SP-CoR is a multimodal LLM framework using dynamics-aware sampling, spectral-physics view fusion, and prompt distillation that outperforms baselines on the new CoopSR benchmark and EgoTeam dataset for multi-robot cooperative spatial reasoning.
Video-RAG: Visually-aligned retrieval-augmented long video comprehension
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2years
2026 2representative citing papers
EgoExoMem introduces the first cross-view ego–exo video memory benchmark (2.6K MCQs, eight QA types) and E²-Select, a training-free dual-view frame selector scoring 58.2%.
citing papers explorer
-
Seeing Together: Multi-Robot Cooperative Egocentric Spatial Reasoning with Multimodal Large Language Models
SP-CoR is a multimodal LLM framework using dynamics-aware sampling, spectral-physics view fusion, and prompt distillation that outperforms baselines on the new CoopSR benchmark and EgoTeam dataset for multi-robot cooperative spatial reasoning.
-
EgoExoMem: Cross-View Memory Reasoning over Synchronized Egocentric and Exocentric Videos
EgoExoMem introduces the first cross-view ego–exo video memory benchmark (2.6K MCQs, eight QA types) and E²-Select, a training-free dual-view frame selector scoring 58.2%.