Embedding Consistency Regulation for Persistent Semantic Routing in Compact Language Models
cs.CL, cs.AI
Submitted: 2026-01-02
Updated: 2026-10-31
Terminology
Sources
- Empowering Edge Intelligence: A Comprehensive Survey on On-Device AI Models
- MobileLLM: Optimizing Sub-billion Parameter Language Models for On-Device Use Cases
- LLM in a flash: Efficient Large Language Model Inference with Limited Memory
- Distilling the Knowledge in a Neural Network
- Feature Alignment and Representation Transfer in Knowledge Distillation for Large Language Models
- Multi-Sense Embeddings for Language Models and Knowledge Distillation
- Representation Learning with Contrastive Predictive Coding
- MiniLM: Deep Self-Attention Distillation for Task-Agnostic Compression of Pre-Trained Transformers
- Multiplicity of solutions for a class of quasilinear problems involving the $1$-Laplacian operator with critical growth
- Improving language models by retrieving from trillions of tokens
- Prefix-Tuning: Optimizing Continuous Prompts for Generation
Related papers
- ALARM: Audio-Language Alignment for Reasoning Models
- ThinkSum: Probabilistic reasoning over sets using large language models
- Coherence boosting: When your pretrained language model is not paying enough attention
- From Facts to Insights: A Persona-Driven Dual Memory Framework and Dataset for Role-Playing Agents
- Improving General Role-Playing Agents via Psychology-Grounded Reasoning and Role-Aware Policy Optimization
- The Art of Asking: Multilingual Prompt Optimization for Synthetic Data