TASKMIXPGM, a framework for learning continuous task mixtures through energy-based modelling over SFT tasks, is introduced and the induced set function defined over the set of such tasks is weakly submodular under budget constraints, enabling approximation guarantees for discrete task selection.
Prateek Chanda, Saral Sureka, Krishnateja Killamsetty et al.· 0 citations
Open-vocabulary segmentation enables rich semantic perception for UAVs, but frame-wise predictions can remain temporally inconsistent across repeated observations and changing viewpoints. We present PerSeM, a training-free persistent semantic memory framework for long-horizon open-vocabulary UAV mapping. PerSeM associa...
This work introduces TaskPGM, a framework for learning continuous task mixtures via an energy-based model over tasks, and shows that the resulting set function is weakly submodular under budget constraints, enabling approximation guarantees for discrete selection variants.
Prateek Chanda, Saral Sureka, Parthiv Chatterjee et al.· 1 citation
MASCOT (Model-Aware Submodular Coverage for Composite-Attribute Text-to-Image Retrieval) formulates multi-attribute diversity as a resource allocation problem, projecting attributes into a soft-binning space weighted by query-driven importance.
Aaryan Sharma, C. VishakPrasad, Virendra Singh et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.