Related papers: Multimodal Learned Sparse Retrieval with Probabili…

Despite their recent popularity and well-known advantages, dense retrievers still lag behind sparse methods such as BM25 in their ability to reliably match salient phrases and rare entities in the query and to generalize to out-of-domain…

Shuffled linear regression (SLR) seeks to estimate latent features through a linear transformation, complicated by unknown permutations in the measurement dimensions. This problem extends traditional least-squares (LS) and Least Absolute…

Learned sparse retrieval systems aim to combine the effectiveness of contextualized language models with the scalability of conventional data structures such as inverted indexes. Nevertheless, the indexes generated by these systems exhibit…

In complex visual recognition tasks it is typical to adopt multiple descriptors, that describe different aspects of the images, for obtaining an improved recognition performance. Descriptors that have diverse forms can be fused into a…

Pre-trained models have been a foundational approach in speech recognition, albeit with associated additional costs. In this study, we propose a regularization technique that facilitates the training of visual and audio-visual speech…

Large language models deliver strong generative performance but at the cost of massive parameter counts, memory use, and decoding latency. Prior work has shown that pruning and structured sparsity can preserve accuracy under substantial…

Cross-lingual cross-modal retrieval (CCR) aims to retrieve visually relevant content based on non-English queries, without relying on human-labeled cross-modal data pairs during training. One popular approach involves utilizing machine…

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.…

Distributional models provide a convenient way to model semantics using dense embedding spaces derived from unsupervised learning algorithms. However, the dimensions of dense embedding spaces are not designed to resemble human semantic…

Multimodal Large Language Models (MLLMs) possess intrinsic reasoning and world-knowledge capabilities, yet adapting them for dense retrieval remains challenging. Existing approaches rely on invasive parameter updates, such as full…

Automatic Speech Recognition (ASR) aims to convert human speech content into corresponding text. In conversational scenarios, effectively utilizing context can enhance its accuracy. Large Language Models' (LLMs) exceptional long-context…

Since the release of Deepseek-R1, reinforcement learning with verifiable rewards (RLVR) has become a central approach for training large language models (LLMs) on reasoning tasks. Recent work has largely focused on modifying loss functions…

We propose Latent Terms, a method revealing that models trained for dense retrieval, whether single- or multi-vector, learn representations that can trivially be decomposed into retrieval-ready sparse features. When trained on frozen…

State-of-the-art learned reconstruction methods often rely on black-box modules that, despite their strong performance, raise questions about their interpretability and robustness. Here, we build on a recently proposed image reconstruction…

Existing Visual Speech Recognition (VSR) systems commonly rely on left-to-right autoregressive decoding, which can force premature decisions on visually ambiguous tokens before sufficient context is available. We propose DLLM-VSR, to the…

Sequential Recommender Systems (SRS) aim to predict users' next interaction based on their historical behaviors, while still facing the challenge of data sparsity. With the rapid advancement of Multimodal Large Language Models (MLLMs),…

Neural networks are predominantly trained using gradient-based methods, yet in many applications their final predictions remain far from the accuracy attainable within the model's expressive capacity. We introduce Linearized Subspace…

Image and text retrieval is one of the foundational tasks in the vision and language domain with multiple real-world applications. State-of-the-art approaches, e.g. CLIP, ALIGN, represent images and texts as dense embeddings and calculate…

Decentralized sparsity learning has attracted a significant amount of attention recently due to its rapidly growing applications. To obtain the robust and sparse estimators, a natural idea is to adopt the non-smooth median loss combined…

We study the Sparse Plus Low-Rank decomposition problem (SLR), which is the problem of decomposing a corrupted data matrix into a sparse matrix of perturbations plus a low-rank matrix containing the ground truth. SLR is a fundamental…