Related papers: A Replicability Study of XTR

Image retrieval remains a fundamental yet challenging problem in computer vision. While recent advances in Multimodal Large Language Models (MLLMs) have demonstrated strong reasoning capabilities, existing methods typically employ them only…

Click-through rate (CTR) prediction is crucial for personalized online services. Sample-level retrieval-based models, such as RIM, have demonstrated remarkable performance. However, they face challenges including inference inefficiency and…

The advent of transformer-based models such as BERT has led to the rise of neural ranking models. These models have improved the effectiveness of retrieval systems well beyond that of lexical term matching models such as BM25. While…

Multi-vector late-interaction retrievers such as ColBERT achieve state-of-the-art retrieval quality, but their query-time cost is dominated by exhaustively computing token-level MaxSim interactions for every candidate document. While…

The recent literature on online learning to rank (LTR) has established the utility of prior knowledge to Bayesian ranking bandit algorithms. However, a major limitation of existing work is the requirement for the prior used by the algorithm…

Multimodal Large Language Models (MLLMs) have demonstrated exceptional success in various multimodal tasks, yet their deployment is frequently limited by substantial computational demands and prolonged inference times. Given that the vision…

Recent progress in neural information retrieval has demonstrated large gains in effectiveness, while often sacrificing the efficiency and interpretability of the neural model compared to classical approaches. This paper proposes ColBERTer,…

Code generation aims to automatically generate code snippets of specific programming language according to natural language descriptions. The continuous advancements in deep learning, particularly pre-trained models, have empowered the code…

Embedding based retrieval (EBR) is a fundamental building block in many web applications. However, EBR in sponsored search is distinguished from other generic scenarios and technically challenging due to the need of serving multiple…

Multi-task representation learning (MTRL) is an approach that learns shared latent representations across related tasks, facilitating collaborative learning that improves the overall learning efficiency. This paper studies MTRL for…

Retrieval-augmented generation (RAG) enhances large language models (LLMs) by incorporating external knowledge, but existing approaches indiscriminately trigger retrieval and rely on single-path evidence construction, often introducing…

Video-Text Retrieval (VTR) aims to search for the most relevant video related to the semantics in a given sentence, and vice versa. In general, this retrieval task is composed of four successive steps: video and textual feature…

Semi-supervised learning (SSL) algorithms have had great success in recent years in limited labeled data regimes. However, the current state-of-the-art SSL algorithms are computationally expensive and entail significant compute time and…

Reinforcement learning with verifiable rewards (RLVR) typically optimizes for outcome rewards without imposing constraints on intermediate reasoning. This leaves training susceptible to reward hacking, where models exploit loopholes (e.g.,…

Offline post-training adapts a pretrained robot policy to a target dataset by supervised regression on recorded actions. In practice, robot datasets are heterogeneous: they mix embodiments, camera setups, and demonstrations of varying…

This paper introduces xRAG, an innovative context compression method tailored for retrieval-augmented generation. xRAG reinterprets document embeddings in dense retrieval--traditionally used solely for retrieval--as features from the…

The landscape of extremely low-resource machine translation (MT) is characterized by perplexing variability in reported performance, often making results across different language pairs difficult to contextualize. For researchers focused on…

Deep reinforcement learning (DRL) is one promising approach to teaching robots to perform complex tasks. Because methods that directly reuse the stored experience data cannot follow the change of the environment in robotic problems with a…

Traditional multimodal retrieval systems rely primarily on bi-encoder architectures, where performance is closely tied to embedding dimensionality. Recent work, Think-Then-Embed (TTE), shows that incorporating multimodal reasoning to elicit…

The performance of Deep Neural Networks (DNNs) keeps elevating in recent years with increasing network depth and width. To enable DNNs on edge devices like mobile phones, researchers proposed several network compression methods including…