FrameVGGT replaces token-level KV retention with frame-level segments and prototypes to bound memory while preserving geometric coherence in streaming VGGT.
Scissorhands: Exploiting the persistence of importance hypothesis for llm kv cache compression at test time.Advances in Neural Information Processing Systems, 36:52342–52364, 2023
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
FrameVGGT: Geometry-Aligned Frame-Level Memory for Bounded Streaming VGGT
FrameVGGT replaces token-level KV retention with frame-level segments and prototypes to bound memory while preserving geometric coherence in streaming VGGT.