This technical case study explores the architectural transition from monolithic systems to a resilient Microservices framework using Domain-Driven Design (DDD). It details the strategy for managing high-stakes tax compliance across multiple international jurisdictions for global enterprises. Key takeaways include implementing Bounded Contexts to isolate regulatory logic, ensuring 100% operational uptime through fault isolation, and scaling infrastructure to handle massive transaction volumes.

Ver mais

arXiv:2602.01449v1 Announce Type: cross Abstract: Designing algorithms that can explore multimodal target distributions accurately across successive refinements of an underlying high-dimensional problem is a central challenge in sampling. Annealed Langevin dynamics (ALD) is a widely used alternative to classical Langevin since it often yields much faster mixing on multimodal targets, but there is still a gap between this empirical success and existing theory: when, and under which design choices, can ALD be guaranteed to remain stable as dimension […]

Ver mais

arXiv:2601.14340v1 Announce Type: new Abstract: Large Language Models (LLMs) are widely integrated into interactive systems such as dialogue agents and task-oriented assistants. This growing ecosystem also raises supply-chain risks, where adversaries can distribute poisoned models that degrade downstream reliability and user trust. Existing backdoor attacks and defenses are largely prompt-centric, focusing on user-visible triggers while overlooking structural signals in multi-turn conversations. We propose Turn-based Structural Trigger (TST), a backdoor attack that activates from dialogue structure, using the turn […]

Ver mais

TL;DR: Fine-tuned Chatterbox-Multilingual (Resemble AI’s open-source TTS) to support Telugu, Kannada, Bengali, Tamil, Malayalam, Marathi, Gujarati, and Hindi using LoRA adapters + tokenizer extension. Only 7.8M / 544M parameters trained. Model + audio samples available. — The Problem Chatterbox-Multilingual supports 23 languages with zero-shot voice cloning, but no Dravidian languages (Telugu, Kannada, Tamil, Malayalam) and limited Indo-Aryan coverage beyond Hindi. That’s 500M+ speakers with no representation. The conventional approach would be: build G2P (grapheme-to-phoneme) for each language, retrain […]

Ver mais

arXiv:2603.18391v1 Announce Type: cross Abstract: The distance from calibration, introduced by B{l}asiok, Gopalan, Hu, and Nakkiran (STOC 2023), has recently emerged as a central measure of miscalibration for probabilistic predictors. We study the fundamental problems of computing and estimating this quantity, given either an exact description of the data distribution or only sample access to it. We give an efficient algorithm that exactly computes the calibration distance when the distribution has a uniform marginal and noiseless labels, which […]

Ver mais

arXiv:2602.09277v1 Announce Type: new Abstract: The $beta$-VAE is a foundational framework for unsupervised disentanglement, using $beta$ to regulate the trade-off between latent factorization and reconstruction fidelity. Empirically, however, disentanglement performance exhibits a pervasive non-monotonic trend: benchmarks such as MIG and SAP typically peak at intermediate $beta$ and collapse as regularization increases. We demonstrate that this collapse is a fundamental information-theoretic failure, where strong Kullback-Leibler pressure promotes marginal independence at the expense of the latent channel’s semantic informativeness. By […]

Ver mais