CoFL-S: Spatially Queryable Sector Flow Fields for Local Language-Conditioned Navigation
Vision-Language Navigation has increasingly emphasized high-level instruction reasoning, memory, global map construction, and instruction decomposition, while the low-level action representation remains comparatively underexplored. We propose CoFL-S, a low-level vision-language-action framework that predicts a language-conditioned flow field over the robot's local visible sector and generates continuous trajectories by rolling out the predicted field. To train this low-level representation, we convert each VLN-CE episode, originally a whole-episode instruction paired with an action sequence, i
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- PossiblePossibly related (embedding) · 55%vlm-starter →
- PossiblePossibly related (embedding) · 51%VioletVision-3B →
- PossiblePossibly related (embedding) · 49%sou350121/VLA-Handbook →
- LinkedLinked via arxiv author · 85%Haokun Liu →
“CoFL-S: Spatially Queryable Sector Flow Fields for Local Language-Conditioned Navigation”
- LinkedLinked via arxiv author · 85%Zhaoqi Ma →
“CoFL-S: Spatially Queryable Sector Flow Fields for Local Language-Conditioned Navigation”
- LinkedLinked via arxiv author · 85%Yicheng Chen →
“CoFL-S: Spatially Queryable Sector Flow Fields for Local Language-Conditioned Navigation”
- LinkedLinked via arxiv author · 85%Wentao Zhang →
“CoFL-S: Spatially Queryable Sector Flow Fields for Local Language-Conditioned Navigation”
- LinkedLinked via arxiv author · 85%Masaki Kitagawa →
“CoFL-S: Spatially Queryable Sector Flow Fields for Local Language-Conditioned Navigation”