TOPS formulates visual token pruning as constructing Token Optimal Preservation Sets using three information-theoretic principles and demonstrates superior performance on MLLM benchmarks.
arXiv preprint arXiv:2602.17196 (2026)
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3verdicts
UNVERDICTED 3representative citing papers
CLSE prunes tokens in MLLMs by quantifying cross-layer spectral redistribution in the frequency domain to preserve semantically active tokens and reduce compute.
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.
citing papers explorer
-
TOPS: First-Principles Visual Token Pruning via Constructing Token Optimal Preservation Sets for Efficient MLLM Inference
TOPS formulates visual token pruning as constructing Token Optimal Preservation Sets using three information-theoretic principles and demonstrates superior performance on MLLM benchmarks.
-
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.