Related papers: LD4MRec: Simplifying and Powering Diffusion Model …

Brains construct not only "first-order" representations of the environment but also "higher-order" representations about those representations -- including higher-order uncertainty estimates that guide learning and adaptive behavior.…

Latent diffusion models (LDMs) dominate high-quality image generation, yet integrating representation learning with generative modeling remains a challenge. We introduce a novel generative image modeling framework that seamlessly bridges…

Image classification models often demonstrate unstable performance in real-world applications due to variations in image information, driven by differing visual perspectives of subject objects and lighting discrepancies. To mitigate these…

We propose a diffusion-based framework for prompt optimization that leverages Diffusion Language Models (DLMs) to iteratively refine system prompts through masked denoising. By conditioning on interaction traces, including user queries,…

Reinforcement learning (RL) recommender systems often rely on static datasets that fail to capture the fluid, ever changing nature of user preferences in real-world scenarios. Meanwhile, generative AI techniques have emerged as powerful…

Dataset distillation provides an effective approach to reduce memory and computational costs by optimizing a compact dataset that achieves performance comparable to the full original. However, for large-scale datasets and complex deep…

Motion has shown to be useful for video understanding, where motion is typically represented by optical flow. However, computing flow from video frames is very time-consuming. Recent works directly leverage the motion vectors and residuals…

In recommender systems, the user-item interaction data is usually sparse and not sufficient for learning comprehensive user/item representations for recommendation. To address this problem, we propose a novel dual-bridging recommendation…

Diffusion models have recently shown significant potential in solving decision-making problems, particularly in generating behavior plans -- also known as diffusion planning. While numerous studies have demonstrated the impressive…

Diffusion-based generative models (DBGMs) perturb data to a target noise distribution and reverse this process to generate samples. The choice of noising process, or inference diffusion process, affects both likelihoods and sample quality.…

Agentic systems powered by Large Language Models (LLMs) have shown strong potential in recommender systems but remain hindered by several challenges. Fine-tuning LLMs is parameter-inefficient, and prompt-based agentic reasoning is limited…

The surge in multimedia content has led to the development of Multi-Modal Recommender Systems (MMRecs), which use diverse modalities such as text, images, videos, and audio for more personalized recommendations. However, MMRecs struggle…

Recent developments in offline reinforcement learning have uncovered the immense potential of diffusion modeling, which excels at representing heterogeneous behavior policies. However, sampling from diffusion policies is considerably slow…

Multi-behavior recommendation faces a critical challenge in practice: auxiliary behaviors (e.g., clicks, carts) are often noisy, weakly correlated, or semantically misaligned with the target behavior (e.g., purchase), which leads to biased…

Diffusion models have shown promising capabilities in trajectory generation for planning in offline reinforcement learning (RL). However, conventional diffusion-based planning methods often fail to account for the fact that generating…

The conditional diffusion model (CDM) enhances the standard diffusion model by providing more control, improving the quality and relevance of the outputs, and making the model adaptable to a wider range of complex tasks. However, inaccurate…

Offline decision-making via diffusion models often produces trajectories that are misaligned with system dynamics, limiting their reliability for control. We propose Model Predictive Diffuser (MPDiffuser), a compositional diffusion…

As the micro-video apps become popular, the numbers of micro-videos and users increase rapidly, which highlights the importance of micro-video recommendation. Although the micro-video recommendation can be naturally treated as the…

Denoising diffusion models show remarkable performances in generative tasks, and their potential applications in perception tasks are gaining interest. In this paper, we introduce a novel framework named DiffRef3D which adopts the diffusion…

Diversity control is an important task to alleviate bias amplification and filter bubble problems. The desired degree of diversity may fluctuate based on users' daily moods or business strategies. However, existing methods for controlling…