Siyuan Li

Whether vision language models can decide when to answer immediately and, when more evidence is needed, which experiment to perform is studied to reveal limitations in physical reasoning that conventional answer accuracy can overlook.

UBone3D is presented, a novel framework based on physics-rectified conditional flow matching (CFM) that performs point cloud completion directly from partial US observations and demonstrates significant improvements in reconstruction accuracy and anatomical fidelity over existing baselines.

Agent memory can be compressed by 50% with virtually zero performance degradation (retaining up to 99.7% accuracy) and a 2x retrieval speedup by structuring historical context into event-centric maximum spanning trees.

A novel safe task-planning framework, SafeMem, which constructs and maintains a long-term semantic graph memory of the open and dynamic environment, and substantially improves safe success rates compared to state-of-the-art VLM-driven task planners.

ArmorOCR not only enhances adversarial OCR perception but also preserves competitive performance on standard OCR tasks, bridging a critical gap in model robustness.

ASTELD uncovers a critical gap in the autonomous AI landscape: no evaluated systems achieve both local-first deployment and enterprise-grade security.

Multi-turn jailbreaks exploit user intent in ways that traditional safety measures fail to detect, revealing a critical vulnerability in LLM interactions.