6 papers
PHASE-Tree: Modeling Character-State Evolution in Long-Horizon Role-Playing Dialogue
Bo Tang, Jianan Yang, Junyi Zhu +7
Long-horizon role-playing demands that characters remain recognizable as they evolve with the narrative. Yet existing work falls short on two fronts: representations are typically…
See First, Answer Later: Visual Evidence Pre-Alignment via Sufficiency-Driven RL
Yilian Liu, Sicong Leng, Guoshun Nan +7
Multimodal large language models (MLLMs) integrate strong text reasoning with visual inputs, yet their responses can be inconsistent with the underlying images, indicating ineffect…
PERMA: Benchmarking Personalized Memory Agents via Event-Driven Preference and Realistic Task Environments
Shuochen Liu, Junyi Zhu, Long Shu +11
Empowering large language models with long-term memory is crucial for building agents that adapt to users' evolving needs. Existing evaluations of this capability typically interle…
Jigsaw-R1: A Study of Rule-based Visual Reinforcement Learning with Jigsaw Puzzles
Zifu Wang, Junyi Zhu, Bo Tang +4
The application of rule-based reinforcement learning (RL) to multimodal large language models (MLLMs) introduces unique challenges and potential deviations from findings in text-on…
Adversarial Preference Learning for Robust LLM Alignment
Yuanfu Wang, Pengyu Wang, Chenyang Xi +13
Modern language models often rely on Reinforcement Learning from Human Feedback (RLHF) to encourage safe behaviors. However, they remain vulnerable to adversarial attacks due to th…
Xinyu AI Search: Enhanced Relevance and Comprehensive Results with Rich Answer Presentations
Bo Tang, Junyi Zhu, Chenyang Xi +15
Traditional search engines struggle to synthesize fragmented information for complex queries, while generative AI search engines face challenges in relevance, comprehensiveness, an…