Human evaluation confirms that RefCaptioner achieves the best overall performance among the open-source models while remaining competitive on standard video captioning benchmarks, and human evaluation further confirms that its captions are preferred by annotators and enable more source-faithful video reconstruction wit...
Teng-Fei Liu, Yang Shi, Yu-Ran Wang et al.· arXiv.org· 0 citations
Beacon, a novel agentic visual reasoning model trained with supervised fine-tuning and reinforcement learning, is proposed, which achieves the highest average score among the evaluated open-source models and ranks first on 11 benchmarks.
Qi-Xun Wang, Yang Shi, Le-Tian Cheng et al.· arXiv.org· 1 citation
SciToolAgent-Evo, an ontology-aware self-evolving agent for open-world scientific tool acquisition, driven by an evolving memory of skills, experiences, and an ontologized tool graph achieves state-of-the-art performance, validating its robustness and generalization.
Yuqi Tang, Chenyi Zhou, Libin Wang et al.· arXiv.org· 0 citations
MultiRef-Compass is introduced, a unified benchmark for MR2AV generation that integrates automatic metrics with a rejudging-enhanced MLLM-as-a-Judge framework, enabling scalable and auditable evaluation of both perceptual fidelity and reference-conditioned composition.
It is argued that effective knowledge editing must account for the intricate nature of knowledge representation, and three promising research directions are proposed that respect the complexity of knowledge representation in a real-world setting.
