9 papers
Segregation Before Polarization: How Recommendation Strategies Shape Echo Chamber Pathways
Junning Zhao, Kazutoshi Sasahara, Yu Chen
Social media platforms facilitate echo chambers through feedback loops between user preferences and recommendation algorithms. While algorithmic homogeneity is well-documented, the…
SGR: Stepwise Semantic-Guided Reasoning in Latent Space for Generative Recommendation
Zihao Guo, Jian Wang, Ruxin Zhou +6
Generative Recommendation (GR) has emerged as a transformative paradigm with its end-to-end generation advantages. However, existing GR methods primarily focus on direct Semantic I…
FloCA: Towards Faithful and Logically Consistent Flowchart Reasoning
Jinzi Zou, Bolin Wang, Liang Li +3
Flowchart-oriented dialogue (FOD) systems aim to guide users through multi-turn decision-making or operational procedures by following a domain-specific flowchart to achieve a task…
Enhancing Image Quality Assessment Ability of LMMs via Retrieval-Augmented Generation
Kang Fu, Huiyu Duan, Zicheng Zhang +5
Large Multimodal Models (LMMs) have recently shown remarkable promise in low-level visual perception tasks, particularly in Image Quality Assessment (IQA), demonstrating strong zer…
CoDA: A Context-Decoupled Hierarchical Agent with Reinforcement Learning
Xuanzhang Liu, Jianglun Feng, Zhuoran Zhuang +7
Large Language Model (LLM) agents trained with reinforcement learning (RL) show great promise for solving complex, multi-step tasks. However, their performance is often crippled by…
InconVAD: A Two-Stage Dual-Tower Framework for Multimodal Emotion Inconsistency Detection
Zongyi Li, Junchuan Zhao, Francis Bu Sung Lee +1
Detecting emotional inconsistency across modalities is a key challenge in affective computing, as speech and text often convey conflicting cues. Existing approaches generally rely…