arXiv:2606. 18627v1 Announce Type: new Abstract: Model merging has emerged as a training-free alternative to multi-task learning, aiming to combine multiple task-specific fine-tuned models into a single multi-task model.
arXiv:2510.14697v2 Announce Type: replace Abstract: Model merging aims to integrate task-specific abilities from individually fine-tuned models into a single model without extra training. In recent m...
CRLoMTL is a parameter‑efficient multi‑task learning framework that mitigates task interference by operating in a low‑rank parameter‑update space rather than gradient space. It learns task‑specific LoRA updates and fuses them through a shared‑subspace resolver based on singular value decomposition, producing a single deployment‑time update that can be folded into the backbone. Experiments on Swin Transformer backbones across PASCAL‑Context, NYUD‑v2, and CelebA show that CRLoMTL improves accuracy over single‑task baselines while training only a small fraction of the parameters.
arXiv:2606.19164v4 Announce Type: replace-cross Abstract: Model merging enables training-free multi-task learning by aggregating knowledge from models fine-tuned from a shared checkpoint, but their t...
The paper introduces the Universe of Universes (UoU) framework, treating the ecosystem of major large language models as a structured retrieval corpus and proposing a compositional Automated Reasoning and Machine Learning architecture for cross-model retrieval‑augmented generation. It formally defines the Benefit Yield Function (BYF), measuring marginal performance gain per added model, and identifies an implosion threshold θ* where BYF becomes zero and ensemble performance degrades. The work highlights gaps in current LLM ensemble research, such as lack of performance analysis across full model universes, and connects these findings to implications for DoD AI acquisition policy and testing of AI‑enabled systems.
arXiv:2606. 19164v1 Announce Type: cross Abstract: Model merging aims to enable multi-task learning by integrating the capabilities of multiple models fine-tuned from the same pre-trained checkpoint into a single model.
arXiv:2607. 18026v1 Announce Type: new Abstract: Can large language models with substantially different parameter spaces be merged by direct weighted averaging, without training or semantic alignment?
arXiv:2608. 13596v1 Announce Type: cross Abstract: Heterogeneous model fusion seeks to combine models that differ in tasks, initializations, architectures, or scales.
arXiv:2507. 09471v4 Announce Type: replace Abstract: Continual Learning (CL) empowers AI models to continuously learn from sequential task streams.
arXiv:2508. 04227v3 Announce Type: replace-cross Abstract: Vision-language models (VLMs), spanning predictive architectures to generative Multimodal Large Language Models (MLLMs), have revolutionized artificial intelligence through powerful cross-modal alignment and zero-shot generalization.
arXiv:2602. 00072v2 Announce Type: replace Abstract: The performance of machine learning surrogates is critically dependent on data quality and quantity.
The paper introduces Align‑LoRA, a unified LoRA framework for multi‑task learning that replaces complex, isolated adapter designs with a single‑adapter model enhanced by a higher rank and an explicit alignment loss. It demonstrates that a router‑free, multi‑head model with high inter‑head redundancy can outperform more elaborate baselines, and that a unified LoRA can achieve competitive performance while enabling weight merging and zero inference latency. Extensive experiments and theoretical analysis confirm that Align‑LoRA surpasses prevailing approaches, offering a simpler, production‑friendly paradigm for parameter‑efficient fine‑tuning of large language models.