XMerge: Cross-Axis Selection and Reconstructive Layer Merging for LLM Depth Compression
cs.LG, cs.CL
Submitted: 2026-09-02
Updated: 2026-09-02
Code: https://github.com/karpathy/nanochat
Terminology
Sources
- The Llama 3 Herd of Models
- Distilling the Knowledge in a Neural Network
- The Structure of Quantization Damage in LLMs: Why the Next Bit Should Be Spent Globally
- Qwen2.5 Technical Report
- Qwen3 Technical Report
- A Free Lunch in LLM Compression: Revisiting Retraining after Pruning
- Layer as Puzzle Pieces: Compressing Large Language Models through Layer Concatenation
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