Visual token pruning in MLLMs fails on complex reasoning due to Relevant Visual Information Shift during decoding, but the DSTP framework fixes it training-free across models.
Visiontrim: Unified vision token compression for training-free mllm acceleration
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
years
2026 4verdicts
UNVERDICTED 4roles
background 2polarities
background 2representative citing papers
DualComp uses a lightweight router to split visual token compression into a semantic stream with size-adaptive clustering and a geometric stream with path-tracing recovery, enabling low-cost high-fidelity UHR remote sensing interpretation.
CIVIC is a path-consistent compact visual inference framework that reduces KV-cache memory to approximately one-third and end-to-end latency in VLMs while preserving accuracy via text-aligned KL distillation and adaptive spatial retention.
DepthVLM converts a standard VLM into a dense metric depth predictor by attaching a lightweight head and training under unified vision-text supervision, outperforming prior VLMs and some pure vision models on a new indoor-outdoor benchmark.
citing papers explorer
-
Why and When Visual Token Pruning Fails? A Study on Relevant Visual Information Shift in MLLMs Decoding
Visual token pruning in MLLMs fails on complex reasoning due to Relevant Visual Information Shift during decoding, but the DSTP framework fixes it training-free across models.
-
Semantic-Geometric Dual Compression: Training-Free Visual Token Reduction for Ultra-High-Resolution Remote Sensing Understanding
DualComp uses a lightweight router to split visual token compression into a semantic stream with size-adaptive clustering and a geometric stream with path-tracing recovery, enabling low-cost high-fidelity UHR remote sensing interpretation.
-
CIVIC: End-to-End Sequence Compactness for Efficient Vision-Language Models
CIVIC is a path-consistent compact visual inference framework that reduces KV-cache memory to approximately one-third and end-to-end latency in VLMs while preserving accuracy via text-aligned KL distillation and adaptive spatial retention.
-
Unlocking Dense Metric Depth Estimation in VLMs
DepthVLM converts a standard VLM into a dense metric depth predictor by attaching a lightweight head and training under unified vision-text supervision, outperforming prior VLMs and some pure vision models on a new indoor-outdoor benchmark.