overfeed.news
Anuncio

SRExpert

Deja de saltar entre 6 herramientas de Kubernetes.

Monitoreo, alertas, seguridad, despliegues Helm y operaciones con IA en una sola plataforma.

Probar 30 días gratis

Tema

Código abierto

1633documentos

157últimos 7 días

arXiv AI Papers

Can KV Cache Be Reused Across Model Updates? A DeepSeek-V4-Flash Case Study

Reusing key--value (KV) caches across language model updates could avoid repeated computation of shared context, but changes in model weights raise a fundamental question about what these caches preserve. We investigate direct cache reuse across four model updates, with a detailed study of DeepSeek-V4-Flash to Flash-0731. Our central finding is that caches can retain useful task information without faithfully reproducing the updated model's behavior. Retrieval accuracy varies substantially across updates, ranging from near-native performance to large losses. With source caches already available, reuse achieves median time-to-first-token speedups of 2.10--5.08on three longer-prefix QA benchmarks. To characterize the behavioral differences behind these outcomes, we introduce Functional Cache Divergence, which compares next-token distributions under reused and native caches. Direct KV cache reuse better preserves native model behavior in natural-text continuation, whereas compatibility degrades with increasing prefix length in single-token retrieval tasks. Answer-margin analyses help explain how correct retrieval decisions survive substantial internal state changes. Yet even agreement on the first generated token does not ensure agreement in answer content or stopping behavior. These findings establish task utility and fidelity to native inference as distinct criteria for evaluating cross-version KV cache reuse.

en
arXiv AI Papers

RB-LDC: Redundancy-Balanced Latent Coding for Noise-Robust Diffusion Latents

Latent diffusion models decode approximately correct latents, making decoder sensitivity to perturbations relevant to image quality. After whitening, forward diffusion corrupts every direction at the same signal-to-noise ratio (SNR), despite unequal decoder sensitivities. We study an invertible linear layer between the encoder and diffusion process that shifts each direction's log-SNR. Its linear minimum mean-square-error (LMMSE) recovery risk has an exact spectral expression for any whitened latent distribution. Under an energy budget and a floor ensuring invertibility, minimizing decoder-sensitivity-weighted LMMSE risk integrated over the diffusion schedule yields a unique optimal allocation. The layer aligns with the decoder's expected pullback metric and equalizes marginal risk reduction across directions, computed by a deterministic spectral solver. At large budgets, the allocation follows a power law in sensitivity whose exponent is determined by the low-SNR tail of the loss weighting: one half for noise prediction and two thirds for data prediction under the cosine schedule, with a crossover on truncated schedules. We instantiate this principle as RB-LDC using Jacobian-based sensitivity estimates. On ImageNet at 256 x 256 resolution with SD-VAE and VA-VAE, trained RB-LDC improves reconstruction from noisy latents over budget-matched isotropic coding in all four metrics and five coding configurations, averaged over 15 SNRs and three pipeline seeds. It reduces average perturbed FID by 17.1 for VA-VAE block-local coding while preserving clean reconstruction. We also report intermediate SNRs where perturbed FID worsens. With a frozen diffusion model, RB-LDC yields lower FID point estimates in all 12 tested combinations of sampling progress and channel SNR under corruption during sampling.

en
arXiv AI Papers

Learning from First Discrepancies with Joint Reset and Pilot Guarantees

A run that stops at its first wrong decision shows the queries and their correct labels up to and including that decision, and nothing after it. We study how many such runs are needed for learning. Each run tests a hypothesis, the pilot, chosen beforehand from a fixed binary class of VC dimension at most d, on a fresh record of at most D queries drawn from one unknown distribution that does not depend on the pilot. The terminal information of a record is shown only if the pilot makes no discrepancy, and a bounded loss, fixed in advance, is attached to the position where a hypothesis stops. If the discrepancy probabilities of members of the class have infimum at most f and their risks have infimum at most r, one learner uses O((d+1)[D(f+)+r]/^2) runs and O(D(1+f/)) distinct pilots on every history. It returns a member of the class and an interval of width at most containing, with probability at least 1-δ, both the output's risk and the optimal risk. We also treat unknown ceilings and expected costs. Lower bounds for finite classes show that each order is necessary in the worst case, possibly on different instances, at positive dimension, small accuracy and fixed confidence. The learner enumerates label patterns of the class on displayed queries, possibly in exponential time; the results, under standard measurability conditions, concern statistical resources only. The proof combines a gain computable from stopped displays, exponential weights, a sparse depth-robust graph and a harmonic-mean bound.

en
arXiv AI Papers

Seeing the Small: Deformable Duality Mamba for Retinal Lesion Segmentation

Diabetic retinopathy (DR) lesions vary widely in shape, and microaneurysms (MAs) span only a few pixels. We hypothesize that modeling the spatial organization of lesion regions, with global context and shape-adaptive scanning, improves the segmentation of such small and irregular lesions. To test this, we propose D^2Mamba, which couples non-causal state space duality with deformable Mamba scanning. We evaluate it with five-fold cross-validation on the DDR dataset, comparing against representative segmentation baselines under an identical training protocol, and conduct ablations on each component. D^2Mamba achieved the best overall performance, with 33.87% mIoU, 2.99 percentage points above the strongest baseline. The largest gain appeared on MAs, the smallest and most easily missed lesions, where Dice improved by 10.06 percentage points. These results confirm our hypothesis that spatially adaptive state space modeling benefits tiny-lesion segmentation. Code and pretrained weights are available at https://github.com/PUREPANEL1/D2Mamba.

en
arXiv AI Papers

Distribution Shift Detection in Remote Sensing Imagery using Machine Learning Models

Remote sensing imagery acquired by Unmanned Aerial Vehicles (UAVs) supports wide range of applications; however, deploying machine learning (ML) models on resource-constrained aerial platforms introduces challenges beyond predictive accuracy, particularly when deployment data differ from the distributions observed during training. Such shifts are common in remote sensing due to geographic, sensor, seasonal, and other visual variations. A practical solution is to equip deployed models with mechanisms that detect emerging distribution shifts and support subsequent responsive actions. This paper presents an empirical case study of three open-source detection tools: (i) Alibi-Detect; (ii) NannyML; and (iii) PyTorch-OOD. Using cross-dataset remote-sensing shifts, we evaluate both detection effectiveness and computational latency of these tools. Our results reveal differences in detection behavior and processing cost across methods and implementations, highlighting trade-offs between detection capability and response-time. These findings motivate further work toward lightweight, and latency-aware monitoring mechanisms for resource-constrained systems.

en
arXiv AI Papers

Sharp Sample Complexity of KL-Regularized Reinforcement Learning

KL-regularized reinforcement learning, the objective behind maximum-entropy RL and RL from human feedback, is variational inference in the graphical model of "control as inference": the regularized optimal policy is a posterior over trajectories, and the suboptimality of a policy is β times a KL divergence between path measures. However, it is not known how many samples it takes to learn this posterior, even with a generative model. Earlier 1/ε guarantees scale with H^5 in the effective horizon H, and no lower bound for MDPs depends on the temperature β. In this work, we show that for a discounted MDP with K state-action pairs, the plug-in estimator finds a policy that is ε-optimal from every initial state with {O}(KH^3/(ε\{ε,β\}) + KH) samples, and that no algorithm, even one that chooses where to sample, can do with fewer when ε\{H, H^2/β\}. For ε< β this is a 1/ε rate with the same horizon dependence as unregularized RL. We also find the exact asymptotic constant of the plug-in estimator, a Fisher-weighted variance of the estimated soft Q-function. The estimator is locally asymptotically minimax among methods that sample every pair equally often, and we give the allocation of samples that is optimal among adaptive designs. Simulations on small MDPs match the rates and the constants.

en
arXiv AI Papers

SafeRoute-MAS: Coverage-Aware and Risk-Calibrated Message Routing for Multi-Agent Scientific Reasoning

We introduce SafeRoute-MAS, a coverage-aware, risk-calibrated procedure that keeps all specialist messages or removes one using only pre-integration information. On a sealed cache of 5,328 committees, its source-compatible operating point gains +1.80 percentage points (95% CI [+1.13, +2.52]) while removing 12.76% of message tokens. We also run 4,580 controlled integrations over a stratified 458-committee sample on a public gpt-oss-120b endpoint. The sample estimate is -0.09 points; design weighting to the original workload gives +0.94 points (95% CI [-1.31, +3.50]) and 18.72% acted-input reduction. A weighted token-matched comparison likewise does not establish a selector advantage (+1.68 points, CI [-1.27, +5.10]). Only 13 of 88 cached non-neutral labels (14.8%) retain direction by repeated-call majority. Expected-corruption UCL is 4.60% after weighting, but only 2 of 11 prespecified marginals pass the support/risk rule. We therefore propose a numerical qualification with Keep-All fallback, applied here retrospectively rather than validated prospectively.

en
arXiv AI Papers

SLIC: Reinforcement Fine-Tuning Small LMs for Multi-Turn Analog Circuit Optimization

Analog integrated circuit (IC) design is a multi-turn, simulator-grounded engineering task that demands iterative reasoning over coupled performance tradeoffs, yet proprietary process design kits (PDKs) make hosted large language model workflows difficult to deploy in practical design settings. We present SLIC (Small LM Iterating on Circuits), a reinforcement fine-tuning framework that trains a 4B-scale, locally deployable language model for closed-loop analog circuit optimization. SLIC pairs structured circuit representations with discretized relative-update actions, domain- and success-gated multiobjective rewards, and Reward-Guided Rollout Steering (RGRS), which turns per-step simulator feedback into signals for both policy learning and online rollout construction in this sparse, highly constrained domain. We further release an open, goal-conditioned benchmark of 41 amplifier topologies with standardized protocols for in-distribution validation, held-out topology evaluation, and cross-technology-node transfer. Trained solely with open source 65 nm CMOS predictive technology models (PTM), SLIC-Random achieves 87.1% in-distribution four-specification Pass@1 within eight turns, surpassing the 763B DeepSeek-V4.1-Flash Think by 48.5 percentage points. Beyond the training distribution, SLIC-Softmax reaches 72.6% Pass@1 on held-out topologies, and the trained policies consistently transfer across five unseen technology nodes without additional fine-tuning. This transfer extends to a commercial TSMC 65 nm CMOS PDK, where SLIC-Random achieves 49.9% held-out-topology Pass@1, demonstrating practical deployment through local inference without transmitting proprietary data to external LLM services. Performance further scales with test-time simulator interactions, reaching up to 83.2% held-out-topology Pass@1 at a 32-turn budget.

en
arXiv AI Papers

Fermat ProbCover: Coverage-Based Active Learning on Fermat Distance Graphs

Active learning aims to reduce annotation cost by selecting the most informative examples for labeling. In the low-budget regime, where uncertainty-based methods often fail, coverage-based active learning methods such as ProbCover have been shown to be effective. However, these methods typically rely on Euclidean distance, which may not adequately capture the underlying geometry of data. In this article, we propose PC-Fermat, a coverage-based active learning method that replaces Euclidean coverage neighborhoods with neighborhoods defined by a Fermat distance, i.e., a data-adaptive distance that reflects the underlying distribution of the data points. To facilitate computation, we construct a weighted Euclidean neighborhood graph and use a truncated shortest-path algorithm to compute the Fermat coverage graph. We also establish sufficient conditions under which this construction exactly preserves the Fermat coverage computed on the complete graph. Finally, we evaluate PC-Fermat on eight classification datasets across varying labeling budgets, with particular emphasis on the very low-budget regime. Our experimental results demonstrate that PC-Fermat outperforms several existing active learning methods on the majority of the datasets.

en
arXiv AI Papers

Inherited Weights: Measuring the Tokenization Premium and the Sovereignty Cost of Language Models for the Global South

Most language models deployed outside the United States and China are fine-tuned descendants of a small number of pretrained families. We argue that fine-tuning leaves the decisive properties of a model inherited from its base: vocabulary, knowledge, cultural alignment, memorized data and license. We contribute (i) an updated, reproducible measurement of the tokenization premium across 31 languages and 7 tokenizers released in 2023-2024, on 27 articles of the Universal Declaration of Human Rights, with explicit correction for unknown-token collapse. Premiums reach 10x for Amharic in older tokenizers and remain at 6.8x in the newest commercial one; Indigenous South American languages pay between 1.6x and 2.7x under global tokenizers. A vocabulary built from Portuguese lowers the premium for 11 of 13 Latin-script Global South languages relative to every global tokenizer tested, by about 24% for Guarani and Quechua. (ii) An eight-test black-box sovereignty audit that a buyer can run without access to weights. (iii) A regime argument: under energy and liability constraints, accuracy per joule, calibration and selective risk should replace raw accuracy as design objectives, with metrics that abstention cannot inflate. We close with preliminary internal measurements from a proprietary architecture built around these objectives, reported with their limitations. Data and measurement code are included.

en
Apple Machine Learning Research

Weighted State Souping for Efficient Long-Context Retrieval

This paper was accepted at the Workshop on Personalized, Aligned, Long-term Memory for AI Systems (PALM) at NeurIPS 2026. State space models (SSMs) combine fast inference and fixed state size with competitive language-modeling performance. Recently, state souping has been proposed as a procedure whereby an SSM independently encodes chunks of tokens like documents, tool definitions, or memory records. The resulting…

en
arXiv AI Papers

When Are Predictions Enough? An Evaluation Protocol for Frozen Expert Composition

Practitioners often combine independently trained models while keeping their weights frozen. These experts are commonly combined through their final predictions, although their internal features may retain useful information that those predictions omit. We ask when combining features improves on combining predictions, and how to make that comparison fair. We introduce a reusable evaluation protocol, apply it to 21 frozen deepfake detectors from DF40 (Yan et al., 2024), and audit how evaluation choices change the conclusions. The protocol uses strong prediction baselines, compares simple and larger feature combiners, varies architecture and training data separately, and reports results by held-out generator with train/test overlap controls. Under leave-one-generator-out evaluation, logistic regression on the features of six architecture-diverse experts improves macro AUROC by 0.081 over the best tested prediction combiner in each fold, with gains on seven of eight generators. The larger network shows no clear improvement over the linear model (approximately 3.5M versus 10K parameters), suggesting that access to richer information matters more than additional combiner capacity on this pool. Features may help when they retain information that the predictions omit and that transfers to new generators. Predictions may be enough when the strongest prediction baseline already performs well, while neither approach reliably compensates for poor expert transfer. Weakening prediction baselines on the overlap-affected standard split inflates the apparent feature advantage by up to 0.172 AUROC. Overlap-aware evaluation also changes the estimated gain, though the contrast does not isolate overlap. Results by generator and expert pool show where the advantage holds, weakens, or reverses. Without these controls, the same benchmark can support different conclusions.

en
AWS Machine Learning Blog

Introducing Claude Fable 5.2 on AWS

Claude Fable 5.2 and Claude Mythos 5.2 are now available on Amazon Bedrock and Claude Platform on AWS. Learn what's new in both models, why Fable 5.2 matters for your technical workloads, and how to get started building with it on Amazon Bedrock.

en
Código abierto — overfeed.news