Related papers: Decomposing Task Vectors for Refined Model Editing

Foundation models and their checkpoints have significantly advanced deep learning, boosting performance across various applications. However, fine-tuned models often struggle outside their specific domains and exhibit considerable…

Enabling robots to solve multiple manipulation tasks has a wide range of industrial applications. While learning-based approaches enjoy flexibility and generalizability, scaling these approaches to solve such compositional tasks remains a…

In imitation learning for robotic manipulation, decomposing object manipulation tasks into sub-tasks enables the reuse of learned skills and the combination of learned behaviors to perform novel tasks, rather than simply replicating…

We introduce a new multi-modal task for computer systems, posed as a combined vision-language comprehension challenge: identifying the most suitable text describing a scene, given several similar options. Accomplishing the task entails…

The power of multivariate functions is their ability to model a wide variety of phenomena, but have the disadvantages that they lack an intuitive or interpretable representation, and often require a (very) large number of parameters. We…

Many computer vision tasks address the problem of scene understanding and are naturally interrelated e.g. object classification, detection, scene segmentation, depth estimation, etc. We show that we can leverage the inherent relationships…

Large-scale general domain pretraining followed by downstream-specific finetuning has become a predominant paradigm in machine learning. However, discrepancies between the pretraining and target domains can still lead to performance…

Rare words remain a critical bottleneck for speech-to-text systems. While direct fine-tuning improves recognition of target words, it often incurs high cost, catastrophic forgetting, and limited scalability. To address these challenges, we…

Text-guided diffusion models have revolutionized generative tasks by producing high-fidelity content from text descriptions. They have also enabled an editing paradigm where concepts can be replaced through text conditioning (e.g., a dog to…

Learning vector representation for words is an important research field which may benefit many natural language processing tasks. Two limitations exist in nearly all available models, which are the bias caused by the context definition and…

There is a lot of research interest in encoding variable length sentences into fixed length vectors, in a way that preserves the sentence meanings. Two common methods include representations based on averaging word vectors, and…

Dense action detection involves detecting multiple co-occurring actions while action classes are often ambiguous and represent overlapping concepts. We argue that handling the dual challenge of temporal and class overlaps is too complex to…

Existing deep learning approaches for learning visual features tend to overlearn and extract more information than what is required for the task at hand. From a privacy preservation perspective, the input visual information is not protected…

As a few large-scale pre-trained models become the major choices of various applications, new challenges arise for model pruning, e.g., can we avoid pruning the same model from scratch for every downstream task? How to reuse the pruning…

We present a framework for automatically decomposing ("block-modeling") the functional classes of agents within a complex network. These classes are represented by the nodes of an image graph ("block model") depicting the main patterns of…

Increased training parameters have enabled large pre-trained models to excel in various downstream tasks. Nevertheless, the extensive computational requirements associated with these models hinder their widespread adoption within the…

Applying convolutional neural networks to large images is computationally expensive because the amount of computation scales linearly with the number of image pixels. We present a novel recurrent neural network model that is capable of…

Vector space word representations are learned from distributional information of words in large corpora. Although such statistics are semantically informative, they disregard the valuable information that is contained in semantic lexicons…

Multi-task model merging aims to consolidate knowledge from multiple fine-tuned task-specific experts into a unified model while minimizing performance degradation. Existing methods primarily approach this by minimizing differences between…

Effective modeling of heterogeneous subpopulations presents a significant challenge due to variations in individual characteristics and behaviors. This paper proposes a novel approach to address this issue through multi-task learning (MTL)…