相关论文: STAR: Spectral Truncation and Rescale for Model Me…

Model merging unifies independently fine-tuned LLMs from the same base, enabling reuse and integration of parallel development efforts without retraining. However, in practice we observe that merging does not always succeed: certain…

Recent large reasoning models (LRMs) have made substantial progress in complex reasoning tasks, yet they often generate lengthy reasoning paths for every query, incurring unnecessary computation and latency. Existing speed-up approaches…

Model merging aims to integrate multiple task-adapted models into a unified model that preserves the knowledge of each task. In this paper, we identify that the key to this knowledge retention lies in maintaining the directional consistency…

Fine-tuning pre-trained Large Language Models (LLMs) for specialized tasks incurs substantial computational and data costs. While model merging offers a training-free solution to integrate multiple task-specific models, existing methods…

Multi-task learning is effective for related applications, but its performance can deteriorate when the target sample size is small. Transfer learning can borrow strength from related studies; yet, many existing methods rely on restrictive…

Foundation models, such as large language models (LLMs), are powerful but often require customization before deployment to satisfy practical constraints such as safety, privacy, and task-specific requirements, leading to "constrained"…

Training Transformer models on long sequences in a distributed setting poses significant challenges in terms of efficiency and scalability. Current methods are either constrained by the number of attention heads or excessive communication…

Model merging is an efficient post-training strategy for integrating knowledge from multiple finetuned checkpoints of a shared foundation model. Existing methods operate in the parameter space, combining task vectors to mitigate conflicts,…

We observe that current state-of-the-art (SOTA) methods suffer from the performance imbalance issue when performing multi-task reinforcement learning (MTRL) tasks. While these methods may achieve impressive performance on average, they…

Model merging has emerged as a compelling data-free paradigm for multi-task learning, enabling the fusion of multiple fine-tuned models into a single, powerful entity. A key technique in merging methods is sparsification, which prunes…

Fine-tuning large language models (LMs) for individual tasks yields strong performance but is expensive for deployment and storage. Recent works explore model merging to combine multiple task-specific models into a single multi-task model…

In this paper, we consider deep neural networks for solving inverse problems that are robust to forward model mis-specifications. Specifically, we treat sensing problems with model mismatch where one wishes to recover a sparse…

Face clustering is a promising method for annotating unlabeled face images. Recent supervised approaches have boosted the face clustering accuracy greatly, however their performance is still far from satisfactory. These methods can be…

RRAM crossbars have been studied to construct in-memory accelerators for neural network applications due to their in-situ computing capability. However, prior RRAM-based accelerators show efficiency degradation when executing the popular…

I/O performance is crucial to efficiency in data-intensive scientific computing; but tuning large-scale storage systems is complex, costly, and notoriously manpower-intensive, making it inaccessible for most domain scientists. To address…

Motion retargeting seeks to faithfully replicate the spatio-temporal motion characteristics of a source character onto a target character with a different body shape. Apart from motion semantics preservation, ensuring geometric plausibility…

Merging parameters of multiple models has resurfaced as an effective strategy to enhance task performance and robustness, but prior work is limited by the high costs of ensemble creation and inference. In this paper, we leverage the…

As an effective approach to equip models with multi-task capabilities without additional training, model merging has garnered significant attention. However, existing methods face challenges of redundant parameter conflicts and the…

Merging models becomes a fundamental procedure in some applications that consider model efficiency and robustness. The training randomness or Non-I.I.D. data poses a huge challenge for averaging-based model fusion. Previous research efforts…

Deep model merging represents an emerging research direction that combines multiple fine-tuned models to harness their specialized capabilities across different tasks and domains. Current model merging techniques focus on merging all…