Thinking Outside the Box: Retention and Transmission of Information in Sliding-Window KV Inference
cs.AI
Submitted: 2026-09-28
Updated: 2026-09-28
Code: https://github.com/jefferythewind/Thinking-Outside-the-Box
Terminology
Sources
- Refusal in Language Models Is Mediated by a Single Direction
- Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context
- The Llama 3 Herd of Models
- Language models recognize dropout and Gaussian noise applied to their activations
- Mamba: Linear-Time Sequence Modeling with Selective State Spaces
- Mistral 7B
- Locating and Editing Factual Associations in GPT
- Nemotron-H: A Family of Accurate and Efficient Hybrid Mamba-Transformer Models
- Compressive Transformers for Long-Range Sequence Modelling
- Qwen2.5 Technical Report
- Efficient Streaming Language Models with Attention Sinks
- H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models
Related papers
- 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
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems
- VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection