Related papers: S$^2$GR: Stepwise Semantic-Guided Reasoning in Lat…

Generative Recommenders (GRs), exemplified by the Hierarchical Sequential Transduction Unit (HSTU), have emerged as a powerful paradigm for modeling long user interaction sequences. However, we observe that their "flat-sequence" assumption…

Reinforcement learning (RL) has proven effective in strengthening the reasoning capabilities of large language models (LLMs). A widely adopted method, Group Relative Policy Optimization (GRPO), has shown strong empirical results in training…

Latent reasoning has emerged as a promising paradigm for sequential recommendation, enabling models to capture complex user intent through multi-step deliberation. Yet existing approaches often rely on deterministic latent chains that…

Reasoning segmentation is an emerging vision-language task that requires reasoning over intricate text queries to precisely segment objects. However, existing methods typically suffer from overthinking, generating verbose reasoning chains…

Generative retrieval represents a novel approach to information retrieval. It uses an encoder-decoder architecture to directly produce relevant document identifiers (docids) for queries. While this method offers benefits, current approaches…

Recent studies generally enhance MLLMs' reasoning capabilities via supervised fine-tuning on high-quality chain-of-thought reasoning data, which often leads models to merely imitate successful reasoning paths without understanding what the…

Generative recommendation (GR) is an emerging paradigm that tokenizes items into discrete tokens and learns to autoregressively generate the next tokens as predictions. While this token-generation paradigm is expected to surpass traditional…

Large language models (LLMs) have demonstrated impressive capabilities in natural language understanding and generation, including multi-step reasoning such as mathematical proving. However, existing approaches often lack an explicit and…

Generative recommendation with Semantic IDs (SIDs) has emerged as a promising paradigm, yet existing methods apply a fixed inference strategy, either fast direct generation or slow chain-of-thought reasoning, uniformly across all user…

Generative Recommendation (GR) has gained traction for its merits of superior performance and cold-start capability. As the vital role in GR, Semantic Identifiers (SIDs) represent item semantics through discrete tokens. However, current…

Large Language Models (LLMs) have demonstrated exceptional performance across diverse natural language processing tasks. However, these models exhibit a critical limitation in output diversity, often generating highly similar content across…

Large reasoning language models are typically run with fixed inference budgets, which can waste computation or terminate reasoning prematurely. We introduce Certainty-Guided Reasoning (CGR), a model-agnostic adaptive inference procedure…

Generative recommendation with large language models (LLMs) reframes prediction as sequence generation, yet existing LLM-based recommenders remain limited in leveraging geographic signals that are crucial in mobility and local-services…

Recent advances in Large Language Models (LLMs) have significantly improved complex reasoning capabilities. Retrieval-Augmented Generation (RAG) has further extended these capabilities by grounding generation in dynamically retrieved…

Generative Retrieval (GR) has emerged as a promising paradigm for modern search systems. Compared to multi-stage cascaded architecture, it offers advantages such as end-to-end joint optimization and high computational efficiency. OneSearch,…

Large Language Models (LLMs) achieve strong performance across diverse tasks, but their effectiveness often depends on the quality of the provided context. Retrieval-Augmented Generation (RAG) enriches prompts with external information, but…

Generative models powered by Large Language Models (LLMs) are emerging as a unified solution for powering both recommendation and search tasks. A key design choice in these models is how to represent items, traditionally through unique…

Text-to-Video Retrieval (TVR) is essential in video platforms. Dense retrieval with dual-modality encoders leads in accuracy, but its computation and storage scale poorly with corpus size. Thus, real-time large-scale applications adopt…

A core objective in recommender systems is to accurately model the distribution of user preferences over items to enable personalized recommendations. Recently, driven by the strong generative capabilities of large language models (LLMs),…

Generative recommendation has emerged as a promising paradigm that formulates the recommendations into a text-to-text generation task, harnessing the vast knowledge of large language models. However, existing studies focus on considering…