gezi2333/OrthoReg_checkpoints

Understanding and Enforcing Weight Disentanglement in Task Arithmetic

[CVPR 2026] Official checkpoints for the paper "Understanding and Enforcing Weight Disentanglement in Task Arithmetic".

[Paper]   [Code]

---

🎯 Abstract

Task arithmetic provides an efficient, training-free way to edit pre-trained models, yet lacks a fundamental theoretical explanation for its success. The existing concept of "weight disentanglement" describes the ideal outcome of non-interfering task composition but does not reveal its underlying cause. Crucially, what intrinsic properties of the pre-trained model ($\theta_0$) or the task vectors ($\tau_t$) enable this disentanglement remains underexplored. In this paper, we introduce Task-Feature Specialization (TFS), a model's ability to allocate distinct internal features to different tasks, as the fundamental principle. We first prove that TFS is a sufficient condition for weight disentanglement. More importantly, we find that TFS also gives rise to an observable geometric consequence: weight vector orthogonality. This positions TFS as the common cause for both the desired functional outcome (disentanglement) and a measurable geometric property (orthogonality). This relationship provides the key insight for our method: since the abstract TFS property is intractable to enforce directly, we can instead promote weight disentanglement by shaping its concrete geometric consequence, orthogonality. Therefore, we propose OrthoReg, a simple and effective regularization method that actively enforces an internal orthogonal structure on weight updates ($\Delta W$) that constitute $\tau_t$ during fine-tuning. And we theoretically prove that OrthoReg promotes disentanglement. Extensive experiments demonstrate that OrthoReg consistently and significantly enhances the performance of various task arithmetic methods.

✨ Key Contributions

• 📐 Theory: We identify TFS as a sufficient condition for weight disentanglement, and WVO as its geometric consequence, providing the first principled explanation for task arithmetic.
• 🔧 Method (OrthoReg): A simple regularization term added to the fine-tuning loss that enforces column-wise orthogonality on ΔW, for which we prove theoretical efficacy.
• 🔗 Connection to TTA: We show that OrthoReg and Tangent Task Arithmetic (TTA) share the same underlying mechanism (i.e. inter-task vector orthogonality), but OrthoReg achieves this more efficiently.
• 📊 Experiments: Consistent and significant improvements over Non-linear FT, TTA, ATT-FT, LoRA-ATT across ViT-B-32, ViT-B-16, and ViT-L-14.

---

The OrthoReg Loss

The total loss adds a regularization term to the standard task objective:

$$\mathcal{L}={\mathcal{L}}_{\text{task}}({\theta }_0+\mathrm{\Delta }\theta )+\lambda \cdot {\mathcal{L}}_{\text{ortho}}(\mathrm{\Delta }\theta )\backslash mathcal\{L\}\; =\; \backslash mathcal\{L\}\_\{\backslash text\{task\}\}(\backslash theta\_0\; +\; \backslash Delta\backslash theta)\; +\; \backslash lambda\; \backslash cdot\; \backslash mathcal\{L\}\_\{\backslash text\{ortho\}\}(\backslash Delta\backslash theta)$$

$${\mathcal{L}}_{\text{ortho}}(\mathrm{\Delta }\theta )=\sum _l{\parallel (\mathrm{\Delta }{W}^{(l)}{)}^{\mathrm{\top }}\mathrm{\Delta }{W}^{(l)}-I\parallel }_F^2\backslash mathcal\{L\}\_\{\backslash text\{ortho\}\}(\backslash Delta\backslash theta)\; =\; \backslash sum\_l\; \backslash left\backslash |(\backslash Delta\; W^\{(l)\})^\backslash top\; \backslash Delta\; W^\{(l)\}\; -\; I\backslash right\backslash |\_F^2$$

---

📁 Checkpoint Structure

This repository contains fine-tuned checkpoints for ViT-B-32, ViT-B-16, and ViT-L-14 on all 8 tasks, covering the following finetuning modes:

Directory	Mode	Description
standard_1e-05_{model}/	standard	Non-linear full fine-tuning (baseline)
linear_1e-05_{model}/	linear	TTA — tangent space fine-tuning (baseline)
linear-2_1e-05_{model}/	linear-2	ATT-FT — attention-only fine-tuning (baseline)
linear_ortho_1e-05_lambda1.0_{model}/	linear_ortho	TTA + OrthoReg
ViT-B-32/, ViT-B-16/, ViT-L-14/	—	Pre-trained CLIP base model weights

Each mode directory is organized by dataset:

{mode}_{lr}_{model}/
├── head_CarsVal.pt          # linear classification head
├── head_DTDVal.pt
├── head_EuroSATVal.pt
├── head_GTSRBVal.pt
├── head_MNISTVal.pt
├── head_RESISC45Val.pt
├── head_SUN397Val.pt
├── head_SVHNVal.pt
├── CarsVal/
│   ├── {mode}_finetuned.pt  # fine-tuned model weights (task vector + θ₀)
│   └── {mode}_zeroshot.pt   # zero-shot reference weights
├── DTDVal/
...
└── SVHNVal/

All checkpoints use seed=1993 and lr=1e-5 to match the paper's reported results.

---

🚀 Usage

Step 1 — Clone this repository

git lfs install
git clone https://huggingface.co/gezi2333/OrthoReg-checkpoints

Place the cloned folder as OrthoReg/checkpoints_1993/ inside your code directory:

mv OrthoReg-checkpoints/* OrthoReg/checkpoints_1993/

Step 2 — Install the codebase

git clone https://github.com/RL-MIND/OrthoReg
cd OrthoReg
conda env create
conda activate tangent-arithmetic
export PYTHONPATH="$PYTHONPATH:$PWD"

Step 3 — Run evaluation

Evaluate single-task accuracy:

python src/eval_single_task.py \
    --model ViT-B-32 \
    --finetuning-mode linear_ortho \
    --ortho-lambda 1.0 \
    --lr 1e-5 \
    --seed 1993 \
    --data-location /path/to/datasets/

Evaluate task addition:

python src/eval_task_addition.py \
    --model ViT-B-32 \
    --finetuning-mode linear_ortho \
    --ortho-lambda 1.0 \
    --lr 1e-5 \
    --seed 1993 \
    --data-location /path/to/datasets/

Evaluate task negation:

python src/eval_task_negation.py \
    --model ViT-B-32 \
    --finetuning-mode linear_ortho \
    --ortho-lambda 1.0 \
    --lr 1e-5 \
    --seed 1993 \
    --data-location /path/to/datasets/

Run eval_single_task with --finetuning-mode none --ortho-lambda 0 first to generate zeroshot_accuracies.json, which is required as the reference for normalized accuracy.

Argument reference

Argument	Value for these checkpoints
--seed	1993
--lr	1e-5
--ortho-lambda	0 for baselines, xx for OrthoReg variants
--finetuning-mode	see table above

---

📦 Datasets

We evaluate on 8 image classification benchmarks: Cars · DTD · EuroSAT · GTSRB · MNIST · RESISC45 · SUN397 · SVHN

For dataset preparation, follow the instructions in the TTA repository.

---

📝 Citation

If you find this work useful, please cite:

@inproceedings{liu2026orthoreg,
  title     = {Understanding and Enforcing Weight Disentanglement in Task Arithmetic},
  author    = {Liu, Shangge and Yin, Yuehan and Wang, Lei and Fan, Qi and
               Shi, Yinghuan and Li, Wenbin and Gao, Yang and Tao, Dacheng},
  booktitle = {CVPR},
  year      = {2026}
}

---

📬 Acknowledgements

This codebase is built on top of Task Arithmetic, Tangent Task Arithmetic, and Attention-Only Fine-tuning. We thank the authors for releasing their code.