3 papers
cs.CV2026
Linguistic Trajectory Encoding for Efficient Long-Horizon Spatial Memory in Embodied Agents
Tianyidan Xie, Shenyi Wang, Qiang Tang +7
Embodied agents performing long-horizon tasks require a memory representation in which the state transitions of dynamic objects remain queryable in natural language across hours-to…
cs.CV2026
EgoMonth: A Month-Level Egocentric Video Benchmark for Long-Term Spatiotemporal Memory
Weitao Chen, Hu Jiaxin, Xie Tianyidan +15
Recent advances in Multimodal Large Language Models (MLLMs) have led to substantial progress in video understanding, accompanied by a growing number of long video benchmarks. Howev…
cs.CV2026
SLARM: Streaming and Language-Aligned Reconstruction Model for Dynamic Scenes
Zhicheng Qiu, Jiarui Meng, Tong-an Luo +4
We propose SLARM, a feed-forward model that unifies dynamic scene reconstruction, semantic understanding, and real-time streaming inference. SLARM captures complex, non-uniform mot…