technocracy

arXiv:2105.13440v5 Announce Type: replace Abstract: In an effort to develop topic modeling methods that can be quickly applied to large data sets, we revisit the problem of maximum-likelihood estimation in topic models. It is known, at least informally, that maximum-likelihood estimation in topic models is closely related to non-negative matrix factorization (NMF). Yet, to our knowledge, this relationship has not been exploited previously to fit topic models. We show that recent advances in NMF optimization methods can be […]

Ver mais

arXiv:2602.23556v1 Announce Type: new Abstract: Large-scale Graph Neural Networks (GNNs) are typically trained by sampling a vertex’s neighbors to a fixed distance. Because large input graphs are distributed, training requires frequent irregular communication that stalls forward progress. Moreover, fetched data changes with graph, graph distribution, sample and batch parameters, and caching polices. Consequently, any static prefetching method will miss crucial opportunities to adapt to different dynamic conditions. In this paper, we introduce Rudder, a software module embedded in […]

Ver mais

arXiv:2601.22305v1 Announce Type: new Abstract: Automatic workflow generation is the process of automatically synthesizing sequences of LLM calls, tool invocations, and post-processing steps for complex end-to-end tasks. Most prior methods cast this task as an optimization problem with limited theoretical grounding. We propose to cast workflow generation as Bayesian inference over a posterior distribution on workflows, and introduce textbf{Bayesian Workflow Generation (BWG)}, a sampling framework that builds workflows step-by-step using parallel look-ahead rollouts for importance weighting and a […]

Ver mais

arXiv:2510.06165v2 Announce Type: replace-cross Abstract: Feature attributions are post-training analysis methods that assess how various input features of a machine learning model contribute to an output prediction. Their interpretation is straightforward when features act independently, but it becomes less clear when the predictive model involves interactions, such as multiplicative relationships or joint feature contributions. In this work, we propose a general theory of higher-order feature attribution, which we develop on the foundation of Integrated Gradients (IG). This work […]

Ver mais

Author(s): Mukundan Sankar Originally published on Towards AI. I built a Streamlit SQL coach that grades your queries and fixes your form without giving away the answer. I use SQL a lot. I made this app to help me when my queries are wrong. I didn’t build it because I’m perfect at SQL. Photo by Rubaitul Azad on UnsplashThe author describes the motivation and development of an AI app designed to enhance SQL training, likening the training process […]

Ver mais

The life of a prescription at Amazon Pharmacy From pricing estimation and regulatory compliance to inventory management and chatbot assistants, machine learning models help Amazon Pharmacy customers stay healthy and save time and money. Conversational AI Alexandre Alves Anita Vila September 30, 01:32 PM October 02, 11:42 AM Pharmacies play a vital role in ensuring patients health, but the process of dispensing medications is far more complex than it may appear. At Amazon Pharmacy, we are using artificial […]

Ver mais

Federated Learning (FL) facilitates collaborative model training while preserving data locality; however, the exchange of gradients renders the system vulnerable to Gradient Inversion Attacks (GIAs), allowing adversaries to reconstruct private training data with high fidelity. Existing defenses, such as Differential Privacy (DP), typically employ indiscriminate noise injection across all parameters, which severely degrades model utility and convergence stability. To address those limitation, we proposes Targeted Interpretable Perturbation (TIP), a novel defense framework that integrates model interpretability with frequency […]

Ver mais

The H100 gets all the FP8 attention. But Ampere, Turing, and Volta aren’t going anywhere. Feather emulates FP8 in software using custom Triton kernels with bit-packing, targeting memory bandwidth as the primary optimisation lever. RTX 3050 results: TinyLlama-1.1B: 1.5x over HF FP32 with minimal accuracy loss. Other Results are described in the Github Repo. Honestly though, the kernels are still pretty naive. There’s a long way to go: CUDA Graph optimisation Block-level quantisation Llama-2/3 family support, TinyLlama was […]

Ver mais

arXiv:2601.08858v1 Announce Type: new Abstract: Large Language Models (LLMs) are increasingly deployed in sensitive domains such as healthcare, finance, and law, yet their integration raises pressing concerns around trust, accountability, and reliability. This paper explores adaptive trust metrics for multi LLM ecosystems, proposing a framework for quantifying and improving model reliability under regulated constraints. By analyzing system behaviors, evaluating uncertainty across multiple LLMs, and implementing dynamic monitoring pipelines, the study demonstrates practical pathways for operational trustworthiness. Case studies […]

Ver mais

The life of a prescription at Amazon Pharmacy From pricing estimation and regulatory compliance to inventory management and chatbot assistants, machine learning models help Amazon Pharmacy customers stay healthy and save time and money. Conversational AI Alexandre Alves Anita Vila September 30, 01:32 PM October 02, 11:42 AM Pharmacies play a vital role in ensuring patients health, but the process of dispensing medications is far more complex than it may appear. At Amazon Pharmacy, we are using artificial […]

Ver mais