LearnPruner prunes vision tokens to 5.5% of the original count while retaining about 95% of VLM performance and delivering 3.2 times faster inference by fixing attention sink in encoders and using unbiased middle-layer attention in LLMs.
Stop looking for important tokens in multimodal language models: Duplication matters more
8 Pith papers cite this work. Polarity classification is still indexing.
8
Pith papers citing it
years
2026 8representative citing papers
SPpruner reduces visual tokens in VLMs via focus identification followed by context-aware scanning, retaining 22.2% tokens for 2.53x speedup on Qwen2.5-VL with negligible accuracy loss.
A unified learnable KV eviction policy with cross-layer calibration reduces memory and matches or exceeds full-cache performance on long-context tasks by retaining useful tokens and limiting attention dilution.
ST-Prune is a training-free spatio-temporal token pruning framework for VLMs in autonomous driving that achieves near-lossless results at 90% token reduction by exploiting motion volatility, temporal recency, and multi-view geometry.
HAWK is a training-free method that prunes over 80% of visual tokens in MLLMs while retaining 96% accuracy by using head importance weights and text-guided attention to select task-relevant tokens.
RTPrune introduces a reading-twice inspired two-stage pruning technique for DeepSeek-OCR that retains 84.25% tokens while delivering 99.47% accuracy and 1.23x faster prefill on OmniDocBench.
EvoComp compresses visual tokens in MLLMs by 3x while retaining 99.3% accuracy via an evolutionary labeling strategy that searches for low-loss, semantically diverse token subsets.
AOT reduces visual tokens in VLLMs via intra-frame and inter-frame anchors with local-global optimal transport, delivering competitive benchmark performance and efficiency gains in a training-free way.
citing papers explorer
-
LearnPruner: Rethinking Attention-based Token Pruning in Vision Language Models
LearnPruner prunes vision tokens to 5.5% of the original count while retaining about 95% of VLM performance and delivering 3.2 times faster inference by fixing attention sink in encoders and using unbiased middle-layer attention in LLMs.
-
Focus-then-Context: Subject-Centric Progressive Visual Token Reduction for Vision-Language Models
SPpruner reduces visual tokens in VLMs via focus identification followed by context-aware scanning, retaining 22.2% tokens for 2.53x speedup on Qwen2.5-VL with negligible accuracy loss.
-
Make Each Token Count: Towards Improving Long-Context Performance with KV Cache Eviction
A unified learnable KV eviction policy with cross-layer calibration reduces memory and matches or exceeds full-cache performance on long-context tasks by retaining useful tokens and limiting attention dilution.
-
ST-Prune: Training-Free Spatio-Temporal Token Pruning for Vision-Language Models in Autonomous Driving
ST-Prune is a training-free spatio-temporal token pruning framework for VLMs in autonomous driving that achieves near-lossless results at 90% token reduction by exploiting motion volatility, temporal recency, and multi-view geometry.
-
HAWK: Head Importance-Aware Visual Token Pruning in Multimodal Models
HAWK is a training-free method that prunes over 80% of visual tokens in MLLMs while retaining 96% accuracy by using head importance weights and text-guided attention to select task-relevant tokens.
-
RTPrune: Reading-Twice Inspired Token Pruning for Efficient DeepSeek-OCR Inference
RTPrune introduces a reading-twice inspired two-stage pruning technique for DeepSeek-OCR that retains 84.25% tokens while delivering 99.47% accuracy and 1.23x faster prefill on OmniDocBench.
-
EvoComp: Learning Visual Token Compression for Multimodal Large Language Models via Semantic-Guided Evolutionary Labeling
EvoComp compresses visual tokens in MLLMs by 3x while retaining 99.3% accuracy via an evolutionary labeling strategy that searches for low-loss, semantically diverse token subsets.
-
Token Reduction via Local and Global Contexts Optimization for Efficient Video Large Language Models
AOT reduces visual tokens in VLLMs via intra-frame and inter-frame anchors with local-global optimal transport, delivering competitive benchmark performance and efficiency gains in a training-free way.