Related papers: MICE: Minimal Interaction Cross-Encoders for effic…

Precoding techniques are key to dealing with multiuser interference in the downlink of cell-free (CF) multiple-input multiple-output systems. However, these techniques rely on accurate estimates of the channel state information at the…

This paper reviews, analyzes, and proposes a new perspective on the bi-encoder architecture for neural search. While the bi-encoder architecture is widely used due to its simplicity and scalability at test time, it has some notable issues…

Database algorithms play a crucial part in systems biology studies by identifying proteins from mass spectrometry data. Many of these database search algorithms incur huge computational costs by computing similarity scores for each pair of…

Clinicians need ranking systems that work in real time and still justify their choices. Motivated by the need for a low-latency, decoder-based reranker, we present OG-Rank, a single-decoder approach that pairs a pooled first-token scoring…

We investigate the information complexity of mixed-integer convex optimization under different types of oracles. We establish new lower bounds for the standard first-order oracle, improving upon the previous best known lower bound. This…

The recent breakthrough in artificial intelligence (AI), especially deep neural networks (DNNs), has affected every branch of science and technology. Particularly, edge AI has been envisioned as a major application scenario to provide…

Large language models have achieved remarkable success in various tasks but suffer from high computational costs during inference, limiting their deployment in resource-constrained applications. To address this issue, we propose a novel…

Tool-using agents that act in the world need to be both useful and safe. Well-calibrated model confidences can be used to weigh the risk versus reward of potential actions, but prior work shows that many models are poorly calibrated.…

An important component of autoencoders is the method by which the information capacity of the latent representation is minimized or limited. In this work, the rank of the covariance matrix of the codes is implicitly minimized by relying on…

Late-interaction retrieval models like ColBERT achieve superior accuracy by enabling token-level interactions, but their computational cost hinders scalability and integration with Approximate Nearest Neighbor Search (ANNS). We introduce…

Multiple classifier system (MCS) has become a successful alternative for improving classification performance. However, studies have shown inconsistent results for different MCSs, and it is often difficult to predict which MCS algorithm…

Long document re-ranking has been a challenging problem for neural re-rankers based on deep language models like BERT. Early work breaks the documents into short passage-like chunks. These chunks are independently mapped to scalar scores or…

Pre-trained language models are increasingly important components across multiple information retrieval (IR) paradigms. Late interaction, introduced with the ColBERT model and recently refined in ColBERTv2, is a popular paradigm that holds…

We present a comparative study between cross-encoder and LLMs rerankers in the context of re-ranking effective SPLADE retrievers. We conduct a large evaluation on TREC Deep Learning datasets and out-of-domain datasets such as BEIR and…

BERT based ranking models have achieved superior performance on various information retrieval tasks. However, the large number of parameters and complex self-attention operation come at a significant latency overhead. To remedy this, recent…

Transformers have made great progress in dealing with computer vision tasks. However, existing vision transformers do not yet possess the ability of building the interactions among features of different scales, which is perceptually…

Post-hoc explanation methods for machine learning models have been widely used to support decision-making. One of the popular methods is Counterfactual Explanation (CE), also known as Actionable Recourse, which provides a user with a…

Large language models (LLMs), while driving a new wave of interactive AI applications across numerous domains, suffer from high inference costs and heavy cloud dependency. Motivated by the redundancy phenomenon in linguistics, we propose a…

Reranker models aim to re-rank the passages based on the semantics similarity between the given query and passages, which have recently received more attention due to the wide application of the Retrieval-Augmented Generation. Most previous…

Large Language Models (LLMs) have significantly advanced the field of information retrieval, particularly for reranking. Listwise LLM rerankers have showcased superior performance and generalizability compared to existing supervised…