Chao Ding

Jinru Ding, Lu Lu, Chao Ding et al.

Recent advances in medical large language models (LLMs), multimodal models, and agents demand evaluation frameworks that reflect real clinical workflows and safety constraints. We present MedBench v4, a nationwide, cloud-based benchmarking infrastructure comprising over 700,000 expert-curated tasks spanning 24 primary and 91 secondary specialties, with dedicated tracks for LLMs, multimodal models, and agents. Items undergo multi-stage refinement and multi-round review by clinicians from more than 500 institutions, and open-ended responses are scored by an LLM-as-a-judge calibrated to human ratings. We evaluate 15 frontier models. Base LLMs reach a mean overall score of 54.1/100 (best: Claude Sonnet 4.5, 62.5/100), but safety and ethics remain low (18.4/100). Multimodal models perform worse overall (mean 47.5/100; best: GPT-5, 54.9/100), with solid perception yet weaker cross-modal reasoning. Agents built on the same backbones substantially improve end-to-end performance (mean 79.8/100), with Claude Sonnet 4.5-based agents achieving up to 85.3/100 overall and 88.9/100 on safety tasks. MedBench v4 thus reveals persisting gaps in multimodal reasoning and safety for base models, while showing that governance-aware agentic orchestration can markedly enhance benchmarked clinical readiness without sacrificing capability. By aligning tasks with Chinese clinical guidelines and regulatory priorities, the platform offers a practical reference for hospitals, developers, and policymakers auditing medical AI.

Yuanpeng Liu, Jun Zhou, Yuqi Zhang et al.

In this paper, we focus on estimating the 6D pose of objects in point clouds. Although the topic has been widely studied, pose estimation in point clouds remains a challenging problem due to the noise and occlusion. To address the problem, a novel 3DPVNet is presented in this work, which utilizes 3D local patches to vote for the object 6D poses. 3DPVNet is comprised of three modules. In particular, a Patch Unification (\textbf{PU}) module is first introduced to normalize the input patch, and also create a standard local coordinate frame on it to generate a reliable vote. We then devise a Weight-guided Neighboring Feature Fusion (\textbf{WNFF}) module in the network, which fuses the neighboring features to yield a semi-global feature for the center patch. WNFF module mines the neighboring information of a local patch, such that the representation capability to local geometric characteristics is significantly enhanced, making the method robust to a certain level of noise. Moreover, we present a Patch-level Voting (\textbf{PV}) module to regress transformations and generates pose votes. After the aggregation of all votes from patches and a refinement step, the final pose of the object can be obtained. Compared to recent voting-based methods, 3DPVNet is patch-level, and directly carried out on point clouds. Therefore, 3DPVNet achieves less computation than point/pixel-level voting scheme, and has robustness to partial data. Experiments on several datasets demonstrate that 3DPVNet achieves the state-of-the-art performance, and is also robust against noise and occlusions.