DeepRubric is introduced, a data construction framework that first determines what an evidence-backed report should be evaluated on and then synthesizes aligned query--rubric pairs from those evaluation targets, achieving comparable performance to prior open state-of-the-art deep research models across three benchmarks...
Ming-Hang Zhu, Chu-Yang Wei, Jun Xu et al.· arXiv.org· 5 citations
ZS-CIR aims to retrieve a target image from a reference image and a modification text without paired supervision, typically by encoding composed queries as text-dominant representations within the image-text matching space of VLPs. However, queries reconstructed by visual pseudo-word learning or MLLM-based target reaso...
Xuri Ge, Chun-Hao Wang, Junchen Fu et al.· 0 citations
Analysis shows that effective QE induces layer-concentrated changes in sparse latents aligned with retrieval intent and entity attributes, rather than only perturbing final query embeddings, and suggests that SAEs can explain QE effects and offer a lightweight option for precise retrieval behavior modulation without qu...
Fang Dong, Wei-Ran Shi, Zhi-Wei Xu et al.· 0 citations
The Unified Embodied Seeking and Following Benchmark (UESF-Bench) is introduced, a large-scale and diverse benchmark for embodied human seeking and following that requires agents to handle semantic-guided exploration, reliable behavior switching and recovery, and delayed identity grounding.
Kun Yu, Jianhua Yang, Yixiang Chen et al.· arXiv.org· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.