FeatCal: Feature Calibration for Post-Merging Models
cs.LG, cs.AI
Submitted: 2026-05-13
Updated: 2026-10-08
Code: https://github.com/egangu/featcal
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- SurgeryV2: Bridging the Gap Between Model Merging and Multi-Task Learning with Deep Representation Surgery
- RegMean++: Enhancing Effectiveness and Generalization of Regression Mean for Model Merging
- MergeBench: A Benchmark for Merging Domain-Specialized LLMs
- Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms
- Model Merging Scaling Laws in Large Language Models
- MergePipe: A Budget-Aware Parameter Management System for Scalable LLM Merging
- InfiFPO: Implicit Model Fusion via Preference Optimization in Large Language Models
- InfiGFusion: Graph-on-Logits Distillation via Efficient Gromov-Wasserstein for Model Fusion
- InfiCoEvalChain: A Blockchain-Based Decentralized Framework for Collaborative LLM Evaluation
- A Comprehensive FP8 Training Recipe for Reasoning-Enhanced 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