EchoPrune prunes video tokens via query relevance and temporal reconstruction error to let VideoLLMs handle up to 20x more frames under fixed budget with reported gains in accuracy and speed.
Efficient streaming language models with attention sinks
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 2verdicts
UNVERDICTED 2roles
background 1polarities
background 1representative citing papers
A semantics-aware KV cache hierarchy offloads tokens to slower memory with zero approximation error, demonstrating that LLM reasoning accuracy depends only on the permanent eviction ratio and not on HBM residency.
citing papers explorer
-
EchoPrune: Interpreting Redundancy as Temporal Echoes for Efficient VideoLLMs
EchoPrune prunes video tokens via query relevance and temporal reconstruction error to let VideoLLMs handle up to 20x more frames under fixed budget with reported gains in accuracy and speed.
-
Not All Thoughts Need HBM: Semantics-Aware Memory Hierarchy for LLM Reasoning
A semantics-aware KV cache hierarchy offloads tokens to slower memory with zero approximation error, demonstrating that LLM reasoning accuracy depends only on the permanent eviction ratio and not on HBM residency.