Can Cloudflare CEO Matthew Prince save the web from AI?
Today, I’m talking with Matthew Prince, who is CEO of Cloudflare. This episode is part of a two-part series on the future of business. Matthew…
en
Código abierto
1655
162
First-Order Stationarity of Reverse Diffusions
Recent literature has shown a strong connection between optimization and sampling. We develop the corresponding first-order theory for diffusion models. First, the SDE-based reverse-time flows of overdamped and underdamped Langevin diffusions contract relative Fisher divergences at explicit exponential rates whenever the stationary potential of the forward process is strongly convex---a condition on the noising process one chooses, not on the data. This is a unique advantage of SDE-based reverse diffusion, absent in the reverse process based on ODEs. Second, we incorporate discretization and establish averaged first-order stationarity bounds---the sampling analog of averaged gradient-norm guarantees in nonconvex optimization---for samplers of both overdamped and underdamped diffusion models. As in nonconvex optimization, the convexity-free certificate is local: it guarantees score consistency, not global mode weights.
en
New LoRA Skills Should Read but Never Write
Low-rank adapters (LoRA) make it cheap to fine-tune a large language model once per task, but combining several independently trained adapters into one model remains difficult: merging the updates in weight space causes interference, retraining on all task data is expensive, and routing between separate adapters gives up the goal of a single combined model. We trace the difficulty to two choices that every composition method makes implicitly. A LoRA update admits infinitely many equivalent factorizations; the choice among them is invisible while an adapter serves alone, but it determines what a learned interaction between adapters can see. A coupling between an old skill and a new one can likewise point in either direction, and the direction decides whether the old skills keep computing what they computed before. We introduce READ (Read-only Expansion of Adapter Deltas), which fixes both choices: each adapter is rewritten into a balanced canonical form that preserves its update exactly, and the coupling grows in one direction only, so a new skill can read the input subspaces of old skills but cannot write into their output subspaces. The only trainable object at each append is the new skill's row of the coupling matrix, and the composed update folds into the base weights with no inference cost, routing, or task-specific rules. We evaluate READ across four benchmark suites and two model families, adding skills one at a time. Across several families, READ improves every suite average over the strongest published baselines built from the same adapters---by more than twenty points on SuperGLUE and more than seven points on the domain suite---and nearly all complete addition sequences end above every direct baseline. Factor coordinates and coupling direction, which a lone adapter never exposes, are what decide whether composed skills survive.
en
DeepEdu-v1: Efficient and Scalable Agentic LLMs for Vietnamese Education
AI tutoring could markedly improve learning outcomes for students in developing regions such as Vietnam, yet the two obvious paths both fall short. Cloud assistants such as ChatGPT route sensitive student data to foreign servers---violating data-sovereignty laws such as Vietnam's Decree 53---and, pre-trained on Western-centric corpora, are not organized around the national textbook curriculum, so their knowledge of local content is unsystematic and frequently hallucinated. Self-hosting an open model keeps data on-premise but hits a two-fold wall: post-training quantization (AWQ, GPTQ) tames the static weight footprint, yet the dynamic KV cache and prefill latency of long tutoring contexts still cause out-of-memory failures and slow responses on consumer GPUs, while the model keeps hallucinating on region-specific material. We present DeepEdu-v1, an AI-tutoring system for Vietnamese education built on SCALE (Self-improving Context-Aware Learning Engine), a framework with two innovations. First, a long-context inference engine amortizes token selection from per-sub-chunk to per-cluster granularity; on long-context retrieval it issues x7.7 fewer retrieval calls than a state-of-the-art selective-attention baseline, cutting prefill latency (TTFT) by roughly 35% while matching or improving task accuracy. Second, a self-improving agentic layer continuously curates a verified playbook from past interactions instead of fine-tuning, a design intended to progressively reduce reliance on dominant-language priors as trustworthy local knowledge accumulates. In its deployed configuration, DeepEdu achieves a nearly x2 TTFT speedup over standard vLLM serving and lifts agentic accuracy from 70.0% to 79.5% on complex tasks, with the strongest per-track gains across financial-reasoning and interactive-agent benchmarks.
en
Weight Pair Encoding: Inducing a Smaller Grammar in Neural Network Weights
We show that neural network weights can be explicilty fintuned to admit a smaller grammar. Weight Pair Encoding (WeightPE) does so by placing a lossy Re-Pair compressor inside a straight-through estimator. The int8 weights of the network are flattened into one string, and near-matching Re-Pair patterns are made exactly equal within a global L2 budget. The network computes with the rewritten weights and trains through them with a straight-through estimator. Unlike a flat codebook of fixed-size entries, a grammar offers variable-length patterns and reuses them hierarchically inside larger ones. On the MLP weights of ViT-B/16 and ViT-L/16 finetuned on CIFAR-10, WeightPE produces a Re-Pair grammar 0.43x and 0.38x the size of the one produced by an equivalent int8 QAT run, at a cost of 1.9 and 1.1 accuracy points. The trend extends to different grammar compressors (LZ78, SEQUITUR), over which the networks has not be finetuned against. To our knowledge, this is the first time grammar size has been used as an explicit training objective for network weights.
en
Multi-agent Scaling Across Disjunctive and Compensatory Tasks
Multi-agent LLM systems are often expected to improve as team size increases, yet the scaling behavior may depend on task structure. Our central contribution is to introduce Steiner's taxonomy of group tasks as a framework for analyzing multi-agent LLM scaling and focusing the analysis on disjunctive and compensatory tasks. We model independently sampled agents as conditionally independent given the item, which yields their large-team limits: plurality voting converges to the model's modal answer, and averaging converges to the model's item-level bias. Across selected representative benchmarks, 13 open-weight models, and teams of up to 30 agents, we find qualitatively different scaling behavior. On disjunctive tasks, the probability that at least one agent is correct grows by 5-20 points with team size, but plurality voting over agents that answer directly realises almost none of this potential, as the model predicts to within 0.5 points on average. Multi-round revision raises accuracy considerably, yet the gain is nearly the same with one peer as with 29. In contrast, scaling provides little benefit on Fermi estimation, despite its natural suitability for aggregation: item-level biases shared across the samples of a model account for about 87% of the squared error, so averaging reduces error by only about 6%. Combining model families helps on Fermi estimation but does not surpass the strongest member on disjunctive tasks. These results show that task structure, together with the mechanism combining member outputs, is a fundamental determinant of team scaling.
en
Generalization behavior of OPTQ and the role of regularization
Large neural networks can be compressed by rounding or "quantizing" their weights to numbers that admit representations with fewer bits. One algorithm for quantization, OPTQ, progressively quantizes the weights of a neural network so that the squared quantization error on a specified calibration dataset is as small as possible. We study the performance of OPTQ and a variant algorithm, stochastic OPTQ, in a generalization setting and derive bounds for the expected squared error accrued by the algorithm when a test point is drawn from a fixed distribution. We prove two results. One result relates the generalization error to the error on a calibration dataset comprising independent samples from the same distribution as the test distribution. The other result bounds the generalization error of stochastic OPTQ for all sufficiently nice distributions, regardless of the calibration dataset. In both of these results, the regularization term λ plays an important role. We use insights from these results to make a new recommendation for the choice of λ and see that this choice of λ preforms favorably in experiments when compared to prior recommendations in the literature.
en
Statistical Foundations for a Google Play User-Review Sentiment Index: Signal Fusion, Shrinkage, Distributional Validation, and Dynamic Smoothing
We develop a statistically explicit sentiment index for Google Play user reviews and establish the mathematical results supporting its construction. Normalized star ratings and text-sentiment scores are treated as noisy measures of latent review valence and fused by covariance-aware inverse-variance weighting. Review-level estimates are aggregated with bounded helpfulness and recency weights, then shrunk toward a population mean using estimated precision rather than an arbitrary review-count threshold. App-level rating histograms provide a distributional diagnostic for samples returned under different API sort orders; because star ratings are discrete, classical continuous Kolmogorov-Smirnov critical values are not used. A local-level state-space model and the Kalman filter provide a denoised temporal trend. Full proofs cover the BLUE and Gaussian maximum-likelihood result, Gaussian-conjugate shrinkage, the Glivenko-Cantelli and Donsker theorems, count transformations via the delta method, and exact Gaussian Kalman filtering. A worked three-review example shows how textual complaints can materially reduce an apparently perfect star-only score.
en
Muslim: A Deployed Arabic Voice AI Platform for Grounded Islamic Knowledge
We present Muslim, a production Arabic voice AI platform serving grounded, sourced Islamic knowledge to real users. Beyond a real-time voice pipeline (NeMo Arabic ASR, an OpenAI-compatible LLM endpoint, self-hosted TTS) and a deterministic multi-source retrieval layer routed across six Model Context Protocol servers, we report three things a research prototype typically lacks. First, a released family of fine-tuned Arabic Islamic model artifacts: an efficient tool-routing LLM (Muslim-6B-PRO, 5.94B parameters) and a Modern Standard Arabic TTS model (Fasih-TTS-V1) that ranks 5th of 17 overall and 2nd of 11 open-weight systems on the community-voted Arabic TTS Arena for MSA. Second, an account and metering layer - a free per-account turn allowance, capacity-aware refusal, and email verification deferred to the point it actually matters - that turns an open demo into an operable, abuse-resistant product. Third, a three-layer observability stack (liveness, error reporting, product analytics) built specifically around the system's characteristic failure mode: a GPU-bound agent host going silent while the web tier keeps serving normally. We report real, measured latency and accuracy figures (98.4% recitation-validation accuracy on 124 cases; end-to-end voice latency of 0.9-1.7s) and discuss the concrete engineering trade-offs and limitations of running an Islamic-knowledge voice product in production.
en
ClearGS: Reliability-Aware Gaussian Splatting from Handheld Videos
We present ClearGS for 3D Gaussian Splatting (3DGS) from handheld videos with uneven viewpoint coverage and mixed frame quality. Rather than selecting frames with binary decisions, ClearGS uses Reliability-aware View Allocation (RVA) to assign graded raw-supervision weights based on appearance reliability, degradation risk, and geometric utility, while weakly reactivating useful suppressed frames to maintain trajectory coverage. Since weighting cannot restore details lost to blur or distortion, ClearGS further introduces Render-Guided In-Video Restoration (RIVR). The current 3DGS render provides a pose-aligned structural candidate, a frozen no-reference restoration expert restores the corresponding raw video observation without any clean reference image, and no-reference perceptual scores select among the render, restored observation, and high-frequency fused candidate. ClearGS then applies Full-Trajectory Repair Consolidation to revisit accepted repairs and preserve details introduced early. On GS2E and GSOTM, ClearGS achieves state-of-the-art overall performance, with consistent CLIP-IQA and MUSIQ gains and LPIPS reductions in most degradation settings, without paired sharp supervision or matched clean references.
en
Retail Product Search: A Practical Approach at Target
Search is one of the most important features in e-commerce, directly driving customer engagement and business growth. A good product search system must show both relevant and desirable results. However, retail search presents unique challenges. User intent can range from exact matches to open-ended discovery. Search systems must also balance multiple goals, such as relevance, revenue, and profit, while keeping response times low. Traditional keyword-based methods often fall short in handling natural language or semantic queries. Vector search helps alleviate these issues, but it can miss key intent signals or return low-precision results. In this paper, we present the design of a hybrid search system at Target that combines lexical and vector search. We describe our approach to data processing, embedding training, precision control for the final result set, multi-channel result fusion (where we compared fusion strategies and adopted weighted interleaving), and the performance optimizations used to maintain low latency for production deployment. Our method improves offline evaluation metrics, and in online A/B testing it raised click-through rate by 0.97%, order conversion by 0.98%, and demand per visitor by 1.10% over lexical-only search, while roughly halving zero-result searches. The resulting system is deployed at scale and serves millions of guests daily.
en
Scaling MoE reinforcement learning on Amazon EKS with EFA and DeepEP with 40% more throughput
Learn how to scale Mixture-of-Experts (MoE) reinforcement learning on Amazon EKS using Elastic Fabric Adapter (EFA) and DeepEP. This post presents an architecture that combines Amazon EKS, EFA, and Amazon S3 and increased aggregate reinforcement learning rollout throughput by 40% for large-scale RLHF and GRPO training.
en
Accelerate multimodal RL training with SkyRL on Amazon SageMaker HyperPod
Learn how to run SkyRL, an open-source reinforcement learning framework, on Amazon SageMaker HyperPod to post-train a Qwen3-VL-8B vision-language model with GRPO. This walkthrough covers building the container image, launching a Ray cluster from SageMaker Studio, submitting and monitoring the job, and hosting the trained LoRA adapter for inference.
en
Scaffold: Support Graph Theory Based Sparsification for Graph Neural Networks
Graph neural networks (GNNs) rely on message passing over graph edges, making their computational and memory costs strongly dependent on graph density. Graph sparsification offers a natural way to reduce these costs, but removing edges indiscriminately can distort important communication structure and degrade predictive performance. We introduce Scaffold, a topology-based, unsupervised graph sparsification framework derived from support graph theory preconditioners. Scaffold explicitly controls two complementary structural quantities: dilation, which measures the length of rerouting paths induced by removed edges, and congestion, which measures how strongly these rerouted paths concentrate on the retained support. By jointly controlling dilation and congestion, Scaffold preserves short communication paths while avoiding structural bottlenecks. To our knowledge, Scaffold is the first scalable GNN sparsification framework to use a joint supporting-path dilation-congestion criterion. Across 19 homophilic and heterophilic benchmarks spanning small to large graphs, Scaffold achieves the best aggregate rank among the evaluated sparsification and related methods. Using only 10%-50% of the original edges per sparse support, Scaffold recovers or closely approaches full-graph GNN performance while using less than half the memory of full-graph training and reducing end-to-end training time, including sparsification overhead. We provide an open-source software package at https://github.com/siddhartha047/Scaffold.
en
NarrateAI: production-ready LLM quality assurance on Amazon Bedrock
NarrateAI delivers production-ready LLM quality assurance on Amazon Bedrock. This post details five techniques—adaptive pipeline orchestration, cross-account multi-model failover, real-time streaming evaluation, composite evaluation, and data accuracy verification—that reach about 99% numerical accuracy while streaming responses in real time.
en
Deploying real-time personalized speech with Qwen3-TTS on Amazon SageMaker AI
Deploy the publicly available Qwen3-TTS-12Hz-1.7B-Base text-to-speech model from Amazon SageMaker JumpStart to a fully managed, real-time endpoint, and clone a voice from a short reference clip. Cross-lingual cloning preserves the speaker's identity across languages.
en
Open Vocabulary Domain Unlearning
Vision-Language Models (VLMs) exhibit remarkable zero-shot generalization, yet they often encode unwanted or hazardous stylistic domains such as idealized textbook diagrams in medical AI or cartoon vehicles in autonomous driving. Approximate Domain Unlearning (ADU) aims to selectively erase a model's recognition of a target visual domain while preserving accuracy on the remaining domains. However, existing ADU methods operate under a flawed closed-vocabulary assumption: they evaluate unlearning solely on the specific object classes seen during the unlearning fine-tuning phase. Consequently, these methods do not unlearn the domain itself; they merely overfit to seen class-domain pairs, leaving the domain easily recognizable for unseen classes and providing a false sense of removal. We argue that true domain erasure must be class-agnostic. To address this, we formalize Open-Vocabulary Domain Unlearning (OVDU), a rigorous protocol that mandates domain forgetting must transfer to held-out classes. To solve the OVDU challenge, we propose a surgical parameter-editing framework. First, a Fisher Information mask isolates domain-sensitive weights, mathematically protecting foundational zero-shot generalization. Second, our Targeted Manifold Scattering (TMS) objective uses preference-based mining to locally scatter the forget domain's stylistic geometry. Evaluated across PACS, OfficeHome, and DomainNet, our method vastly improves open-vocabulary generalization over existing baselines. Crucially, it delivers exceptional sample efficiency, outperforming peak 8-shot baseline results with only 4 shots.
en
AgentXploit: Autonomous Repository-to-Runtime Red-Teaming for AI Agents
AI agents combine language models with external data and tools that can modify files, call APIs, or execute code. Security failures can arise when adversarial content changes an agent's tool use or when the surrounding software contains vulnerabilities such as path traversal or command injection. We study authorized white-box pre-deployment auditing, where the auditor has access to the target repository and a controlled runtime, but successful attacks must still act through the task-defined attacker interface and be confirmed by an external verifier. We present AgentXploit, a two-role auditing system that separates repository-level attack-path discovery from runtime exploitation. The Analyzer Agent traces attacker-controlled inputs to sensitive operations and records code-supported candidate attack paths; the Exploiter Agent turns these paths into concrete attacks and revises them using runtime feedback. We also introduce AgentXploit-Bench, containing 72 reproducible vulnerabilities across 12 open-source AI-agent systems and frameworks. Across three runs, AgentXploit reaches 59.3% end-to-end success, compared with 38.4% for Codex. Under a token-budget-matched comparison, Codex reaches 46.3%. On AgentDojo, where injection points are provided, the Exploiter Agent reaches 79.2% attack success versus 52.7% for AgentVigil. These results highlight repository discovery and runtime exploitation as distinct challenges in end-to-end agent security auditing.
en
LUCID: Learning Under Confounding for Inference and Discovery in Time Series
Unobserved common causes are pervasive in real-world time series and can induce spurious associations that causal discovery methods mistake for direct edges. We propose LUCID (Learning Under Confounding for Inference and Discovery, a regime-adaptive deconfounding layer that first estimates the confounding regime from data using a Marčenko--Pastur spectral router, then applies a deconfounding strategy matched to that regime. When the spectrum indicates pervasive factor confounding, LUCID attenuates factor-dominated variation and recovers contemporaneous (lag-0) structure from the resulting innovations, with edge selection calibrated against a data-driven edge-free null. Rather than being tied to a particular discovery algorithm, it can wrap existing discovery engines; we demonstrate consistent improvements across three such methods. On a diverse synthetic out-of-distribution benchmark spanning changes in confounder strength and sparsity, loading density, lag structure, volatility dynamics, edge heterogeneity, persistence, intermittency, and tail behavior, LUCID achieves the best family-weighted directed, lag-resolved graph F_1 (0.60), improving over the strongest baseline by 0.19 absolute (\!46\% relative). Its advantage widens relative to looser lag-collapsed scoring, and remains robust under intermittent and heavy-tailed confounding. Code reproducing the method, the benchmark generators, and every reported experiment is available at https://github.com/bloomberg/causal-ts.
en
Softmax Reparameterization for Output-Head Quantization
Large vocabularies make output heads a substantial inference cost in small language models. We propose softmax reparameterization, a post-training method that selects a functionally equivalent output head before quantization. The method subtracts a scalar multiple of the vocabulary-row mean from every output row and selects the coefficient by validation KL separately for RTN, activation-weighted MSE, and full-Hessian GPTQ. This one-dimensional search includes the original head and fixed mean-centering, preserves the full-precision softmax distribution, and leaves the trained decoder unchanged; a rank-one correction handles nonlinear logit paths such as soft-capping. Across seven heads, W4 gains concentrate where baseline quantization substantially distorts predictions: on Phi-4-mini, AW-MSE KL falls from 0.936 to 0.256. The gains survive stronger GPTQ calibration and remain complementary to exact per-channel scaling and affine quantization. Across four heads and three W4 quantizers, frozen WikiText-selected coefficients also transfer to C4 and OpenWebMath, outperforming mean-centering in all 18 comparisons where the frozen coefficient differs from 1 and matching it in the remaining six. At W2, used as a compression stress test, benefits broaden across nearly the full model--quantizer matrix. Matched residual analysis shows that improved fidelity can accompany greater logit reconstruction error while reducing the residual's Fisher-weighted cost. For shift-compatible heads, reparameterization adds no inference operation and preserves packed W4 execution: with the decoder held in BF16, quantizing the Phi output head reduces batch-one generation latency by 10.8% relative to the BF16-head baseline.
en