CLSE prunes tokens in MLLMs by quantifying cross-layer spectral redistribution in the frequency domain to preserve semantically active tokens and reduce compute.
Re- thinking token reduction in mllms: Towards a unified paradigm for training-free acceleration
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 4verdicts
UNVERDICTED 4roles
background 1polarities
background 1representative citing papers
PriorTR estimates model-induced prior attention via a null token in one forward pass and contrasts it with task-conditioned attention to improve visual token pruning accuracy-efficiency trade-offs in MLLMs.
Efficient3D prunes visual tokens in 3D MLLMs via DVTIE and ATR modules, reporting better performance than unpruned baselines on Scan2Cap and other benchmarks.
TwigVLM adds a twig module to VLMs for twig-guided token pruning and self-speculative decoding, retaining 96% performance after pruning 88.9% visual tokens and delivering 154% speedup on long responses for LLaVA-1.5-7B.
citing papers explorer
-
Spectral Evolution-Guided Token Pruning in Multimodal Large Language Models
CLSE prunes tokens in MLLMs by quantifying cross-layer spectral redistribution in the frequency domain to preserve semantically active tokens and reduce compute.
-
Accelerating Multimodal Large Language Models with Prior-Corrected Token Reduction
PriorTR estimates model-induced prior attention via a null token in one forward pass and contrasts it with task-conditioned attention to improve visual token pruning accuracy-efficiency trade-offs in MLLMs.
-
Efficient3D: A Unified Framework for Adaptive and Debiased Token Reduction in 3D MLLMs
Efficient3D prunes visual tokens in 3D MLLMs via DVTIE and ATR modules, reporting better performance than unpruned baselines on Scan2Cap and other benchmarks.
-
Growing a Multi-head Twig via Distillation and Reinforcement Learning to Accelerate Large Vision-Language Models
TwigVLM adds a twig module to VLMs for twig-guided token pruning and self-speculative decoding, retaining 96% performance after pruning 88.9% visual tokens and delivering 154% speedup on long responses for LLaVA-1.5-7B.