3 papers
cs.AI2026
ToolPRM: Fine-Grained Inference Scaling of Structured Outputs for Function Calling
Jianghao Lin, Yuanyuan Shi, Xin Peng +10
Large language models (LLMs) excel at function calling, but inference scaling has been explored mainly for unstructured generation. We propose an inference-scaling framework for st…
cs.CV2025
Anatomical Region-Guided Contrastive Decoding: A Plug-and-Play Strategy for Mitigating Hallucinations in Medical VLMs
Xiao Liang, Chenxi Liu, Zhi Ma +4
Medical Vision-Language Models (MedVLMs) show immense promise in clinical applicability. However, their reliability is hindered by hallucinations, where models often fail to derive…
cs.CL2025
Uncovering the Bigger Picture: Comprehensive Event Understanding Via Diverse News Retrieval
Yixuan Tang, Yuanyuan Shi, Yiqun Sun +1
Access to diverse perspectives is essential for understanding real-world events, yet most news retrieval systems prioritize textual relevance, leading to redundant results and limi…