LiST: Local-Simplex Test-Time LoRA Fusion

• URL: http://arxiv.org/abs/2608.22370v2
• Date: Mon, 31 Aug 2026 07:53:00 GMT
• Title: LiST: Local-Simplex Test-Time LoRA Fusion
• Abstract summary: textbfLiST is a label-free test-time LoRA fusion framework.<n>Experiments on multimodal and language benchmarks show that LiST outperforms static LoRA merging and conventional test-time adaptation baselines.
• Score: 68.96696100246577
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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 \textbf{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.

Related papers

• Dual-Grained Agent Memory and Shapley Context Attribution for Multimodal Agentic Learner [55.80248281761638]
  multimodal large language models (MLLMs) deliver impressive perception yet still falter on scientific and mathematical reasoning.<n>We propose DG-Mem, a dual-grained agentic memory framework that augments a frozen MLLM with a non- externally stored memory built once from training-time rollouts and consulted read-only at test time.
  arXiv  Detail & Related papers  (2026-08-24T13:56:01Z)
• Compliance2LoRA: Personalizable On-Demand Safety Alignment on Arbitrary Policy Subsets via Hypernetwork-Generated LoRA Adapters [50.29667251847595]
  Post-training alignment in large reasoning models (LRMs) has significantly improved their adaptability to diverse safety compliance settings.<n>As LRMs personalization for downstream users takes center stage, the demand for varying levels of policy compliance grows.<n>We propose a unified adaptive hypernetwork-based framework for multi-policy compliance.
  arXiv  Detail & Related papers  (2026-07-30T02:30:03Z)
• REAR: Test-time Preference Realignment through Reward Decomposition [68.09214603569744]
  We introduce a novel framework that models the task as a realignment problem, since the base model often fails to align with the stated preference.<n>We derive a REAlignment Reward (REAR) that selectively rescales the proportions of these two reward terms.<n>We show that REAR can be formulated as a linear combination of token-level policy log-probabilities, making it computationally efficient and easy to integrate with various TTS algorithms.
  arXiv  Detail & Related papers  (2026-06-29T14:17:53Z)
• SCALE-LoRA: Auditing Post-Retrieval LoRA Composition with Residual Merging and View Reliability [2.9388795721577328]
  Low-Rank Adaptation (LoRA) adapters are becoming a practical by-product of parameter-efficient adaptation.<n>We introduce the Sparse-Composition Agreement Layer (SCALE), a post-retrieval audit and composition framework for open-pool LoRA reuse.<n> Detailed scores, paired audits, and path-cost records are reported in the experimental section.
  arXiv  Detail & Related papers  (2026-05-02T13:00:05Z)
• A Unified Language Model for Large Scale Search, Recommendation, and Reasoning [29.766824024623336]
  We introduce NEO, a framework that adapts a pre-trained decoder-only LLM into a tool-free, catalog-grounded generator.<n>NEO represents items as SIDs and trains a single model to interleave natural language and typed item identifiers.<n>We evaluate NEO at scale on a real-world catalog of over 10M items across multiple media types and discovery tasks.
  arXiv  Detail & Related papers  (2026-03-18T09:42:32Z)
• LoRA on the Go: Instance-level Dynamic LoRA Selection and Merging [9.68092924064735]
  Low-Rank Adaptation (LoRA) has emerged as a parameter-efficient approach for fine-tuning large language models.<n>LoGo is a training-free framework that dynamically selects and merges adapters at the instance level without any additional requirements.<n>LoGo outperforms training-based baselines on some tasks upto a margin of 3.6% while remaining competitive on other tasks.
  arXiv  Detail & Related papers  (2025-11-10T14:13:10Z)
• Context Parametrization with Compositional Adapters [3.4155322317700576]
  CompAs is a meta-learning framework that translates context into adapter parameters with a compositional structure.<n>Our work establishes composable adapter generation as a practical and efficient alternative for scaling large language models.
  arXiv  Detail & Related papers  (2025-09-26T10:16:28Z)
• ELDER: Enhancing Lifelong Model Editing with Mixture-of-LoRA [55.697627106315004]
  Large language models (LLMs) require model editing to efficiently update specific knowledge within them and avoid factual errors.<n>Previous approaches manage sequential edits by freezing original parameters and discretely allocating new parameters for each knowledge update.<n>We propose ELDER, a novel approach to create a continuous association between data and adapters.
  arXiv  Detail & Related papers  (2024-08-19T02:27:00Z)
• LoRA-Guard: Parameter-Efficient Guardrail Adaptation for Content Moderation of Large Language Models [15.900125475191958]
  Guardrails have emerged as an alternative to safety alignment for content moderation of large language models (LLMs)<n>We introduce LoRA-Guard, a parameter-efficient guardrail adaptation method that relies on knowledge sharing between LLMs and guardrail models.<n>We show that LoRA-Guard outperforms existing approaches with 100-1000x lower parameter overhead while maintaining accuracy, enabling on-device content moderation.
  arXiv  Detail & Related papers  (2024-07-03T10:38:40Z)
• Retrieval-Augmented Mixture of LoRA Experts for Uploadable Machine Learning [57.36978335727009]
  Low-Rank Adaptation (LoRA) offers an efficient way to fine-tune large language models (LLMs) In this paper, we propose a framework that adaptively retrieves and composes multiple LoRAs based on input prompts.
  arXiv  Detail & Related papers  (2024-06-24T05:24:41Z)
• MeteoRA: Multiple-tasks Embedded LoRA for Large Language Models [4.978361907192563]
  MeteoRA is a scalable and efficient framework that reuses multiple task-specific LoRA adapters into the base LLM. MeteoRA achieves superior performance in handling composite tasks, effectively solving ten sequential problems in a single inference pass.
  arXiv  Detail & Related papers  (2024-05-19T20:46:07Z)
• Towards Modular LLMs by Building and Reusing a Library of LoRAs [64.43376695346538]
  We study how to best build a library of adapters given multi-task data. We introduce model-based clustering, MBC, a method that groups tasks based on the similarity of their adapter parameters. To re-use the library, we present a novel zero-shot routing mechanism, Arrow, which enables dynamic selection of the most relevant adapters.
  arXiv  Detail & Related papers  (2024-05-18T03:02:23Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.