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

Recommender systems and search engines serve as foundational elements of online platforms, with the former delivering information proactively and the latter enabling users to seek information actively. Unifying both tasks in a shared model…

Large reasoning models achieve strong performance on complex tasks through long chain-of-thought (CoT) trajectories, but directly transferring such reasoning processes to smaller models remains challenging. A key difficulty is that not all…

To advance time series forecasting (TSF), various methods have been proposed to improve prediction accuracy, evolving from statistical techniques to data-driven deep learning architectures. Despite their effectiveness, most existing methods…

Chain-of-Thought reasoning significantly improves the performance of large language models on complex tasks, but incurs high inference latency due to long generation traces. Step-level speculative reasoning aims to mitigate this cost, yet…

Real-world user behavior rarely consists of isolated actions; instead, it often forms intent flows governed by spatiotemporal dependencies. To provide integrated service recommendations, we focus on the task of Generative Spatiotemporal…

Generative recommendation has recently attracted widespread attention in industry due to its potential for scaling and stronger model capacity. However, deploying real-time generative recommendation in large-scale advertising requires…

The field of Language Reasoning Models (LRMs) has been very active over the past few years with advances in training and inference techniques enabling LRMs to reason longer, and more accurately. However, a growing body of studies show that…

Inspired by advances in LLMs, reasoning-enhanced sequential recommendation performs multi-step deliberation before making final predictions, unlocking greater potential for capturing user preferences. However, current methods are…

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…

Deep generative models, such as generative adversarial networks and diffusion models, have recently emerged as powerful tools for planning tasks and behavior synthesis in autonomous systems. Various guidance strategies have been introduced…

Reinforcement Learning with Verifiable Rewards (RLVR) has markedly enhanced the reasoning abilities of large language models (LLMs). Its success, however, largely depends on strong base models with rich world knowledge, yielding only modest…

Multimodal Large Language Models (MLLMs) have made remarkable progress on vision-language reasoning, yet most methods still compress visual evidence into discrete textual thoughts, creating an information bottleneck for fine-grained…

Cognitive diagnosis (CD) models latent cognitive states of human learners by analyzing their response patterns on diagnostic tests, serving as a crucial machine learning technique for educational assessment and evaluation. Traditional…

Fine-tuning large language models (LLMs) for recommendation in a generative manner has delivered promising results, but encounters significant inference overhead due to autoregressive decoding in the language space. This work explores…

While generative AI enables high-fidelity UI generation from text prompts, users struggle to articulate design intent and evaluate or refine results-creating gulfs of execution and evaluation. To understand the information needed for UI…

Recommendation system delivers substantial economic benefits by providing personalized predictions. Generative recommendation (GR) integrates LLMs to enhance the understanding of long user-item sequences. Despite employing attention-based…

Large Language Models (LLMs) achieve strong performance through extended inference-time deliberation, yet how their reasoning failures arise remains poorly understood. By analyzing model-generated reasoning trajectories, we find that errors…

Medical Image Grounding (MIG), which involves localizing specific regions in medical images based on textual descriptions, requires models to not only perceive regions but also deduce spatial relationships of these regions. Existing…

Embodied planning requires agents to make coherent multi-step decisions based on dynamic visual observations and natural language goals. While recent vision-language models (VLMs) excel at static perception tasks, they struggle with the…

Reinforcement learning with verifiable rewards (RLVR) is a promising approach for improving the complex reasoning abilities of large language models (LLMs). However, current RLVR methods face two significant challenges: the near-miss reward…