arXiv (All)
open access
On the Nature of Attention Sink that Shapes Decoding Strategy in Omni-LLMs
The goal of this paper is to strengthen the reasoning of Omnimodal Large Language Models (Omni-LLMs) at inference time, without additional training. These models jointly process video, audio, and text, and given the large number of tokens they consume, how attention is routed across them is central
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
- Libra: Taming Attention Workload Skew in Long-Context LLM Training with Bounded Sequence Pool#1014774
- Tail-Replay: Escaping the Curse of Linear Attention in Prefix Caching for Hybrid LLMs#799522
- Tail-Replay: Escaping the Curse of Linear Attention in Prefix Caching for Hybrid LLMs#798099
- HumorGen: Cognitive Synergy for Humor Generation in Large Language Models via Persona-Based Distillation#1083071
- Reproducing LightMem: When Does Memory Construction Help Over Raw-Turn Retrieval?#1389367
Record · ID 1389224
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