Cortex: Consolidating Context into Parametric Memory
cs.CL, cs.AI, cs.CV, cs.LG, cs.MA
Submitted: 2026-10-14
Updated: 2026-10-14
Comments: Technical report
Code: https://github.com/zjunlp/cortex
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Sources
- SIEVE: Sample-Efficient Parametric Learning from Natural Language
- A General Language Assistant as a Laboratory for Alignment
- $\tau^2$-Bench: Evaluating Conversational Agents in a Dual-Control Environment
- Doc-to-LoRA: Learning to Instantly Internalize Contexts
- Evaluating Large Language Models Trained on Code
- Training Verifiers to Solve Math Word Problems
- Beyond Benchmarks: MathArena as an Evaluation Platform for Mathematics with LLMs
- Learning without training: The implicit dynamics of in-context learning
- Memp: Exploring Agent Procedural Memory
- Thinking to Recall: How Reasoning Unlocks Parametric Knowledge in LLMs
- Gemma 3 Technical Report
- Equivalence of Context and Parameter Updates in Modern Transformer Blocks
- Measuring Mathematical Problem Solving With the MATH Dataset
- Transformer-Patcher: One Mistake worth One Neuron
- delta-mem: Efficient Online Memory for Large Language Models
- Let's Verify Step by Step
- SHINE: A Scalable In-Context Hypernetwork for Mapping Context to LoRA in a Single Pass
- Locas: Your Models are Principled Initializers of Locally-Supported Parametric Memories
- Transmuting prompts into weights
- gpt-oss-120b & gpt-oss-20b Model Card
Related papers
- Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
- Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
- Subliminal Steering: Stronger Encoding of Hidden Signals
- MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
- The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
- Untangling the Mechanisms of Misleading Context in Medical Question Answering