5 papers
CMI-Mem: Toward Generalizable Long-Term Memory Management via CMI-Augmented Reinforcement Learning
Yubo Wang, Qiuyu Zhao, Zenghui Sun +6
Memory Manager models are pivotal in agent systems. Existing reinforcement-learning methods commonly use LLM-judged synthetic question-answer (QA) pairs: this provides useful downs…
Cross-modal Identity Mapping: Minimizing Information Loss in Modality Conversion via Reinforcement Learning
Haonan Jia, Shichao Dong, Xin Dong +6
Large Vision-Language Models (LVLMs) often omit or misrepresent critical visual content in generated image captions. Minimizing such information loss will force LVLMs to focus on i…
REVISION:Reflective Intent Mining and Online Reasoning Auxiliary for E-commerce Visual Search System Optimization
Yiwen Tang, Qiuyu Zhao, Zenghui Sun +3
In Taobao e-commerce visual search, user behavior analysis reveals a large proportion of no-click requests, suggesting diverse and implicit user intents. These intents are expresse…
Networked Restless Multi-Arm Bandits with Reinforcement Learning
Hanmo Zhang, Zenghui Sun, Kai Wang
Restless Multi-Armed Bandits (RMABs) are a powerful framework for sequential decision-making, widely applied in resource allocation and intervention optimization challenges in publ…
INTER: Mitigating Hallucination in Large Vision-Language Models by Interaction Guidance Sampling
Xin Dong, Shichao Dong, Jin Wang +7
Hallucinations in large vision-language models (LVLMs) pose significant challenges for real-world applications, as LVLMs may generate responses that appear plausible yet remain inc…