Related papers: An Empirical Study and Theoretical Explanation on …
Model Merging (MM) has emerged as a scalable paradigm for multi-task learning (MTL), enabling multiple task-specific models to be integrated without revisiting the original training data. Despite recent progress, the reliability of MM under…
One of the main arguments behind studying disentangled representations is the assumption that they can be easily reused in different tasks. At the same time finding a joint, adaptable representation of data is one of the key challenges in…
Numerous works have noted similarities in how machine learning models represent the world, even across modalities. Although much effort has been devoted to uncovering properties and metrics on which these models align, surprisingly little…
Multi-task learning (MTL) aims at achieving a better model by leveraging data and knowledge from multiple tasks. However, MTL does not always work -- sometimes negative transfer occurs between tasks, especially when aggregating loosely…
We formalize and study a phenomenon called feature collapse that makes precise the intuitive idea that entities playing a similar role in a learning task receive similar representations. As feature collapse requires a notion of task, we…
Model merging has emerged as a promising paradigm for enabling multi-task capabilities without additional training. However, existing methods often experience substantial performance degradation compared with individually fine-tuned models,…
In the era of large-scale training, model merging has evolved into a tool for creating multitasking models efficiently. It enables the knowledge of models to be fused, without the need for heavy computation as required in traditional…
Neural collapse ($\mathcal{NC}$) is a phenomenon observed in classification tasks where top-layer representations collapse into their class means, which become equinorm, equiangular and aligned with the classifiers. These behaviours --…
Recent advances in deep learning have led to a surge of open-source models across diverse domains. While model merging offers a promising way to combine their strengths, existing approaches often suffer from parameter conflicts that degrade…
Despite their empirical success, pushing Transformer architectures to extreme depth often leads to a paradoxical failure: representations become increasingly redundant, lose rank, and ultimately collapse. Existing explanations largely…
Model merging, such as model souping, is the practice of combining different models with the same architecture together without further training. In this work, we present a model merging methodology that addresses the difficulty of…
Mixing datasets for fine-tuning large models (LMs) has become critical for maximizing performance on downstream tasks. However, composing effective dataset mixtures typically relies on heuristics and trial-and-error, often requiring…
The problem of model collapse has presented new challenges in iterative training of generative models, where such training with synthetic data leads to an overall degradation of performance. This paper looks at the problem from a…
Reinforcement learning (RL) is central to post-training, particularly for agentic models that require specialized reasoning behaviors. In this setting, model merging offers a practical mechanism for integrating multiple RL-trained agents…
Catastrophic forgetting is a major problem in continual learning, and lots of approaches arise to reduce it. However, most of them are evaluated through task accuracy, which ignores the internal model structure. Recent research suggests…
Recent advances in foundation models have led to a promising trend of developing large recommendation models to leverage vast amounts of available data. Still, mainstream models remain embarrassingly small in size and na\"ive enlarging does…
There is a growing interest in training domain-expert LLMs that excel in specific technical fields compared to their general-purpose instruction-tuned counterparts. However, these expert models often experience a loss in their safety…
Model merging combines multiple fine-tuned models into a single model by adding their weight updates, providing a lightweight alternative to retraining. Existing methods primarily target resolving conflicts between task updates, leaving the…
Model merging acquires general capabilities without extra data or training by combining multiple models' parameters. Previous approaches achieve linear mode connectivity by aligning parameters into the same loss basin using permutation…
Recent work on permutation-based model merging has shown impressive low- or zero-barrier mode connectivity between models from completely different initializations. However, this line of work has not yet extended to the Transformer…