arXiv (All)
open access
Shallow to Deep: Aligning Token Pruning with Stage-wise Roles in LVLMs
Large Vision-Language Models (LVLMs) incur high computational costs from redundant visual tokens. Although training-free attention-based multi-layer pruning in the vision encoder stage has been explored as an effective strategy, we find that pruning in shallow layers consistently degrades performanc
Conceptio Open Archive
Analyze & explore related research in Conceptio
Connect this record directly into your research workflow or AI agent. Explore citations across open repositories, query full text, and export structured proof bundles.
This document is indexed with metadata only: full text is not available in the archive for this record. Open the official source ↗
Related documents
- SinkPruner: Sink-Free Visual Token Pruning for Multimodal Large Language Models#820996
- Centering before Pruning: Lightweight Geometry Correction for Diversity-Based Visual Token Pruning in LVLMs#799479
- Centering before Pruning: Lightweight Geometry Correction for Diversity-Based Visual Token Pruning in LVLMs#798056
- Multi-Image Visual Token Pruning in Large Visual Language Models#820643
- Layer-Aware Position Embeddings for Visual Token Pruning in Multimodal Large Language Models#1049451
Record · ID 1061272
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Bring this data into your agent: Connect via MCP or API · 20 free credits to start · no card required
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive