# LiST: Local-Simplex Test-Time LoRA Fusion

arXiv: https://arxiv.org/abs/2608.22370 · HTML: https://mlsanity.com/paper/2608.22370/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in Prompt learning and adaptation of CLIP, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 10 of its 37 references that are in the map.
- First posted on arXiv 23 Aug 2026.

## Placed in

- Multimodal LLMs / vision-language models / [Prompt learning and adaptation of CLIP](https://mlsanity.com/mllm/prompt-learning-and-adaptation-of-clip/)

## Builds on (most cited first, 10 of 10)

- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [Qwen3-VL Technical Report](https://mlsanity.com/paper/2511.21631/) (2025)
- [Editing Models with Task Arithmetic](https://mlsanity.com/paper/2212.04089/) (2022)
- [DeepSeek LLM: Scaling Open-Source Language Models with Longtermism](https://mlsanity.com/paper/2401.02954/) (2024)
- [Towards Stable Test-Time Adaptation in Dynamic Wild World](https://mlsanity.com/paper/2302.12400/) (2023)
- [LoraHub: Efficient Cross-Task Generalization via Dynamic LoRA Composition](https://mlsanity.com/paper/2307.13269/) (2023)
- [Tent: Fully Test-time Adaptation by Entropy Minimization](https://mlsanity.com/paper/2006.10726/) (2020)
- [SITA: Single Image Test-time Adaptation](https://mlsanity.com/paper/2112.02355/) (2021)
- [Medical SAM3: A Foundation Model for Universal Prompt-Driven Medical Image Segmentation](https://mlsanity.com/paper/2601.10880/) (2026)
- [Efficient Test-Time Adaptation through Latent Subspace Coefficients Search](https://mlsanity.com/paper/2510.11068/) (2025)

## Built on by (most cited first, 3 of 3)

- [Reconstructing the Dynamic World: A Representation-Centric View of 4D Scene Reconstruction](https://mlsanity.com/paper/2609.39960/) (2026)
- [PaLoRA: Paced Low-Rank Adaptation for Continual Learning](https://mlsanity.com/paper/2610.04226/) (2026)
- [RePrior: Measurement-Reconciled Prior Correction for Sparse-View CBCT Reconstruction](https://mlsanity.com/paper/2610.14102/) (2026)

## Abstract (arXiv)

Task-specific LoRA adapters offer a modular way to specialize large language and vision-language models. However, existing adapter composition methods are mostly static and cannot adapt to individual test inputs. To address these issues, we propose LiST, a label-free test-time LoRA fusion framework that converts an existing LoRA bank into a target-conditioned local simplex and searches sample-specific fusion weights at inference time. LiST builds joint task representations from LoRA parameter anchors and prompt-level behavior vectors, retrieves neighboring adapters as a local search space, and performs branch-preserving fusion without updating the backbone or adapters. Candidate weights are selected by a prompt-level energy with prior, geometric, and stochastic-consistency constraints, and are deployed only when they pass a safe acceptance rule. Otherwise, LiST falls back to a target-conditioned prior. Experiments on multimodal and language benchmarks show that LiST outperforms static LoRA merging and conventional test-time adaptation baselines, while preserving task-specific adapter utility and improving robustness on unseen tasks.