arXiv (OAI Expanded)
open access
Pixel Decodability Is Not a Compression Signal: Causally Evaluating Importance Proxies for Visual KV-Cache Eviction
Vision-language models retain a substantial amount of pixel-decodable visual content in their visual key-value cache. We show, in our setting, that this retention is task-inert: across our preregistered tests, how much a unit retains never positively tracks whether the computation that answers the q
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
- Fixation duration on natural scenes is explained by memory encoding not processing demand#273363
- Learning Dynamic Evidence Routes for Vision Transformer Probing#1061709
- Part Grounding, Not Action Knowledge: Locating the Bottleneck in VLM Affordance Prediction#1071032
- CT-OPD: Counterfactual Trace On-Policy Distillation for Diffusion Vision-Language Models#1117112
- Fast-BEV++: Fast by Algorithm, Deployable by Design#925872
Record · ID 1070520
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