Federated Learning (FL) enables collaborative model training while preserving data privacy, but its practical deployment is hampered by system and statistical heterogeneity. While federated network pruning offers a path to mitigate these issues, existing methods face a critical dilemma: server-side pruning lacks personalization, whereas client-side pruning is computationally prohibitive for resource-constrained devices. Furthermore, the pruning process itself induces significant parametric divergence among heterogeneous submodels, destabilizing training and hindering global convergence. To address these challenges, we propose SubFLOT, a […]

Ver mais

arXiv:2604.06212v1 Announce Type: new Abstract: Analytical code is essential for reproducing diagnostic and prognostic prediction model research, yet code availability in the published literature remains limited. While the TRIPOD statements set standards for reporting prediction model methods, they do not define explicit standards for repository structure and documentation. This review quantifies current code-sharing practices to inform the development of TRIPOD-Code, a TRIPOD extension reporting guideline focused on code sharing. We conducted a scoping review of PubMed-indexed articles citing […]

Ver mais

Research: Claude system prompts as a git timeline Anthropic publish the system prompts for Claude chat and make that page available as Markdown. I had Claude Code turn that page into separate files for each model and model family with fake git commit dates to enable browsing the changes via the GitHub commit view. I used this to write my own detailed notes on the changes between Opus 4.6 and 4.7. Tags: system-prompts, anthropic, claude, generative-ai, ai, llms

Ver mais

arXiv:2603.09453v2 Announce Type: replace-cross Abstract: Foundation models are increasingly being deployed in contexts where understanding the uncertainty of their outputs is critical to ensuring responsible deployment. While Bayesian methods offer a principled approach to uncertainty quantification, their computational overhead renders their use impractical for training or inference at foundation model scale. State-of-the-art models achieve parameter counts in the trillions through carefully engineered sparsity including Mixture-of-Experts (MoE) layers. In this work, we demonstrate calibrated uncertainty at scale by introducing […]

Ver mais

The safety of large language models (LLMs) relies on alignment techniques such as reinforcement learning from human feedback (RLHF). However, recent theoretical analyses suggest that reinforcement learning-based training does not acquire new capabilities but merely redistributes the utilization probabilities of existing ones. In this study, we propose “compound jailbreaks” targeting OpenAI gpt-oss-20b, which exploit the generalization failures of alignment. This approach combines multiple attack techniques — each individually defended against — to saturate the instruction hierarchy maintenance process. […]

Ver mais

Recurrent neural networks (RNNs) can be interpreted as discrete-time state-space models, where the state evolution corresponds to an infinite-impulse-response (IIR) filtering operation governed by both feedforward weights and recurrent poles. While, in principle, all parameters including pole locations can be optimized via backpropagation through time (BPTT), such joint learning incurs substantial computational overhead and is often impractical for applications with limited training data. Echo state networks (ESNs) mitigate this limitation by fixing the recurrent dynamics and training only […]

Ver mais

Movement Network Foundation is building a modular blockchain framework that integrates the security-focused Move language with Ethereum’s liquidity to enable safer smart contracts and scalable decentralized applications. By combining the Move VM, modular rollups, and decentralized governance tools like Snapshot and Tally, the project aims to create a high-throughput infrastructure for Web3 builders while advancing its broader mission of democratizing digital ownership.

Ver mais

arXiv:2602.04911v1 Announce Type: new Abstract: We introduce a simple initial working system in which relations (such as part-whole) are directly represented via an architecture with operating and learning rules fundamentally distinct from standard artificial neural network methods. Arbitrary data are straightforwardly encoded as graphs whose edges correspond to codes from a small fixed primitive set of elemental pairwise relations, such that simple relational encoding is not an add-on, but occurs intrinsically within the most basic components of the […]

Ver mais

The role of a Solution Architect has always been to balance vision and reality. The question is, is there a change in how that process begins with the use of generative AI? The answer is, indeed, there is a change, but not in replacing the architect, but in using a powerful co-architect in the beginning of a design process. For many decades, Solution Architects have been using their experience, documentation, whiteboards, and lengthy discussions with stakeholders for designing […]

Ver mais