4 papers · 1 filter
FOLIO: Focused Semantic Memory for Streaming Video Understanding
Haoyang Fan, Dhruv Parikh, Anvitha Ramachandran +4
In online streaming video understanding, a video stream continues to arrive and queries may be issued at any time. Because streaming frames grow without bound, the system must cont…
Vision Non-Causal Trapezoidal Mamba: Eliminating Directional Scanning in Vision SSMs with Second-Order Dynamics
Anvitha Ramachandran, Dhruv Parikh, Haoyang Fan +2
State Space Models (SSMs) have emerged as an alternative to Vision Transformers, yet most vision SSMs inherit directional token scanning from causal sequence modeling. While effect…
Can Graphs Help Vision SSMs See Better?
Dhruv Parikh, Anvitha Ramachandran, Haoyang Fan +3
Vision state space models inherit the efficiency and long-range modeling ability of Mamba-style selective scans. However, their performance depends critically on the representation…
ConsensusDrop: Fusing Visual and Cross-Modal Saliency for Efficient Vision Language Models
Dhruv Parikh, Haoyang Fan, Rajgopal Kannan +1
Vision-Language Models (VLMs) are expensive because the LLM processes hundreds of largely redundant visual tokens. Existing token reduction methods typically exploit \textit{either…