paper-conference

Large multimodal reasoning models have achieved rapid progress, but their advancement is constrained by two major limitations: the …

Reinforcement learning (RL) has shown strong potential for enhancing reasoning in multimodal large language models, yet existing video …

User interactions in recommender systems are inherently complex, often involving behaviors that go beyond simple acceptance or …

Recent advancements in reinforcement learning (RL) have enhanced the reasoning abilities of large language models (LLMs), yet the …

Reasoning-based large language models have excelled in mathematics and programming, yet their potential in knowledge-intensive medical …

Recent multimodal embedding approaches leveraging multimodal large language models (MLLMs) fine-tuned with contrastive learning (CL) …

Many challenging reasoning tasks require not just rapid, intuitive responses, but a more deliberate, multi-step approach. Recent …

While understanding the knowledge boundaries of LLMs is crucial to prevent hallucination, research on knowledge boundaries of LLMs has …

Despite the substantial success of Information Retrieval (IR) in various NLP tasks, most IR systems predominantly handle queries and …

Large language models (LLMs) have shown remarkable emergent capabilities, transforming the execution of functional tasks by leveraging …