Orthogonal Yet Coupled: Decoupling Geometric Components for Model Merging

arXiv:2609.37564 · cs.CL · Submitted 2026-09-29 · Read on arXiv

cs.CL

Submitted: 2026-09-29

Updated: 2026-09-29

Comments: Under review

Code: https://github.com/wzj1718/DiGA

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Aggregation — 34× in this paper · explained in 1 episode
• Benchmark — 33× in this paper · explained in 2 episodes
• Model Merging — 24× in this paper · explained in 2 episodes
• Fine-Tuning — 9× in this paper · explained in 5 episodes
• Adaptation — 7× in this paper · explained in 1 episode
• Accuracy — 6× in this paper · explained in 1 episode
• Multimodal Reasoning — 6× in this paper · explained in 5 episodes
• Task Arithmetic — 6× in this paper
• Redundancy — 5× in this paper · explained in 2 episodes
• Calibration — 4× in this paper · explained in 7 episodes
• Cosine Similarity — 4× in this paper · explained in 3 episodes
• Transformer — 4× in this paper · explained in 2 episodes
• AI2 Reasoning Challenge — 2× in this paper
• Ablation — 2× in this paper · explained in 1 episode
• Decoupling — 2× in this paper · explained in 2 episodes
• Grounding — 2× in this paper · explained in 3 episodes
• Task Singular Vector Merging — 2× in this paper
• Ablation Studies — 1× in this paper · explained in 1 episode
• Ablation study — 1× in this paper · explained in 1 episode
• Alignment — 1× in this paper · explained in 1 episode
• Artificial General Intelligence — 1× in this paper
• Benchmarking — 1× in this paper · explained in 3 episodes
• Chain-of-Thought Prompting — 1× in this paper · explained in 2 episodes
• Embeddings — 1× in this paper · explained in 2 episodes
• Following Minimum Hyperspherical Energy — 1× in this paper
• Foundation Model — 1× in this paper · explained in 3 episodes
• Foundation Models — 1× in this paper · explained in 7 episodes
• Generalization — 1× in this paper · explained in 13 episodes
• Generative AI — 1× in this paper · explained in 2 episodes
• LoRA Fine-Tuning — 1× in this paper · explained in 3 episodes
• Robustness — 1× in this paper · explained in 5 episodes
• Scaling Laws — 1× in this paper · explained in 4 episodes
• Verifier — 1× in this paper · explained in 2 episodes
• Visual Grounding — 1× in this paper · explained in 2 episodes

Sources

• Program Synthesis with Large Language Models
• Qwen2.5-VL Technical Report
• Lessons from the Trenches on Reproducible Evaluation of Language Models
• On the Opportunities and Risks of Foundation Models
• HuatuoGPT-Vision, Towards Injecting Medical Visual Knowledge into Multimodal LLMs at Scale
• Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge
• Training Verifiers to Solve Math Word Problems
• The Llama 3 Herd of Models
• PathVQA: 30000+ Questions for Medical Visual Question Answering
• Training Compute-Optimal Large Language Models
• Scaling Laws for Neural Language Models
• SMoA: Spectrum Modulation Adapter for Parameter-Efficient Fine-Tuning
• olmOCR 2: Unit Test Rewards for Document OCR
• DiM\textsuperscript{3}: Bridging Multilingual and Multimodal Models via Direction- and Magnitude-Aware Merging
• MMSI-Bench: A Benchmark for Multi-Image Spatial Intelligence
• Orthogonal Model Merging
• Instruction-Following Evaluation for Large Language Models

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering