Related papers: DiffuReason: Bridging Latent Reasoning and Generat…

Generative models such as Variational Autoencoders (VAEs) and Generative Adversarial Networks (GANs) have shown promise in sequential recommendation tasks. However, they face challenges, including posterior collapse and limited…

Generative recommendation represents each item as a semantic ID, i.e., a sequence of discrete tokens, and generates the next item through autoregressive decoding. While effective, existing autoregressive models face two intrinsic…

Autoregressive (AR) models remain the standard for natural language generation but still suffer from high latency due to strictly sequential decoding. Recent diffusion-inspired approaches, such as LlaDA and Dream, mitigate this by…

Sequential recommendation aims to predict a user's next action in large-scale recommender systems. While traditional methods often suffer from insufficient information interaction, recent generative recommendation models partially address…

Diffusion models have achieved remarkable success in generating high-fidelity content but suffer from slow, iterative sampling, resulting in high latency that limits their use in interactive applications. We introduce DRiffusion, a parallel…

Diffusion models have shown promising results in speech enhancement, using a task-adapted diffusion process for the conditional generation of clean speech given a noisy mixture. However, at test time, the neural network used for score…

Generative models such as Generative Adversarial Networks (GANs) and Variational Auto-Encoders (VAEs) are widely utilized to model the generative process of user interactions. However, these generative models suffer from intrinsic…

Recently, small models with latent recursion have obtained promising results on complex reasoning tasks. These results are typically explained by the theory that such recursion increases a networks depth, allowing it to compactly emulate…

Reinforcement learning (RL) has been effective for post-training autoregressive (AR) language models, but extending these methods to diffusion language models (DLMs) is challenging due to intractable sequence-level likelihoods. Existing…

Reinforcement learning has become a central paradigm for improving LLM reasoning, but most existing methods optimize policies over discrete token sequences. This creates a mismatch between the optimization space and the structure of…

Sequential recommendation (SRS) has become the technical foundation in many applications recently, which aims to recommend the next item based on the user's historical interactions. However, sequential recommendation often faces the problem…

Diffusion models are a class of flexible generative models trained with an approximation to the log-likelihood objective. However, most use cases of diffusion models are not concerned with likelihoods, but instead with downstream objectives…

Large Language Models (LLMs) demonstrate their reasoning ability through chain-of-thought (CoT) generation. However, LLM's autoregressive decoding may limit the ability to revisit and refine earlier tokens in a holistic manner, which can…

Sequential Recommendation (SR) plays a pivotal role in recommender systems by tailoring recommendations to user preferences based on their non-stationary historical interactions. Achieving high-quality performance in SR requires attention…

Diffusion models recently emerged as a powerful paradigm for recommender systems, offering state-of-the-art performance by modeling the generative process of user-item interactions. However, training such models from scratch is both…

Diffusion-based large language models offer a non-autoregressive alternative for text generation, but enabling them to perform complex reasoning remains challenging. Reinforcement learning has recently emerged as an effective post-training…

Reasoning with large language models often benefits from generating multiple chains-of-thought, but existing aggregation strategies are typically trajectory-level (e.g., selecting the best trace or voting on the final answer), discarding…

Recent advances in large language models (LLMs) have inspired new paradigms for document reranking. While this paradigm better exploits the reasoning and contextual understanding capabilities of LLMs, most existing LLM-based rerankers rely…

To develop effective sequential recommender systems, numerous methods have been proposed to model historical user behaviors. Despite the effectiveness, these methods share the same fast thinking paradigm. That is, for making…

Diffusion language models (DLMs) enable parallel, order-agnostic generation with iterative refinement, offering a flexible alternative to autoregressive large language models (LLMs). However, adapting reinforcement learning (RL) fine-tuning…