8 papers
CoEvoWhen: Policy-Tool Coevolution for Ultra-Long Video Temporal Grounding
Yiduo Jia, Muzhi Zhu, Jinchuan Shi +4
Ultra-long video temporal grounding requires balancing long-range evidence search with fine-grained event understanding under a limited visual budget, yet existing agentic methods…
Metric-Bench: Exploring In-context Spatial Metric Reasoning in VLMs for Indoor Scenes
Yuling Xi, Haokai Zhang, Muzhi Zhu +10
Metric reasoning is a critical and challenging task for Vision Language Models (VLMs), playing a pivotal role in embodied AI tasks such as robotic manipulation and autonomous navig…
ForeDreamer: A Self-Evolving Dual-Agent Memory Architecture for Future Event Prediction
Linhao Zhong, Zongze Du, Linyu Wu +6
Open-web future event prediction requires agents to distill reliable signals from noisy, redundant, and incomplete evidence. Existing retrieval/memory mechanisms directly feed retr…
Spatial Memory Agent: Experience-Grounded Procedural Memory for Spatial Intelligence
Haokai Zhang, Yuhang Ding, Yunshu Zhou +5
Spatial intelligence is becoming a foundation for embodied agents, robotic planning, and multimodal assistants. To improve the spatial reasoning ability of VLMs, existing work has…
Efficient Self-Evaluation for Diffusion Language Models via Sequence Regeneration
Linhao Zhong, Linyu Wu, Wen Wang +5
Diffusion large language models (dLLMs) have recently attracted significant attention for their ability to enhance diversity, controllability, and parallelism. However, their non-s…
Preserving Source Video Realism: High-Fidelity Face Swapping for Cinematic Quality
Zekai Luo, Zongze Du, Zhouhang Zhu +7
Video face swapping is crucial in film and entertainment production, where achieving high fidelity and temporal consistency over long and complex video sequences remains a signific…
Unified Open-World Segmentation with Multi-Modal Prompts
Yang Liu, Yufei Yin, Chenchen Jing +7
In this work, we present COSINE, a unified open-world segmentation model that consolidates open-vocabulary segmentation and in-context segmentation with multi-modal prompts (e.g.,…
CoLeCLIP: Open-Domain Continual Learning via Joint Task Prompt and Vocabulary Learning
Yukun Li, Guansong Pang, Wei Suo +6
This paper explores the problem of continual learning (CL) of vision-language models (VLMs) in open domains, where the models need to perform continual updating and inference on a…