CoRDS selects a compact KV-cache subset via joint-space coreset coverage and log-det diversity to outperform token-wise heuristics on long-video VLM benchmarks.
Token merging: Your ViT but faster
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 1
method 1
citation-polarity summary
fields
cs.CV 3years
2026 3verdicts
UNVERDICTED 3representative citing papers
PaceVGGT reduces VGGT inference latency by up to 5.1x on ScanNet-50 via pre-AA token pruning with a distilled Token Scorer, per-frame keep budgets, adaptive merge/prune, and feature-guided restoration, while preserving reconstruction quality on ScanNet-50 and 7-Scenes.
SAVEMem improves streaming video understanding scores by adding semantic awareness to memory compression and query-adaptive retrieval without any model training.
citing papers explorer
-
CoRDS: Coreset-based Representative and Diverse Selection for Streaming Video Understanding
CoRDS selects a compact KV-cache subset via joint-space coreset coverage and log-det diversity to outperform token-wise heuristics on long-video VLM benchmarks.
-
PaceVGGT: Pre-Alternating-Attention Token Pruning for Visual Geometry Transformers
PaceVGGT reduces VGGT inference latency by up to 5.1x on ScanNet-50 via pre-AA token pruning with a distilled Token Scorer, per-frame keep budgets, adaptive merge/prune, and feature-guided restoration, while preserving reconstruction quality on ScanNet-50 and 7-Scenes.
-
Semantic-Aware Adaptive Visual Memory for Streaming Video Understanding
SAVEMem improves streaming video understanding scores by adding semantic awareness to memory compression and query-adaptive retrieval without any model training.