An orthogonal update framework tailored to minimax optimization, which equips orthogonal updates with an adaptive stepsize rule driven by accumulated gradient norms, yielding an effectively parameter-free method for nonconvex-strongly-concave minimax optimization.
Zhi-Wei Zhai, Xin-Yu Wang, Wen-Jing Yan et al.· 0 citations
A low-precision agent can call its full-precision (BF16) model at selected decisions as a fallback. A learned precision router chooses where to call it from the disagreement between the two models and is judged by end-to-end success. An inserted BF16 action, however, can rescue a failing task or damage a succeeding one...
Sicheng Lyu, Xin-Yu Wang, Yu Gu et al.· 0 citations
Kronecker-preconditioned optimizers recompute a cached curvature eigendecomposition only periodically, and implementations and adaptive methods control this through the refresh frequency. We show that frequency leaves part of a schedule free: at a fixed number of refreshes, when they occur changes held-out loss at the...
Xin-Yu Wang, Zhi-Wei Zhai, Yu Gu et al.· 0 citations
FTC, a sequential structured compression framework that adapts the approximation to the current compressed model while jointly exploiting the native Q/K/V head structure under a fixed storage budget, achieves the lowest WikiText-2 perplexity among the compared methods.
Jian Chen, Xin-Yu Wang, Tian-Shuo Yan et al.· 0 citations
Financial QA systems are typically improved before deployment through better retrieval, prompting, or agent coordination, leaving their reliability behavior fixed thereafter. In practice, new SEC-filing questions repeatedly expose heterogeneous errors in period, entity, evidence use, and calculation. Existing self-impr...
Yanzhang Ma, Zhenghan Tai, Han-Wei Wu et al.· 0 citations
FinSAgent is proposed, an evidence-grounded multi-agent framework that reframes SEC filing QA as corpus-aligned retrieval planning and corrects both ends with a single principle: inject corpus-side conditioning wherever model priors would otherwise dominate.
Jijun Chi, Zhenghan Tai, Han-Wei Wu 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.