Robuta

https://openreview.net/forum?id=Nu3t6XX103 Model Merging by Gradient Matching | OpenReview Models trained on different datasets can be merged by a weighted-averaging of their parameters, but why does it work and when can it fail? Here, we connect the... model merging gradient matching openreview https://arxiv.org/html/2511.11851v2 Defending Unauthorized Model Merging via Dual-Stage Weight Protection model merging stage weight defending unauthorized via https://aclanthology.org/2025.findings-acl.870/ SeqMMR: Sequential Model Merging and LLM Routing for Enhanced Batched Sequential Knowledge Editing... Shanbao Qiao, Xuebing Liu, Akshat Gupta, Seung-Hoon Na. Findings of the Association for Computational Linguistics: ACL 2025. 2025. sequential model llm routing https://huggingface.co/papers/2505.12082 Paper page - Model Merging in Pre-training of Large Language Models Join the discussion on this paper page model merging pre training paper https://openreview.net/forum?id=KBSh5ChQIo Vanishing Feature: Diagnosing Model Merging and Beyond | OpenReview Model merging offers an efficient way to combine pre-trained neural networks but often suffers from inconsistent performance, especially when merging models... model merging and beyond vanishing feature diagnosing https://openreview.net/forum?id=iD18l6prA7 $C^2M^3$: Cycle-Consistent Multi-Model Merging | OpenReview In this paper, we present a novel data-free method for merging neural networks in weight space. Our method optimizes for the permutations of network neurons... multi model c 2m 3 merging https://github.com/bloomberg/dataless-model-merging GitHub - bloomberg/dataless-model-merging: Code release for Dataless Knowledge Fusion by Merging... Code release for Dataless Knowledge Fusion by Merging Weights of Language Models (https://openreview.net/forum?id=FCnohuR6AnM) -... model merging github bloomberg https://arxiv.org/html/2503.23733v1 AdaMMS: Model Merging for Heterogeneous Multimodal Large Language Models with Unsupervised... large language models merging heterogeneous https://openreview.net/forum?id=W70w5JCzdq DisTaC: Conditioning Task Vectors via Distillation for Robust Model Merging | OpenReview Model merging has emerged as an efficient and flexible paradigm for multi-task learning, with numerous methods being proposed in recent years. However, these... model merging conditioning task vectors via