CONDUIT: A Unified Residual-Stream Restoration Framework for KV Cache Reuse in Vision-Language Models

arXiv:2609.05821 · cs.CL, cs.CV · Submitted 2026-09-05 · Read on arXiv

cs.CL, cs.CV

Submitted: 2026-09-05

Updated: 2026-09-05

Comments: Accepted to Findings of the 2026 Conference on Empirical Methods in Natural Language Processing (EMNLP 2026)

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Failure Modes — 1× in this paper · explained in 3 episodes
• KV cache — 1× in this paper · explained in 3 episodes
• KV cache reuse — 1× in this paper · explained in 2 episodes
• Vision-Language Models (VLMs) — 1× in this paper · explained in 6 episodes

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering