Beyond Compressing Everything: Contrastive Memory Learning for Selective Context Compression
cs.CL, cs.AI
Submitted: 2026-11-12
Updated: 2026-11-12
Code: https://github.com/scar-on/CoMem
Terminology
Sources
- No Mean Feat: Simple, Strong Baselines for Context Compression
- CLaRa: Bridging Retrieval and Generation with Continuous Latent Reasoning
- NV-Embed: Improved Techniques for Training LLMs as Generalist Embedding Models
- Long-context LLMs Struggle with Long In-context Learning
- Label Supervised LLaMA Finetuning
- REFRAG: Rethinking RAG based Decoding
- Read As Human: Compressing Context via Parallelizable Close Reading and Skimming
- DeepSeek-OCR 2: Visual Causal Flow
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