Watermarking the final patch produced by a coding agent provides provenance evidence for the submitted artifact, but does not authenticate the visible process that produced it. Behavioral watermarking methods primarily provide a global detection or identifier-recovery signal, so a locally edited trajectory may retain s...
Bo-Kang Zeng, Zhengguang Gao, Xiao-Yu Li et al.· 0 citations
RiPPLE provides a whole-space ranking from a fractional anchor-training budget, with comparisons interpreted under their respective evaluation and cost protocols, and the results examine ranking quality, label efficiency, architecture selection, and the roles of readout, coverage, and propagation.
Yi-Fan Yang, Zhao-Yan Wang, Zheng-Guang Gao et al.· 0 citations
This work introduces CoRA-NAS (COarse Ranking + Anchor-residual), a two-stage framework combining a static ranking prior with low-cost learning-curve refinement that combines cross-space ranking robustness with low-cost architecture selection.
Yi-Fan Yang, Zhao-Yan Wang, Zhengguang Gao et al.· 1 citation
Language generation in the limit asks for valid unseen elements from every exhaustive positive presentation of an unknown infinite language. We characterize this task for arbitrary families over a countable universe. Generation is possible exactly when each target can be assigned a finite positive witness so that the t...
Xiao-Yu Li, Andi Han, Jiao-Jiao Jiang et al.· 0 citations
DRIFT, a black-box attack that combines partial forward diffusion with stochastic reverse resampling, achieves 98-100% attack success and the best image quality among the compared attacks, without secret keys, verifier internals, or per-image gradient optimization.
Rui Bao, Zheng-Guang Gao, Xiao-Yu Li et al.· 0 citations
A spherical-cap construction proves the latter claim without assuming sparsity merely on the sampling support without assuming sparsity merely on the sampling support, and obtains agnostic minimax excess-risk bounds of order up to logarithms.
Xiao-Yu Li, Zhizhou Sha, Jiao-Jiao Jiang et al.· 0 citations
TRACE is presented, to the authors' knowledge the first agent watermark that is distortion-free in its action choices, self-synchronizing under deletion, and unconditionally invariant under rewriting, and it is proved this behavioral watermark's signal is bought with decision entropy.
We determine exactly what a kurtosis bound buys for one-sided tail control. For the class $\mathcal{C}(\kappa)$ of real random variables with mean $0$, variance $1$, and fourth moment at most $\kappa$, the skewness left free, we compute the worst-case tail probability $V_1(t,\kappa)=\sup_{X\in\mathcal{C}(\kappa)}\mathb...
Xiaoyu Li, Andi Han, Jiaojiao Jiang et al.· 0 citations
Worst-case multiclass bounds do not become smaller when the best classifier is already nearly correct: what is missing is an optimistic rate, a guarantee whose fluctuation scales with the oracle risk itself. For a class of Natarajan dimension $d_N$ and Daniely-Shalev-Shwartz dimension $d_{DS}$, the optimal excess risk...
Xiao-Yu Li, Andi Han, Jiao-Jiao Jiang et al.· 1 citation
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
