables more efficient exploration and robust error recovery compared to traditional methods that rely on fragmented local viewpoints. The results show that EAGLE-360 achieves nearly an 8-fold increase in detection accuracy over baseline models, setting a new state-of-the-art in 360掳 visual search tasks.
EAGLE-360 redefines visual search in panoramic environments, achieving an unprecedented 8-fold increase in accuracy by integrating global context with local exploration.
While Multimodal Large Language Models (MLLMs) have demonstrated exceptional capabilities in standard visual understanding, adapting them for active visual search in 360$^\circ$ panoramic environments exposes fundamental limitations. Specifically, standard MLLMs struggle to effectively model inherent panoramic properties, such as severe polar distortion and continuous cylindrical topologies, which significantly degrades target detection accuracy. Consequently, existing panoramic search methods attempt to compensate by relying heavily on fragmented local viewpoints. Burdened by rigid initialization and a lack of global panoramic priors, these approaches suffer from myopic, inefficient exploration and struggle with robust error recovery when targets are out of view. To overcome these challenges, we propose EAGLE-360, a novel Embodied Active Global-to-Local Exploration framework. Rather than performing exhaustive local searches, EAGLE-360 leverages global priors to establish an initial holistic perspective, iteratively reasoning and progressively narrowing the search space. Architecturally, we adapt RoPE Rolling, a coordinate-shifting positional encoding mechanism, to seamlessly model the continuous topologies of panoramas. To facilitate this paradigm, we construct the large-scale EAGLE-360 dataset, comprising 14,000+ 4K panoramas and 70,000+ rounds of high-quality VQA dialogues. By employing a training pipeline that integrates Supervised Fine-Tuning (SFT) with Group Relative Policy Optimization (GRPO), we effectively elicit complex spatial reasoning and tool-calling capabilities. Extensive experiments demonstrate that EAGLE-360 establishes a new state-of-the-art for 360$^\circ$ visual search, achieving nearly an 8-fold increase in accuracy over the base model while significantly enhancing exploration efficiency.
