Multi-turn visual search agents answer questions about high-resolution images by iteratively deciding where to look. Reinforcement learning for these agents rewards only the final answer, leaving the search process unsupervised. Consequently, faulty routes in which the reasoning process is erroneous yet the final resul...
Zhangquan Chen, Yao-Xin Niu, Xiang An et al.· 0 citations
EviViT, a lightweight attachment that learns where a pretrained vision transformer should acquire detail, is introduced, a lightweight attachment that learns where a pretrained vision transformer should acquire detail without refitting.
Yao-Xin Niu, Zhangquan Chen, Yang Zhang et al.· 0 citations
This work introduces TempFinRAG, a point-in-time evaluation protocol built from public filings and XBRL facts, and introduces TempFinQA, a point-in-time evaluation protocol built from public filings and XBRL facts, and evaluates the framework on complementary evidence-grounded, numerical, conversational, and multi-tabl...
Lanju Tao, Zheng-Ji Li, Ying-Rui Ji et al.· Symmetry· 0 citations
Adaptive Hierarchical Representation Alliance (AHRA), a hierarchical shared--private expert framework, is proposed, which consistently improves over strong baselines and remains robust under noisy and missing-modality settings.
Chun-Lei Meng, Peng-Bin Feng, Jacqueline J. Pang et al.· 2 citations
It is argued that causal deployment, not decodability, is what interpretability should measure when the question is whether a model uses a piece of knowledge, and a cheap instrument for measuring it is given.
Chih-Ting Liao, Xinzhuo Cao· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
