ACCT: Asymmetric Cross-LLM Context Transfer
cs.AI
Submitted: 2026-10-30
Updated: 2026-10-30
Code: https://github.com/meta-llama/llama-models
Terminology
Sources
- Layer Normalization
- PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling
- SearchQA: A New Q&A Dataset Augmented with Context from a Search Engine
- Cache-to-Cache: Direct Semantic Communication Between Large Language Models
- Prompt Cache: Modular Attention Reuse for Low-Latency Inference
- The Llama 3 Herd of Models
- Gaussian Error Linear Units (GELUs)
- Measuring Massive Multitask Language Understanding
- Distilling the Knowledge in a Neural Network
- Perceiver IO: A General Architecture for Structured Inputs & Outputs
- SnapKV: LLM Knows What You are Looking for Before Generation
- DroidSpeak: KV Cache Sharing for Cross-LLM Communication and Multi-LLM Serving
- Pointer Sentinel Mixture Models
- MemGPT: Towards LLMs as Operating Systems
- PyTorch: An Imperative Style, High-Performance Deep Learning Library
- WinoGrande: An Adversarial Winograd Schema Challenge at Scale
- GLU Variants Improve Transformer
- Attention Is All You Need
- Qwen2.5 Technical Report
- Qwen3 Technical Report
Related papers
- Multi-Objective Structured Pruning of LLMs for Latency and Model Size Optimization
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Embeddings for Preferences, Not Semantics
- Can We Trust Item Response Theory for AI Evaluation?
- Diagnosing Task Insensitivity in Language Agents