Related papers: Piccolo2: General Text Embedding with Multi-task H…

Hyperbolic embeddings have demonstrated their effectiveness in capturing measures of uncertainty and hierarchical relationships across various deep-learning tasks, including image segmentation and active learning. However, their application…

Do multilingual embedding models encode a language-general representation of proficiency? We investigate this by training linear and non-linear probes on hidden-state activations from Qwen3-Embedding (0.6B, 4B, 8B) to predict CEFR…

We present models for encoding sentences into embedding vectors that specifically target transfer learning to other NLP tasks. The models are efficient and result in accurate performance on diverse transfer tasks. Two variants of the…

In this report, we introduce PLaMo 2, a series of Japanese-focused large language models featuring a hybrid Samba-based architecture that transitions to full attention via continual pre-training to support 32K token contexts. Training…

Continual post-training adapts a single text-to-image diffusion model to learn new tasks without incurring the cost of separate models, but naive post-training causes forgetting of pretrained knowledge and undermines zero-shot…

In the era of large language models, model merging is a promising way to combine multiple task-specific models into a single multitask model without extra training. However, two challenges remain: (a) interference between different models…

Significant efforts have been directed towards adapting self-supervised multimodal learning for Earth observation applications. However, most current methods produce coarse patch-sized embeddings, limiting their effectiveness and…

Dense retrieval calls for discriminative embeddings to represent the semantic relationship between query and document. It may benefit from the using of large language models (LLMs), given LLMs' strong capability on semantic understanding.…

Recent years have witnessed a big convergence of language, vision, and multi-modal pretraining. In this work, we present mPLUG-2, a new unified paradigm with modularized design for multi-modal pretraining, which can benefit from modality…

Decoder-only large language models (LLMs) have been increasingly adopted to build embedding models for diverse tasks. To overcome the inherent limitations of causal attention in representation learning, many existing methods modify the…

We tackle the problem of localizing 3D point cloud submaps using complex and diverse natural language descriptions, and present Text2Loc++, a novel neural network designed for effective cross-modal alignment between language and point…

Creating meta-embeddings for better performance in language modelling has received attention lately, and methods based on concatenation or merely calculating the arithmetic mean of more than one separately trained embeddings to perform…

There has been a recent spike in interest in multi-modal Language and Vision problems. On the language side, most of these models primarily focus on English since most multi-modal datasets are monolingual. We try to bridge this gap with a…

Large Language Models (LLMs) exhibit a significant "embodiment gap", where their text-based representations fail to align with human sensorimotor experiences. This study systematically investigates whether and how task-specific fine-tuning…

Recently, prototype learning has emerged in semi-supervised medical image segmentation and achieved remarkable performance. However, the scarcity of labeled data limits the expressiveness of prototypes in previous methods, potentially…

This work investigates the role of factors like training method, training corpus size and thematic relevance of texts in the performance of word embedding features on sentiment analysis of tweets, song lyrics, movie reviews and item…

Network analysis of human brain connectivity is critically important for understanding brain function and disease states. Embedding a brain network as a whole graph instance into a meaningful low-dimensional representation can be used to…

Model merging integrates the weights of multiple task-specific models into a single multi-task model. Despite recent interest in the problem, a significant performance gap between the combined and single-task models remains. In this paper,…

We combine multi-task learning and semi-supervised learning by inducing a joint embedding space between disparate label spaces and learning transfer functions between label embeddings, enabling us to jointly leverage unlabelled data and…

The paper demonstrate that simple adjustments of the fine-tuning recipes of multimodal large language models (MLLM) are sufficient to mitigate catastrophic forgetting. On visual question answering, we design a 2x2 experimental framework to…