arXiv (All)
open access
Just MLPs: Efficient Visual State Reconstruction for Multimodal Language Models
Long visual token sequences often account for a substantial fraction of the computational overhead in multimodal large language models~(MLLMs). Existing approaches reduce this cost by pruning redundant visual tokens, but permanently discard visual evidence that may become useful in subsequent layers
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
- Rethinking Visual Token Compression for Video Large Language Models: A Simple Yet Strong Baseline#1129983
- Reducing Hallucination in Multimodal Large Language Models through Hard Grounding Preference Supervision#1116282
- CausalEmbed: Auto-Regressive Multi-Vector Generation in Latent Space for Visual Document Embedding#1061671
- Beyond Tokens: A Survey on Decoding Methods for Large Language and Vision-Language Models#609221
- State-Conditioned Visual Evidence Retrieval for Fine-Grained Perception in Document Vision-Language Models#792946
Record · ID 1129577
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