Related papers: Accurate Network Traffic Matrix Prediction via LEA…

Click-through rate (CTR) prediction plays an important role in online advertising systems. On the one hand, traditional CTR prediction models capture the collaborative signals in tabular data via feature interaction modeling, but they lose…

Large language models (LLMs) have emerged as a powerful foundation for intelligent reasoning and decision-making, demonstrating substantial impact across a wide range of domains and applications. However, their massive parameter scales and…

Large language models (LLMs) exhibit remarkable capabilities across diverse tasks, yet aligning them efficiently and effectively with human expectations remains a critical challenge. This thesis advances LLM alignment by introducing novel…

Climate models (CM) are used to evaluate the impact of climate change on the risk of floods and strong precipitation events. However, these numerical simulators have difficulties representing precipitation events accurately, mainly due to…

We introduce DreamerAD, the first latent world model framework that enables efficient reinforcement learning for autonomous driving by compressing diffusion sampling from 100 steps to 1 - achieving 80x speedup while maintaining visual…

Mobile traffic prediction is an important enabler for optimizing resource allocation and improving energy efficiency in mobile wireless networks. Building on the advanced contextual understanding and generative capabilities of large…

The traffic assignment problem is essential for traffic flow analysis, traditionally solved using mathematical programs under the Equilibrium principle. These methods become computationally prohibitive for large-scale networks due to…

Large language models (LLMs) based on decoder-only transformers have demonstrated superior text understanding capabilities compared to CLIP and T5-series models. However, the paradigm for utilizing current advanced LLMs in text-to-image…

Accurate load forecasting is crucial for maintaining the power balance between generators and consumers,particularly with the increasing integration of renewable energy sources, which introduce significant intermittent volatility. With the…

Large language models (LLMs), especially generative pre-trained transformers (GPTs), have recently demonstrated outstanding ability in information comprehension and problem-solving. This has motivated many studies in applying LLMs to…

The rapid expansion of global cloud wide-area networks (WANs) has posed a challenge for commercial optimization engines to efficiently solve network traffic engineering (TE) problems at scale. Existing acceleration strategies decompose TE…

Understanding the traffic dynamics in networks is a core capability for automated systems to monitor and analyze networking behaviors, reducing expensive human efforts and economic risks through tasks such as traffic classification,…

Textual network embedding leverages rich text information associated with the network to learn low-dimensional vectorial representations of vertices. Rather than using typical natural language processing (NLP) approaches, recent research…

Recent advances in diffusion models have demonstrated their strong capabilities in generating high-fidelity samples from complex distributions through an iterative refinement process. Despite the empirical success of diffusion models in…

Diffusion model-based low-light image enhancement methods rely heavily on paired training data, leading to limited extensive application. Meanwhile, existing unsupervised methods lack effective bridging capabilities for unknown degradation.…

The goal of this paper is to optimize the training process of diffusion-based text-to-speech models. While recent studies have achieved remarkable advancements, their training demands substantial time and computational costs, largely due to…

The performance of deep learning models is critically dependent on sophisticated optimization strategies. While existing optimizers have shown promising results, many rely on first-order Exponential Moving Average (EMA) techniques, which…

Diffusion Language Models (DLMs) have recently achieved significant success due to their any-order generation capabilities. However, existing inference methods typically rely on local, immediate-step metrics such as confidence or entropy…

Diffusion language models promise parallel generation, yet still lag behind autoregressive (AR) models in quality. We stem this gap to a failure of introspective consistency: AR models agree with their own generations, while DLMs often do…

Autoregressive (AR) generation is the standard decoding paradigm for Large Language Models (LLMs), but its token-by-token nature limits parallelism at inference time. Diffusion Language Models (DLLMs) offer parallel decoding by recovering…