Related papers: GReF: A Unified Generative Framework for Efficient…

Time-series forecasting is one of the most active research topics in artificial intelligence. Applications in real-world time series should consider two factors for achieving reliable predictions: modeling dynamic dependencies among…

Retrieval-augmented generation (RAG) connects large language models (LLMs) to external knowledge, but single-round retrieval is often insufficient for complex multi-hop questions. To enhance search capabilities for complex tasks, most…

The slate re-ranking problem considers the mutual influences between items to improve user satisfaction in e-commerce, compared with the point-wise ranking. Previous works either directly rank items by an end to end model, or rank items by…

Industrial recommender systems have been growing increasingly complex, may involve \emph{diverse domains} such as e-commerce products and user-generated contents, and can comprise \emph{a myriad of tasks} such as retrieval, ranking,…

Generative recommendations (GR), which usually include item tokenizers and generative Large Language Models (LLMs), have demonstrated remarkable success across a wide range of scenarios. The majority of existing research efforts primarily…

Long-range time series forecasting is usually based on one of two existing forecasting strategies: Direct Forecasting and Iterative Forecasting, where the former provides low bias, high variance forecasts and the latter leads to low…

Class-conditional generative models have emerged as accurate and robust classifiers, with diffusion models demonstrating clear advantages over other visual generative paradigms, including autoregressive (AR) models. In this work, we revisit…

Current Retrieval-Augmented Generation (RAG) systems typically employ a traditional two-stage pipeline: an embedding model for initial retrieval followed by a reranker for refinement. However, this paradigm suffers from significant…

This paper proposes a novel approach to improve the training efficiency and the generalization performance of Feed Forward Neural Networks (FFNNs) resorting to an optimal rescaling of input features (OFR) carried out by a Genetic Algorithm…

Decision Trees and Random Forests are among the most widely used machine learning models, and often achieve state-of-the-art performance in tabular, domain-agnostic datasets. Nonetheless, being primarily discriminative models they lack…

Current state-of-the-art approaches to cross-modal retrieval process text and visual input jointly, relying on Transformer-based architectures with cross-attention mechanisms that attend over all words and objects in an image. While…

Recommender systems are essential information technologies today, and recommendation algorithms combined with deep learning have become a research hotspot in this field. The recommendation model known as LFM (Latent Factor Model), which…

Existing prompt-optimization techniques rely on local signals to update behavior, often neglecting broader and recurring patterns across tasks, leading to poor generalization; they further rely on full-prompt rewrites or unstructured…

High-level autonomous driving requires motion planners capable of modeling multimodal future uncertainties while remaining robust in closed-loop interactions. Although diffusion-based planners are effective at modeling complex trajectory…

Text embedding and generative tasks are usually trained separately based on large language models (LLMs) nowadays. This causes a large amount of training cost and deployment effort. Context compression is also a challenging and pressing…

Retrieval-augmented generation (RAG) systems have been shown to be effective in addressing many of the drawbacks of relying solely on the parametric memory of large language models. Recent work has demonstrated that RAG systems can be…

Diffusion models, which iteratively denoise data samples to synthesize high-quality outputs, have achieved empirical success across domains. However, optimizing these models for downstream tasks often involves nested bilevel structures,…

Large language model (LLM) based listwise reranking has emerged as the dominant paradigm for achieving state-of-the-art ranking effectiveness in information retrieval. However, its reliance on feeding full passage texts into the LLM…

We propose a new score-based model with one-step sampling. Previously, score-based models were burdened with heavy computations due to iterative sampling. For substituting the iterative process, we train a standalone generator to compress…

Generative models face a fundamental challenge: they must simultaneously learn high-level semantic concepts (what to generate) and low-level synthesis details (how to generate it). Conventional end-to-end training entangles these distinct,…