In-Cell Learning: Language Models That Update Their Own Weights in Sequence Without Changing the File They Ship
cs.LG
Submitted: 2026-08-21
Updated: 2026-08-31
Code: https://github.com/sumsliu/cellfill
Terminology
Sources
- LoRA: Low-Rank Adaptation of Large Language Models
- DoRA: Weight-Decomposed Low-Rank Adaptation
- AdaLoRA: Adaptive Budget Allocation for Parameter-Efficient Fine-Tuning
- QLoRA: Efficient Finetuning of Quantized LLMs
- LoftQ: LoRA-Fine-Tuning-Aware Quantization for Large Language Models
- QA-LoRA: Quantization-Aware Low-Rank Adaptation of Large Language Models
- Low-Rank Quantization-Aware Training for LLMs
- IntLoRA: Integral Low-rank Adaptation of Quantized Diffusion Models
- LoTA-QAF: Lossless Ternary Adaptation for Quantization-Aware Fine-Tuning
- Up or Down? Adaptive Rounding for Post-Training Quantization
- BRECQ: Pushing the Limit of Post-Training Quantization by Block Reconstruction
- Matryoshka Quantization
- Any-Precision LLM: Low-Cost Deployment of Multiple, Different-Sized LLMs
- NestQuant: Nested Lattice Quantization for Matrix Products and LLMs
- MatGPTQ: Accurate and Efficient Post-Training Matryoshka Quantization
- Recurrent Residual Quantization: A Progressive Multi-Precision Representation for LLMs
- ReQuant: Fixed-Grid Discrete Refinement for Post-Training Quantization
- BitDelta: Your Fine-Tune May Only Be Worth One Bit
- S-LoRA: Serving Thousands of Concurrent LoRA Adapters
- PackNet: Adding Multiple Tasks to a Single Network by Iterative Pruning
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: Local-Consistency Optimisation for Bayesian Neural Networks
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks