arXiv:2601.00086v2 Announce Type: new Abstract: Large language models (LLMs) often struggle to use tools reliably in domain-specific settings, where APIs may be idiosyncratic, under-documented, or tailored to private workflows. This highlights the need for effective adaptation to task-specific tools. We propose RIMRULE, a neuro-symbolic approach for LLM adaptation based on dynamic rule injection. Compact, interpretable rules are distilled from failure traces and injected into the prompt during inference to improve task performance. These rules are proposed by the […]

Ver mais

arXiv:2601.07958v1 Announce Type: new Abstract: Speaker-specific anti-spoofing and synthesis-source tracing are central challenges in audio anti-spoofing. Progress has been hampered by the lack of datasets that systematically vary model architectures, synthesis pipelines, and generative parameters. To address this gap, we introduce LJ-Spoof, a speaker-specific, generatively diverse corpus that systematically varies prosody, vocoders, generative hyperparameters, bona fide prompt sources, training regimes, and neural post-processing. The corpus spans one speakers-including studio-quality recordings-30 TTS families, 500 generatively variant subsets, 10 bona […]

Ver mais

arXiv:2502.05730v3 Announce Type: replace-cross Abstract: Le Cam’s two-point testing method yields perhaps the simplest lower bound for estimating the mean of a distribution: roughly, if it is impossible to well-distinguish a distribution centered at $mu$ from the same distribution centered at $mu+Delta$, then it is impossible to estimate the mean by better than $Delta/2$. It is setting-dependent whether or not a nearly matching upper bound is attainable. We study the conditions under which the two-point testing lower bound […]

Ver mais

arXiv:2502.18428v2 Announce Type: replace-cross Abstract: We study the asymptotic spectral distribution of the conjugate kernel random matrix $YY^top$, where $Y= f(WX)$ arises from a two-layer neural network model. We consider the setting where $W$ and $X$ are random rectangular matrices with i.i.d. entries, where the entries of $W$ follow a heavy-tailed distribution, while those of $X$ have light tails. Our assumptions on $W$ include a broad class of heavy-tailed distributions, such as symmetric $alpha$-stable laws with $alpha in […]

Ver mais

Introduction Disclaimer: This article is a cross post from Pytorch Medium Blog Post. One of the most exciting advancements, that has pushed the frontier of the Artificial Intelligence (AI) in recent years, is Deep Reinforcement Learning (DRL). DRL belongs to the family of machine learning algorithms. It assumes that intelligent machines can learn from their actions similar to the way humans learn from experience. Over the recent years we could witness some impressive real-world applications of DRL. The […]

Ver mais

For a while I’ve been looking for a good format to practice implementing ML algorithms. LeetCode feels too disconnected from real work, but in actual projects you just use existing libraries. What worked for me was breaking real algorithms into progressive steps and implementing them piece by piece. I’ve been using this approach for myself, and recently decided to clean up some of it with tests and hints in case others find it useful. Currently covers: attention, BPE […]

Ver mais