pith. sign in

arxiv: 2504.00557 · v1 · pith:ZWGVMJJ2new · submitted 2025-04-01 · 💻 cs.CV · cs.LG

Efficient LLaMA-3.2-Vision by Trimming Cross-attended Visual Features

classification 💻 cs.CV cs.LG
keywords featuresvisualtokenscachecross-attentionimageinferencelayers
0
0 comments X
read the original abstract

Visual token reduction lowers inference costs caused by extensive image features in large vision-language models (LVLMs). Unlike relevant studies that prune tokens in self-attention-only LVLMs, our work uniquely addresses cross-attention-based models, which achieve superior performance. We identify that the key-value (KV) cache size for image tokens in cross-attention layers significantly exceeds that of text tokens in self-attention layers, posing a major compute bottleneck. To mitigate this issue, we exploit the sparse nature in cross-attention maps to selectively prune redundant visual features. Our Trimmed Llama effectively reduces KV cache demands without requiring additional training. By benefiting from 50%-reduced visual features, our model can reduce inference latency and memory usage while achieving benchmark parity.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 3 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. ProjLens: Unveiling the Role of Projectors in Multimodal Model Safety

    cs.CR 2026-04 unverdicted novelty 7.0

    ProjLens shows that backdoor parameters in MLLMs are encoded in low-rank subspaces of the projector and that embeddings shift toward the target direction with magnitude linear in input norm, activating only on poisone...

  2. HotComment: A Benchmark for Evaluating Popularity of Online Comments

    cs.AI 2026-04 unverdicted novelty 6.0

    HotComment is a new multimodal benchmark that quantifies online comment popularity via content quality assessment, interaction-based prediction, and agent-simulated user engagement, accompanied by the StyleCmt stylist...

  3. C-CoT: Counterfactual Chain-of-Thought with Vision-Language Models for Safe Autonomous Driving

    cs.CV 2026-05 unverdicted novelty 5.0

    C-CoT applies VLMs to autonomous driving via five-stage reasoning with a meta-action tree for counterfactuals, yielding 81.9% risk recall, 3.52% collision rate, and 1.98 m L2 error on a new dataset.