Introduces Efficient Operator Search, a differentiable framework that jointly optimizes token reduction locations, retention budgets, and operator behaviors in multimodal models under cost constraints, recovering manual baselines and finding hybrid operators with competitive efficiency.
Cross-self kv cache pruning for efficient vision- language inference
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 3verdicts
UNVERDICTED 3roles
background 1polarities
background 1representative citing papers
KVCapsule compresses KV cache in VLMs by 60% to deliver up to 2x higher tokens-per-second and 2.4x memory reduction with negligible accuracy loss.
AttenA+ reweights action training objectives in VLA and WAM models via inverse velocity attention to prioritize kinematically critical segments, yielding small benchmark gains.
citing papers explorer
-
Differentiable Efficient Operator Search
Introduces Efficient Operator Search, a differentiable framework that jointly optimizes token reduction locations, retention budgets, and operator behaviors in multimodal models under cost constraints, recovering manual baselines and finding hybrid operators with competitive efficiency.
-
KVCapsule: Efficient Sequential KV Cache Compression for Vision-Language Models with Asymmetric Redundancy
KVCapsule compresses KV cache in VLMs by 60% to deliver up to 2x higher tokens-per-second and 2.4x memory reduction with negligible accuracy loss.
-
AttenA+: Rectifying Action Inequality in Robotic Foundation Models
AttenA+ reweights action training objectives in VLA and WAM models via inverse velocity attention to prioritize kinematically critical segments, yielding small benchmark gains.