AI Chronicles

arXiv:2607.01775v1 Announce Type: new Abstract: Discrete diffusion models have steadily improved in quality relative to autoregressive (AR) models. However, these models are normally constrained to fixed-length generation and do not support key-value (KV) caching. Block diffusion partially bridges diffusion and AR by generating token blocks left-to-right, but its fixed-size sequential blocks limit decoding flexibility and parallelism. Here, we present a new class of language models, set diffusion, comprised of (i) a likelihood parameterization that factorizes over flexible-position, flexible-length token sets and (ii) a set-causal diffusion architecture that supports KV cache updates after every inference step. By factorizing over token sets instead of fixed-size blocks, tokens can be decoded in arbitrarily-ordered sets, including sliding-window sets, enabling faster inference and support for any-order decoding. Set diffusion achieves better speed-quality tradeoffs on mathematical reasoning, summarization, and unconditional generation compared to prior diffusion language models while offering stronger infilling performance than block diffusion. We provide the code, along with the model weights and blog post on the project page: https://m-arriola.com/setdlms/

arXiv:2607.01762v1 Announce Type: new Abstract: Many representation learning problems involve directed relations, such as lexical entailment, sentence entailment, ontology hierarchy, and citation links. Standard Euclidean, cosine, and Mahalanobis heads are symmetric, while generic neural scorers can model directionality but provide limited geometric structure. This paper proposes a role-aware neural convex divergence head for asymmetric representation learning. The head applies source- and target-role projections before evaluating an input-convex neural Bregman divergence, yielding a nonnegative structured score in the role-projected space. We characterize its projected-space identity, source-role convexity, directional-gap decomposition, and Hessian-based local curvature. Experiments on lexical, sentence, ontology, and directed graph benchmarks compare symmetric distances, unstructured asymmetric scorers, order/hyperbolic baselines, plain ICNN-Bregman heads, and the proposed role-aware variant. Across ten random seeds on the main semantic and ontology benchmarks, role-aware projections consistently improve directional accuracy over plain ICNN-Bregman heads while preserving zero observed negative divergence rate. The results also identify a boundary case: on large fixed-feature citation prediction, specialized symmetric or hyperbolic baselines remain stronger in ranking accuracy. Overall, the proposed head is best understood as a structured and interpretable plug-in distance module for tasks where directional relations matter.

arXiv:2607.01752v1 Announce Type: new Abstract: Temporal point processes (TPPs) have widespread applications across various domains. Compared to modeling the conditional intensity of a TPP, modeling its cumulative conditional intensity function (CCIF) improves computational efficiency and eliminates numerical approximation errors. However, current CCIF parameterizations uniformly rely on Monotone Neural Networks (MNNs), which we identify as suffering from three structural deadlocks--convexity restrictions, saturation limits, and violations of CCIF modeling requirements--that fundamentally restrict their representational capacity for complex temporal dynamics. To resolve these bottlenecks, this paper proposes a novel framework called Monotone Alternating Splines (MAS). By leveraging distinct interpolation and extrapolation components, MAS provides a flexible and efficient framework for modeling CCIFs. Theoretically, MAS's interpolation provides strong fitting accuracy, while its extrapolation supports robust generalization, reducing the irreducible approximation gaps of MNNs. Extensive experiments show that MAS achieves superior performance on both synthetic and real-world datasets.

arXiv:2607.01746v1 Announce Type: new Abstract: Recurrent representations are trajectories, but representation geometry is often measured from static snapshots. We develop finite-lag operator geometry for recurrent hidden states from observed source-successor pairs $(X_t,X_{t+\Delta})$. The primitive is the conditional transport law $Q_\Delta(dy\mid x)$, estimated by a dense Gaussian source-smoothing operator. From this directed finite-lag law we derive a source-centered transport tensor $G_\Delta$, which decomposes exactly into conditional spread and coherent displacement, and an antisymmetric coordinate circulation $W_\Delta^\rho$, which summarizes directed lagged flow. We prove affine covariance with explicit metric dependence of scalar summaries, dense estimator stability on bounded trajectory clouds, and a finite-lag separation result showing that source-centered transport detects deterministic recurrent motion not recorded by infinitesimal carre-du-champ geometry. A linear-Gaussian closed form calibrates the quantities in terms of the update $A_\Delta$, source covariance, and innovation covariance. Controlled experiments validate the decomposition, circulation, covariance, and stability predictions. In performance matched repeat-copy networks, the framework reveals architecture dependent differences in total transport scale and coherent displacement trace, while coherent displacement fraction is metric and resolution dependent.

arXiv:2607.01736v1 Announce Type: new Abstract: We study how to predict the downstream closed-loop performance of a learned latent world model from validation-time diagnostics alone. Choosing the right checkpoint from a world-model training run is difficult: validation loss and multi-step prediction RMSE keep improving long after closed-loop performance has collapsed. We present a suite of structural validation-time diagnostics drawn from optimal-control theory and apply them to Gymnasium's LunarLander v3, which features shaped rewards. We train an RSSM [5, 4] world model on it and treat per checkpoint CEM-MPC return as the oracle for closed-loop quality. By evaluating 40 metrics against this oracle, we find that the strongest single predictor is the Reward Observability Fraction (ROF), which measures the reward predictor's dependence on the observable subspace. We combine ROF with three structural regularizers into a single-number offline checkpoint selection score, the Composite Reward Observability Fraction (CROF). The CROF-selected world model trains a model-based A2C policy that beats a fairly evaluated model-free A2C baseline by ~24.5 return points while using ~65x fewer real-environment interactions, and the same world model also drives a strong zero-shot CEM-MPC policy. Code and data: https://github.com/nsmoly/LunarLander_RSSM.

arXiv:2607.01694v1 Announce Type: new Abstract: Solving partial differential equations (PDEs) with high-frequency solutions remains a central challenge in physics-informed machine learning due to spectral bias -- the tendency of neural networks to learn low-frequency components preferentially. This paper proposes a Frequency Shift Physics-Informed Extreme Learning Machine (FS-PIELM) framework that addresses this limitation through an additive mechanism for weight initialization. Rather than multiplying random weights by a scaling factor, the method translates the mean of the Gaussian weight distribution while keeping the variance fixed at unity, thereby avoiding the variance amplification inherent in scaling-based methods. Two variants are developed: FS-PIELM-L assigns independent frequency magnitudes to individual neurons, while FS-PIELM-G groups neurons for improved robustness. Theoretical analysis shows that the frequency variance under the proposed framework remains bounded and approaches unity regardless of target frequency, in contrast to the quadratic growth of conventional approaches. The method preserves the computational efficiency of extreme learning machines, requiring only a single linear solve. Experiments on seven benchmark problems spanning six equation types -- Helmholtz, wave, Poisson, Klein-Gordon, heat, and advection-diffusion -- on both regular and complex geometries show that the linear variant achieves the best accuracy in six of seven cases, with improvements of one to nearly five orders of magnitude over existing PIELM variants. The code and data accompanying this manuscript will be made publicly available at https://github.com/xgxgnpu/Physics-informed-vibe-coding/tree/main/FS-PIELM.

arXiv:2607.01693v1 Announce Type: new Abstract: These notes give a proof-oriented introduction to diffusion models from the viewpoint of sampling, tracing a single arc from classical sampling dynamics to modern diffusion samplers, their error analysis, and inference-time control. Throughout, the material is layered into core definitions and identities proved in full, representative estimates proved under simplifying assumptions, and research-level theorems stated with a proof roadmap. The intended audience is beginning graduate students with a background in probability but no prior exposure to stochastic differential equations, stochastic numerics, or diffusion models.

arXiv:2607.01689v1 Announce Type: new Abstract: Model merging aims to combine existing single-task solutions into a multi-task solution without additional data-driven fine-tuning.~Most existing approaches achieve this using geometric properties of local solution spaces. However, such geometric views provide limited guidance for scoring how statistically useful each task-specific update direction is across tasks during merging. To address this, we formulate model merging from a new perspective of probabilistic inference under a product-of-experts (PoE) scenario where each single-task solution defines an energy-based expert model (EBM) over the merged parameters. We show that several existing model merging methods arise as special cases of our framework under energy designs that impose implicit Gaussian assumptions on directional residuals between merged and task-specific models. Empirically, we find that these residuals are often heavy-tailed which exposes a mismatch with the imposed light-tailed Gaussian structures. We address this with a heavy-tailed PoE design based on Cauchy experts, which better captures the observed residual behavior while admitting a provably convergent inference procedure. Experiments across multiple tasks and architectures show significant improvements over state-of-the-arts baselines. Our code is available at https://github.com/MinhLong210/PoE-EBM-Merging.git.

arXiv:2607.01686v1 Announce Type: new Abstract: Foundation models are routinely released to the public, yet the data recipes used to train them -- such as domain mixture weights that determine how different sources are sampled -- are rarely disclosed. This creates an access asymmetry: researchers study the resulting models but lack visibility into the training distribution that produces them. Prior works for inferring training data, such as membership inference, detect at the level of individual samples and thus cannot characterize the global composition of the training corpus. We introduce WARP, a framework that recovers a fine-tuned model's training mixtures directly from its released weights. WARP interpolates between the base and fine-tuned models using model merging, generating pseudo-checkpoints that approximate the missing training trajectory and expose a geometric footprint of the training data in the weight space. From these simulated footprints, WARP extracts geometric features and maps them to domain proportions using either a parameter-free softmax readout or an MLP projector trained on synthetic mixtures. In controlled experiments with BERT and GPT-2, WARP recovers domain mixtures with an average MAE as low as 0.046 and 0.104 respectively, outperforming membership inference and a variant with access to the true training trajectory.

arXiv:2607.01678v1 Announce Type: new Abstract: Communication increasingly dominates the cost of Large Language Model (LLM) pre-training, especially under data-parallel and sharded training schemes, where gradient synchronization and parameter reconstruction overhead increase with model size and system scale. Existing communication-reduction methods either sparsify raw gradients, which can be unstable for modern Adam-style optimizers at high sparsity, or quantize communication, whose savings are fundamentally bounded by bit width and often incur additional runtime overhead. We present SCAPE, a communication-efficient distributed optimizer for LLM training that exploits the stability of AdamS's first-moment to enable aggressive sparsification without loss of LLM quality. Instead of constructing masks from raw gradients, SCAPE derives them from first-moment-based statistics, partitions mask generation across workers to align with optimizer sharding, and delays mask usage by one step so that mask synchronization can overlap with computation. SCAPE also reconstructs the quantities required for second-moment updates from a single synchronized sparse buffer, avoiding an additional collective. We implement SCAPE in Megatron-LM and evaluate its convergence by pre-training GPT-345M on OpenWebText and Llama-500M on SlimPajama-6B using 32 NVIDIA GH200 GPUs on TACC Vista. In both models, SCAPE preserves training stability, validation loss, and downstream task accuracy under 90\% and 99\% sparsity. For Llama-500M, SCAPE reduces end-to-end pre-training wall-clock time by up to 43.3\% while maintaining model quality comparable to dense AdamW and AdamS. For Llama-1.8B, SCAPE achieves up to 3.26$\times$ speedup per step compared to dense AdamS.

Social engineering through phishing remains one of the most common tactics for launching cyberattacks. AI-generated phishing email messages now pose a new challenge for security teams managing email systems, significantly raising the risk because of their advanced sophistication. Modern social engineers use generative AI and open source intelligence (OSINT) to craft thousands of unique messages […]

In this post, we share best practices for reliable multi-turn RL training. We cover how to build a training environment you can trust, set up an external evaluation, design a reward aligned with the end task, manage what changes once the agent runs for multiple turns, and monitor the metrics that tell you when to iterate.

arXiv:2607.00691v1 Announce Type: new Abstract: Black-box optimization is a fundamental science and engineering tool that makes it possible to optimize objectives without gradient information. Unfortunately, as it often requires many function evaluations, it can be challenging when each one is costly. This is especially true when the evaluation function is noisy or failure-prone, and when high-performing solutions are confined to thin, curved, or disconnected regions of the search space. Existing methods leveraging generative models to navigate these subspaces are built to sample from reward-aligned distributions. As a result, they require a large number of evaluations to align their sampler effectively, making them impractical in low-budget settings. We propose SPARROW, an algorithm that completely decouples the generative prior from the reward signal. SPARROW can use any sampler with a known corruption process and trained on unevaluated data, as a fixed, structured proposal operator. Optimization proceeds by rank-based guidance over an archive of evaluated candidates. SPARROW can navigate complex geometries, handle unreliable reward signals, and perform effective optimization under very low evaluation budgets. We provide asymptotic convergence guarantees over the sampler support and demonstrate strong empirical performance on problems with unreliable rewards and geometrically complex landscapes.

arXiv:2607.00095v1 Announce Type: new Abstract: Generative models have emerged as scalable surrogates for physical simulation, yet they offer no guarantee that their outputs respect the conservation laws, boundary conditions, and nonlinear invariants that govern the underlying physics. Constrained sampling closes this gap, enforcing such constraints exactly at inference time without retraining, but at a computational cost: projection, correction, and trajectory-optimization steps are repeated during sampling, with these steps becoming expensive for nonlinear constraints. Standard ML frameworks exacerbate this: their dense tensor algebra and limited sparse solver composability obscure the structure that physical constraints naturally induce, making efficient batched nonlinear optimization difficult to realize in practice. We address this bottleneck by exploiting the structure that sample-wise batching and local PDE couplings induce in the projection subproblems -- namely, block-sparse Jacobian and KKT systems -- exposing this structure using ExaModels.jl and solving the resulting sparse nonlinear programs with MadNLP.jl and GPU sparse factorization. Applied to Physics-Constrained Flow Matching (PCFM), on PDE benchmarks with linear, nonlinear, one-dimensional, and two-dimensional constraints, this approach accelerates nonlinear constraint projection while maintaining constraint satisfaction. These results show that sparse GPU nonlinear optimization is a practical foundation for constrained generative sampling in scientific machine learning.

arXiv:2607.00113v1 Announce Type: new Abstract: Background. Labeled data for security classification is scarce. Semi-supervised learning (SSL) propagates labels from a small labeled pool to larger unlabeled pools. Yet security applications often use SSL as a black box: default parameters, a fixed classifier, and no handling of pseudo-label-induced class imbalance. Aims. Recent work reports sizeable gains from optimizing SSL pipelines via joint search, AutoML, or per-component tuning. These gains are hard to attribute: they may reflect useful SSL-classifier interactions, or mostly from simply tuning the downstream classifier. We disentangle these effects for binary tabular security data with classical SSL and tree-based classifiers. Method. We build SemiScope as an analysis instrument, not a deployment recommendation. It uses Bayesian Optimization to jointly tune SSL settings, confidence filtering, oversampling, and the classifier. The key control, Tuned-Clf, fixes SSL to defaults but gets the same 100-trial classifier budget and validation-set threshold tuning as SemiScope. At 10% labels, we compare them with paired TOST using a +/-1.0 g-measure smallest effect of interest. Results. SemiScope beats every default SSL baseline on all five datasets, improving over the strongest by 0.7-12.7 points. Under the equal-budget control, Tuned-Clf is statistically equivalent to the full pipeline on 4 of 5 datasets; Phishing is inconclusive. Classifier HPO alone recovers a median 86% of SemiScope's gain over Default Self-Training (ST) + Random Forest (RF). Conclusions. The reusable contribution is the decomposition protocol. A simpler recipe suffices: use Self-Training, tune the classifier with Bayesian Optimization, and tune the decision threshold on validation data. It reaches within 1 g-measure of Supervised RF at 20-30% labels on four datasets and 40% on Drebin, at the same or lower label rate than Default ST + RF on every dataset.

arXiv:2607.00127v1 Announce Type: new Abstract: Survival analysis models time-to-event data, but in clinical settings training data are costly and scarce: events accrue over years of follow-up, cohorts are small, and privacy regulations restrict sharing across institutions. Tabular generative models promise augmentation and privacy-preserving cohort sharing, yet are themselves data-hungry -- on the small cohorts typical of survival analysis, a single generator rarely characterizes the population well enough for downstream models trained on its output to match real-data performance. FoGS (Filtered Mixture-of-Generators for Survival analysis) reframes synthetic-data construction as sample selection rather than generation. A candidate pool is drawn from four architecturally distinct tabular generators, and each sample is scored by an ensemble of seven survival models trained on real data, using proper scoring rules as a per-sample plausibility proxy. A two-level pipeline optimizes, in its outer loop, a selection policy -- generator quotas, scorer weights, a random complement, and stratified balancing on event time and censoring -- against held-out downstream performance, while an inner loop tunes the downstream model (XGBoost-Cox). On 16 public datasets under train-on-synthetic, test-on-real (C-index and IBS, $0$--$100$ scale), FoGS yields mean improvements of $+2.17$ in C-index and $+0.67$ in IBS, improving both metrics on 9 of 16 datasets and at least one on 13 (one-sided Wilcoxon $p=0.039$ and $p=0.035$). It matches or exceeds real-data training on most cohorts, with no significant change in nearest-neighbour privacy margin relative to unfiltered sampling. Sample filtering over a heterogeneous generator pool is thus a viable substitute for real-data training in privacy-restricted clinical settings.

arXiv:2607.00152v1 Announce Type: new Abstract: Three of the most popular methods for training language models to reason look like three different tricks. They are not. All three adjust a single number: standard deviation, reflecting how much a prompt's sampled answers disagree. When such a model is trained, it answers each problem many times, and an automatic checker marks every answer right or wrong. The standard deviation of those marks measures the disagreement: largest when the answers split evenly between right and wrong, and zero when they all agree. Group Relative Policy Optimization (GRPO) divides by this number, GRPO Done Right (Dr. GRPO) drops the division, and Decoupled Clip and Dynamic Sampling Policy Optimization (DAPO) discards the groups where it is zero. Each is presented as its own fix, yet this paper proves they are three settings of one dial. That dial is not cosmetic: for right-or-wrong rewards, the disagreement is exactly the size of the training update, the group-standard-deviation identity. A split group teaches the most, while a unanimous group teaches nothing and falls silent. The same result says which problems deserve the most weight and how many tries each one needs. This paper confirms the intuition on a large real difficulty dataset (Big-Math) and in a controlled training run. What looks like a harmless normalization step is the dial that decides where learning happens and how strongly.

arXiv:2607.00154v1 Announce Type: new Abstract: Evolutionary neural architecture design for multivariate time-series forecasting remains underexplored, with most approaches relying on fixed Transformer architectures despite substantial variation across tasks and forecasting settings. This paper introduces an evolutionary neural architecture search framework for discovering task-adaptive Transformer-like models for time-series forecasting (EVOTS). Architectures are encoded using a modular genome representation that enables flexible composition of attention, feed-forward, and projection components, while a repair mechanism enforces structural validity throughout the evolutionary process. This formulation allows effective exploration of a diverse architecture space without relying on hand-crafted design rules. The proposed approach is evaluated on four benchmark datasets from the ETT family (ETTh1, ETTh2, ETTm1, and ETTm2) under multiple forecasting settings, including univariate-to-univariate, multivariate-to-univariate, and multivariate-to-multivariate prediction, with horizons of 96, 192, 336, and 720. In the multivariate-to-multivariate setting, the evolved architectures achieve competitive and, in several cases, improved mean squared error relative to a strong Transformer-based baseline. Additional analyses examine performance differences across forecasting settings and report wall-clock training time to provide a coarse indication of computational cost. Overall, the results demonstrate that evolutionary search can effectively discover flexible and high-performing Transformer-like architectures for multivariate time-series forecasting within practical runtime constraints.

arXiv:2607.00162v1 Announce Type: new Abstract: Parameter-efficient fine-tuning (PEFT) reparameterizes weight updates in a fixed basis: low-rank adapters operate in the spatial domain, while a recent line of spectral methods operates in a fixed Fourier domain. We argue that the choice of domain is itself a design degree of freedom that should be learned, and that no single basis is optimal across tasks, layers, or tokens. We introduce Fractional-Fourier Mixture of Experts, a mixture-of-experts adapter in which every expert carries a learnable fractional-Fourier order that continuously interpolates between the spatial domain (recovering vanilla LoRA) and the Fourier domain (recovering a spectral adapter). Routing tokens through experts that occupy different points on this spatial-spectral continuum lets the model place each low-rank update in the domain where it is most compact, and -- because fractional-Fourier operators of different orders are mutually incoherent -- makes the experts naturally decorrelated, which reduces interference and improves multi-task composition. The order is a single scalar per expert, trained with a separate optimizer, and the transform is computed with an $\mathcal{O}(d\log d)$ chirp--FFT surrogate, so Fractional-Fourier Mixture of Experts adds negligible cost over standard MoE-LoRA. Across commonsense, mathematical, code, and knowledge benchmarks on LLaMA-3.1-8B and Qwen2.5-7B, Fractional-Fourier Mixture of Experts improves over strong MoE-LoRA and spectral baselines -- including FlyLoRA, FourierMoE, and HMoRA -- while keeping the active-parameter budget small, and analysis shows that the learned orders specialize by task and layer in interpretable ways.

arXiv:2607.00164v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards can in principle train calibrated probabilistic forecasters, since a proper scoring rule such as the Brier score is computed from outcomes alone and is minimized in expectation by the true probability. In practice it degrades calibration, and existing remedies address epistemic uncertainty, where a model's confidence accompanies a verifiably correct or incorrect answer. We study aleatoric forecasting, where the forecast itself is the output and the label is one stochastic outcome, taking NFL in-game win probability as a testbed with the betting market as a reference. Rewarding the realized per-play outcome fails, because the single outcome is a noisy target and the policy gradient corrupts the chain of thought. We introduce a verifiable, label-free reward, a state-conditioned empirical win rate estimated from past outcomes, that removes the label noise, and we keep the gradient off the reasoning, by direct prediction or a gradient mask, so it cannot be corrupted. Trained with this reward alone, without human labels or supervised fine-tuning, a 7B model reaches the calibration of the betting market by direct prediction and is better calibrated than a zero-shot frontier model. That frontier model and a tabular estimator reach the same Brier score as this model, identifying the market's small remaining edge as live in-game information beyond their shared inputs. Masking the gradient, rather than dropping the chain of thought, preserves reasoning from which the forecast follows, which ordinary chain-of-thought training corrupts.

arXiv:2607.00170v1 Announce Type: new Abstract: Thermodynamic computing devices based on the Ising model show great promise for low-power AI inference and edge computing, but scalable methods for training large models for such hardware remain limited. Prior theory shows that the time-averaged behavior of high-temperature Gibbs-sampled Ising systems can implement feed-forward neural inference. We turn this theoretical correspondence into a scalable and purely backpropagation-based algorithm for training deep convolutional networks for thermodynamic inference on Ising machine hardware. Our image classification models achieve accuracies of 94.9% on CIFAR-10 and 76.0% on CIFAR-100 under binary Gibbs sampling. We then develop and experimentally validate a mathematical theory relating inference cost to accuracy and controlling autocorrelation times. Subsequently, we calculate asymptotic results showing that inference cost is bounded by a well-controlled tradeoff with performance and exhibit algorithms for computing optimal inference schedules. Finally, we discuss implications for hardware development and the future of high-temperature thermodynamic AI models.

arXiv:2607.00173v1 Announce Type: new Abstract: Federated learning is bandwidth-bound on two orthogonal axes: model size, which limits how often parameter-averaging methods can afford to merge, and class count, which makes per-probe soft-label distillation prohibitive at large vocabularies. Both ceilings tighten as modern systems scale. We collapse the class-count axis to $\lceil \log_2 C \rceil$ bits per probe by transmitting only each peer's $\arg\max$ class index, where $C$ is the number of output classes. The resulting protocol, TallyTrain, is not merely compressed: under non-IID training it can be preferable to soft-label distillation, because under-trained peers are confidently wrong and majority voting filters this noise where soft-label averaging amplifies it. Across standard benchmarks, TallyTrain matches or beats soft-label distillation at up to three orders of magnitude less communication. We also relax the model-size axis: we compose the cheap hard-label consensus with sparse parameter merges to obtain a bandwidth-bridge variant, which Pareto-dominates every tested operating point of the standard FedAvg, FedProx and FedDF baselines.

We're excited to introduce US-based frontier open-weight models in AWS GovCloud (US). With this release, Amazon Bedrock now supports OpenAI’s open-weight GPT OSS models (120B and 20B) and NVIDIA Nemotron (Nano 9B v2, Nano 12B v2, Nano 30B, Super 120B) models. In this post, we cover these models and their capabilities, the inference options for data residency, the available service tiers and how to get started.

In this post, you will learn how to build a serverless A2A gateway on AWS that hosts multiple agents behind a single domain using path-based routing (/agents/{agentId}). Standard A2A clients work without modification.

In this post, you will learn how metadata works across configuration, ingestion, and retrieval, explore enterprise use cases including multi-agent and multi-tenant architectures, and discover best practices for implementation.

In this post, we demonstrate how to implement HippoRAG using a comprehensive AWS stack. We use Amazon Bedrock for LLM capabilities, Amazon Neptune for graph database functionality, Amazon Neptune Analytics for advanced graph algorithms including Personalized PageRank, and Amazon Titan Embeddings for vector representations. This implementation showcases how to build and deploy HippoRAG within AWS infrastructure for enterprise-scale applications.

In this post, you will learn how Inscribe developed an agentic AI system using Amazon Bedrock that reasons across documents the way an expert fraud analyst would. With this new agentic AI system, Inscribe now detects tampered, fabricated, and AI-generated financial documents in under 90 seconds. This is a 20x improvement over traditional manual review, while maintaining the accuracy and explainability required by financial services regulations.

The Amazon Bedrock Model Profiler is an open source tool that aggregates model metadata from multiple AWS APIs and external sources into a single, searchable interface. In this post, you’ll learn what the Model Profiler provides, the real-world scenarios it supports, and how to deploy it in your own environment in under five minutes.

In this post, we demonstrate how to deploy BoltzGen on SageMaker AI and run an end-to-end protein design experiment. By the end of the walkthrough, you have a working setup that scales from quick validation runs to production batch processing. The setup offers two execution modes for different stages of research and uses step-level caching to reduce compute expenses during iterative workflows.

It’s our goal for AWS to be the most secure place to run any workload, and in support of that we’ve been deeply investing in security across our services since AWS's inception more than two decades ago. Our AI services like Amazon Bedrock are built on this foundation and with the same focus.

Today, we’re excited to announce the availability of Anthropic’s most advanced Sonnet model, Claude Sonnet 5, on Amazon Bedrock and Claude Platform on AWS. Claude Sonnet 5 is the first Sonnet model of Anthropic’s latest generation and represents a meaningful step forward. It delivers top-tier intelligence at Sonnet pricing for coding, agents, and everyday professional […]

This post walks through how AG-UI integrates into the Fullstack AgentCore Solution Template (FAST) to build interactive agent frontends on Amazon Bedrock AgentCore. We then show how CopilotKit extends this with generative UI, shared state, and human-in-the-loop interactions, all deployed on Amazon Bedrock AgentCore.

In this post, we show you how to use managed entitlements for Amazon Bedrock to subscribe once from a central account and distribute model access across your organization. This approach removes the need for AWS Marketplace permissions in workload accounts.

In this post, you will learn five practical patterns for building resilient generative AI applications on AWS, progressing from native Amazon Bedrock features to multi-model orchestration using an LLM gateway. These patterns address real-world challenges such as quota exhaustion during unexpected traffic surges, maximizing availability through geographic distribution of inference, and helping prevent noisy neighbor problems in multi-tenant environments.

In this post, we explore how Outpost VFX achieved 8x faster training speeds using AWS infrastructure to transform their face replacement workflow, the technical architecture they implemented to overcome single-GPU limitations, and the measurable results achieved through AWS multi-GPU training.

In this post, we share the technical approach using token-based distillation, lessons learned, and deployment architecture. If you face similar bilingual NER challenges, you can benefit from IBS Software’s experience with the Amazon Bedrock knowledge distillation capabilities.

In this post, you'll learn how fine-tuning Amazon Nova models using Amazon SageMaker AI addresses these specific issues by teaching the models to recognize your exact data patterns, distinguish between similar fields, and process information more efficiently—achieving up to 94.77% extraction accuracy while reducing costs 50%.

In this post, we cover best practices for implementing an effective backup strategy for BI assets in Quick Sight. We start by covering the options for selecting the assets to include in your backup, then explain the high-level APIs available for that purpose, and finalize with sample code to help you get started quickly.

In this post, we show how pairing Amazon Nova 2 Lite with Anthropic’s Claude Sonnet 4.6 delivers an efficient solution for digitizing scanned documents at scale. We built a two-model pipeline on Amazon Bedrock for digitizing scanned yearbook pages. Amazon Nova 2 Lite handles native multimodal extraction in a single call: detecting photos, extracting visible names with coordinates, and returning page-level metadata. Claude Sonnet 4.6 then performs spatial reasoning to match names to faces based on page layout.

In this post, we show you how PAR built a production-ready multi-tenant LLM analytics system that enforces row-level security through a three-layer architecture: cryptographic request signing with AWS SigV4, semantic validation on Amazon Bedrock, and programmatic data isolation via Split-Plane SQL. We demonstrate how each layer operates independently to reduce the risk of cross-tenant data exposure, even when the LLM itself is compromised or manipulated.

In this post, we show you how to build an automated claims processing pipeline using two key Amazon Bedrock capabilities: Amazon Bedrock Data Automation for intelligent document extraction from healthcare claim forms, and Amazon Bedrock AgentCore for hosting an AI agent that validates and transforms the extracted data into FHIR (Fast Healthcare Interoperable Resources) resources in AWS HealthLake. You will learn how to combine these services to create an end-to-end workflow that reduces manual processing while maintaining accuracy through automated validation checks.

In this post, you learn how to debug production agent failures using built-in observability capabilities. We walk through common failure patterns, show how to analyze agent behavior with traces and metrics, and provide structured workflows for resolving issues such as infinite loops and tool invocation failures. This is Part 1 of a two-part series. Part 2 covers performance optimization and memory management.