ReForge: Refining Merged Models with Anchor-Regularized Regression
cs.LG, cs.AI
Submitted: 2026-05-13
Updated: 2026-10-02
Terminology
Sources
- Program Synthesis with Large Language Models
- AP-BMM: Approximating Capability-Cost Pareto Sets of LLMs via Asynchronous Prior-Guided Bayesian Model Merging
- Deep Learning for Classical Japanese Literature
- Training Verifiers to Solve Math Word Problems
- Challenges in Representation Learning: A report on three machine learning contests
- WildGuard: Open One-Stop Moderation Tools for Safety Risks, Jailbreaks, and Refusals of LLMs
- MergeBench: A Benchmark for Merging Domain-Specialized LLMs
- Tulu 3: Pushing Frontiers in Open Language Model Post-Training
- HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal
- XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models
- An Overview of Multi-Task Learning in Deep Neural Networks
- Aya Dataset: An Open-Access Collection for Multilingual Instruction Tuning
- Magicoder: Empowering Code Generation with OSS-Instruct
- Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms
- ACE-Merging: Data-Free Model Merging with Adaptive Covariance Estimation
- 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