Mixture-Trained Merging for Unified Multi-Objective Models
cs.LG
Submitted: 2026-10-01
Updated: 2026-10-01
Code: https://github.com/vllm-project/vllm12https:
Sources
- DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
- Qwen3 Technical Report
- Nemotron-Cascade: Scaling Cascaded Reinforcement Learning for General-Purpose Reasoning Models
- R-4B: Incentivizing General-Purpose Auto-Thinking Capability in MLLMs via Bi-Mode Annealing and Reinforce Learning
- mSFT: Addressing Dataset Mixtures Overfitting Heterogeneously in Multi-task SFT
- Branch-Train-Merge: Embarrassingly Parallel Training of Expert Language Models
- Averaging Weights Leads to Wider Optima and Better Generalization
- MergeMix: Optimizing Mid-Training Data Mixtures via Learnable Model Merging
- A Tutorial on Bayesian Optimization of Expensive Cost Functions, with Application to Active User Modeling and Hierarchical Reinforcement Learning
- Olmo 3
- RegMix: Data Mixture as Regression for Language Model Pre-training
- Data Mixing Laws: Optimizing Data Mixtures by Predicting Language Modeling Performance
- Training Verifiers to Solve Math Word Problems
- Measuring Mathematical Problem Solving With the MATH Dataset
- Program Synthesis with Large Language Models
- LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code
- Instruction-Following Evaluation for Large Language Models
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