arXiv (All)
open access
Look Back, Think Ahead: Visual Memory on Demand for Efficient Multimodal Reasoning
Processing long visual token sequences from high-resolution images makes multi-step reasoning computationally expensive for multimodal Large Language Models (MLLMs). Existing one-shot pruning and aggregation methods compress visual tokens into a fixed context before decoding. However, visual evidenc
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
- TOPS: First-Principles Visual Token Pruning via Constructing Token Optimal Preservation Sets for Efficient MLLM Inference#1063955
- An AI4AI Framework for Visual Token Pruning#974522
- Multi-Image Visual Token Pruning in Large Visual Language Models#820643
- EM^2Mem: Event-Centric Multimodal Memory for Large Language Models#819990
Record · ID 1249484
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