Jinxi He — accepted AI-conference papers

2026

Caption Anything in Video: Fine-grained Object-centric Captioning via Spatiotemporal Multimodal Prompting

Yolo Yunlong Tang, Jing Bi, Chao Huang, Susan Liang, Daiki Shimada, Hang Hua +13

AAAI 2026technical

In this work, we introduce CAT-V (Caption Anything in Video), a training-free framework for fine-grained object-centric video captioning of user-selected instances. CAT-V combines (i) a SAMURAI-based Segmenter for precise object masks across frames, (ii) a TRACE-Uni Temporal Analyzer for event bound

Cited by 0 Source ↗PDF ↗Scholar ↗

2026

Evolving Contextual Safety in Multi-Modal Large Language Models via Inference-Time Self-Reflective Memory

Ce Zhang, Jinxi He, Junyi He, Katia Sycara, Yaqi Xie

CVPR 2026

Multi-modal Large Language Models (MLLMs) have achieved remarkable performance across a wide range of visual reasoning tasks, yet their vulnerability to safety risks remains a pressing concern. While prior research primarily focuses on jailbreak defenses that detect and refuse explicitly unsafe inpu

Cited by 0 Source ↗Scholar ↗