5 papers
ShutterMuse: Capture-Time Photography Guidance with MLLMs
Jiayu Li, Yixiao Fang, Tianyu Hu +5
Real-world photography requires capture-time guidance for both camera framing and subject pose. Yet existing aesthetic cropping benchmarks mainly evaluate post-hoc crop prediction…
MemRouter: Memory-as-Embedding Routing for Long-Term Conversational Agents
Tianyu Hu, Weikai Lin, Weizhi Zhang +2
Long-term conversational agents must decide which turns to store in external memory, yet recent systems rely on autoregressive LLM generation at every turn to make that decision. W…
PPTBench: Towards Holistic Evaluation of Large Language Models for PowerPoint Layout and Design Understanding
Zheng Huang, Xukai Liu, Tianyu Hu +2
PowerPoint presentations combine rich textual content with structured visual layouts, making them a natural testbed for evaluating the multimodal reasoning and layout understanding…
Multi-Agent Debate for LLM Judges with Adaptive Stability Detection
Tianyu Hu, Zhen Tan, Song Wang +2
With advancements in reasoning capabilities, Large Language Models (LLMs) are increasingly employed for automated judgment tasks. While LLMs-as-Judges offer promise in automating e…
ChemAgent: Self-updating Library in Large Language Models Improves Chemical Reasoning
Xiangru Tang, Tianyu Hu, Muyang Ye +9
Chemical reasoning usually involves complex, multi-step processes that demand precise calculations, where even minor errors can lead to cascading failures. Furthermore, large langu…