From Transfer Probes to Expert Grouping: Evidence from LoRA Post-Training
cs.LG
Submitted: 2026-10-10
Updated: 2026-10-10
Code: https://github.com/CodePothunter/Reproduction-for-From-Transfer-Probes-to-Expert-Grouping
Sources
- OpenCodeInstruct: A Large-scale Instruction Tuning Dataset for Code LLMs
- Scaling Expert Language Models with Unsupervised Domain Discovery
- DeepMath-103K: A Large-Scale, Challenging, Decontaminated, and Verifiable Mathematical Dataset for Advancing Reasoning
- Branch-Train-Merge: Embarrassingly Parallel Training of Expert Language Models
- Branch-Train-MiX: Mixing Expert LLMs into a Mixture-of-Experts LLM
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: The Predictive Cost of ELBO Binding
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks