Related papers: Dense Retrieval as Indirect Supervision for Large-…

Recently, several dense retrieval (DR) models have demonstrated competitive performance to term-based retrieval that are ubiquitous in search systems. In contrast to term-based matching, DR projects queries and documents into a dense vector…

Neural sentence embedding models for dense retrieval typically rely on binary relevance labels, treating query-document pairs as either relevant or irrelevant. However, real-world relevance often exists on a continuum, and recent advances…

As a non-linear extension of the classic Linear Discriminant Analysis(LDA), Deep Linear Discriminant Analysis(DLDA) replaces the original Categorical Cross Entropy(CCE) loss function with eigenvalue-based loss function to make a deep neural…

Speculative decoding is an effective and lossless approach for accelerating LLM inference. However, existing widely adopted model-based draft designs, such as EAGLE3, improve accuracy at the cost of multi-step autoregressive inference,…

Dimensionality reduction (DR) on the manifold includes effective methods which project the data from an implicit relational space onto a vectorial space. Regardless of the achievements in this area, these algorithms suffer from the lack of…

Label distribution learning (LDL) requires the learner to predict the degree of correlation between each sample and each label. To achieve this, a crucial task during learning is to leverage the correlation among labels. Deep Forest (DF) is…

Deep Learning is a very powerful machine learning model. Deep Learning trains a large number of parameters for multiple layers and is very slow when data is in large scale and the architecture size is large. Inspired from the shrinking…

While Large Language Models (LLMs) demonstrate exceptional performance in surface-level text generation, their nature in handling complex multi-step reasoning tasks often remains one of ``statistical fitting'' rather than systematic logical…

Text-to-Video Retrieval (TVR) is essential in video platforms. Dense retrieval with dual-modality encoders leads in accuracy, but its computation and storage scale poorly with corpus size. Thus, real-time large-scale applications adopt…

Information Retrieval (IR) is fundamental to many modern NLP applications. The rise of dense retrieval (DR), using neural networks to learn semantic vector representations, has significantly advanced IR performance. Central to training…

Controlling the false discovery rate (FDR) is a popular approach to multiple testing, variable selection, and related problems of simultaneous inference. In many contemporary applications, models are not specified by discrete variables,…

Deep neural networks (DNNs) trained with the logistic loss (i.e., the cross entropy loss) have made impressive advancements in various binary classification tasks. However, generalization analysis for binary classification with DNNs and…

Reinforcement learning improves the reasoning ability of large language models but remains costly and sample-inefficient, as many rollouts provide weak learning signals. Difficulty-aware data selection methods attempt to address this by…

Document-level relation extraction (DocRE) predicts relations for entity pairs that rely on long-range context-dependent reasoning in a document. As a typical multi-label classification problem, DocRE faces the challenge of effectively…

Generative retrieval is a promising new paradigm in text retrieval that generates identifier strings of relevant passages as the retrieval target. This paradigm leverages powerful generative language models, distinct from traditional sparse…

Dense retrieval conducts text retrieval in the embedding space and has shown many advantages compared to sparse retrieval. Existing dense retrievers optimize representations of queries and documents with contrastive training and map them to…

Recent research demonstrates the effectiveness of using fine-tuned language models~(LM) for dense retrieval. However, dense retrievers are hard to train, typically requiring heavily engineered fine-tuning pipelines to realize their full…

Dense retrieval models are typically fine-tuned with contrastive learning objectives that require binary relevance judgments, even though relevance is inherently graded. We analyze how graded relevance scores and the threshold used to…

Supervised deep learning requires a large amount of training samples with annotations (e.g. label class for classification task, pixel- or voxel-wised label map for segmentation tasks), which are expensive and time-consuming to obtain.…

Natural language (NL)-driven table discovery identifies relevant tables from large table repositories based on NL queries. While current deep-learning-based methods using the traditional dense vector search pipeline, i.e.,…