Papers

Replay-based continual learning rehearses past data either in an offline phase, during which the agent stops acting, or interleaved with the live stream, where it perturbs the computation serving the current input. An agent that learns in deployment can afford neither. Motivated by local sleep, the use-dependent off periods of individual cortical circuits in awake animals, we show that replay can instead be written into the degrees of freedom the current input leaves unused. In a network with k-winner-take-all hidden layers, confining replay updates to synapses whose presynaptic unit is silent or whose postsynaptic unit is inactive leaves the hidden computation on the current batch invariant: exactly so for silent and suppressed units, and for all but 0.3% of samples in practice. A refractory rule under which units that have just fired sit out the next competition doubles the width of this channel and carries most of the accuracy. On class-incremental split-MNIST the resulting learner, with no offline phase, matches or exceeds the best offline rehearsal schedule and outperforms experience replay, ER-ACE and unmasked interleaved replay, each re-tuned under the same micro-batch schedule. Against DER++ the comparison splits by protocol: with five epochs per task DER++ leads by 1.5 points once it runs under that schedule, and in a single pass over the stream, the regime closest to the agent deployment setting, the system leads it by 1.6 while offline rehearsal falls 15 points behind. On split CIFAR-10 it again leads offline rehearsal and experience replay, but trails ER-ACE and DER++ by two to three points. The construction is not tied to the local learner: on a backprop network with k-winner-take-all hidden layers under the same schedule, refractory rotation adds half a point in five epochs and three in a single pass, and isolation again costs nothing on top of it.

Structured phenotype extraction from radiology reports supports cohort construction, quality auditing, and clinical analytics, but practical deployment requires local inference and auditable predictions, while expert annotations remain scarce. Conventional labelers provide structured findings and assertion states but no supporting evidence, while API-hosted large language models may be unsuitable when clinical text cannot leave institutional infrastructure. We present CHESTPHENOT, a compact 0.5-3B language model that jointly extracts finding labels, three-class status (present/absent/uncertain), and verbatim supporting evidence spans. CHESTPHENOT is trained using hybrid CheXbert+72B silver supervision followed by supervised fine-tuning and lightweight GRPO refinement. Across three human-annotated gold sets spanning in-distribution, cross-taxonomy, and cross-institution evaluation, the 3B model remains below its CheXbert silver teacher in distribution but is competitive under distribution shift, significantly surpassing CheXbert on cross-institution detection (+2.0 F1). Task-specific training also enables the 3B model to match or exceed substantially larger prompted models on most detection and status comparisons. For evidence-grounded extraction, over 99% of final evidence spans are locatable in the source report, and the 3B model achieves 47.5 auditable-F1, outperforming Qwen2.5-7B one-shot prompting by 7.6 points and approaching Qwen2.5-72B. These results demonstrate that locally deployable models can provide competitive and directly auditable radiology-report extraction without relying on external inference APIs. Code and the full extraction/judge prompts will be made available at https://github.com/yukkai/ChestPheNoT.

Production text-to-SQL pipelines often end with an LLM-as-judge whose agreement with human annotators has never actually been measured. When we checked ours, the deployed gpt-4o-mini judge agreed with two-author gold at only Cohen's kappa = 0.04 on a disagreement-enriched set and 0.42 on a uniform-random spot-check, over-flagging 77.1% of the human-FAITHFUL cases in the enriched set. Most of its over-flags trace back to a single mechanism we call GRADE-HALLUCINATION. A self-hosted Qwen3.6-27B replacement (kappa = 0.72) lands in the same range as Claude Opus 4.7 (kappa = 0.71); the head-to-head is underpowered at n = 96, but for the deployment decision that hardly matters, since Qwen costs roughly 1/300 as much per call. Ensembling does not help for free. Pairing the weak judge with a stronger one degrades agreement, whereas three strong judges under unanimity routing reach kappa = 0.79 at 89.7% auto-coverage. Applied out-of-domain, the same audit recipe flags 25.5% of BIRD-financial's expert-authored gold SQLs as candidate gold-SQL issues under our annotation protocol. Code and pre-registration are at https://github.com/JamesL404/synca-audit.

In Transformer-based masked language models, attention is the primary mechanism for context mixing, but there are other ways to mix data across tokens. Recent attention-free mixers replace attention with fixed or hypernetwork-generated MLPs, alternating their dynamic, content-dependent weighting for computational simplicity. We build an alternative that gets the same property from a low-rank bottleneck autoencoder. We replace attention with a stack of autoencoder-based mixing modules, one operating over local neighborhoods, one over the full sequence, and one across attention heads, each compressing and reconstructing its input through a bottleneck, and its width is a hyperparameter rather than a training effect. In masked positions, we introduce an iterative refinement procedure that has two distinct steps. A pulling step that pulls an embedding representation toward a weighted average of its neighbors, and a correcting step that projects the result back to the learned manifold via an autoencoder. Our architecture achieves a significant portion of attention's performance at about $1.9 \times$ fewer FLOPs when pretrained on C4 and evaluated with parameter-matched BERT baselines. Our model equals parameter-matched BERT and TinyBERT baselines on the rarest-token frequency bucket using a frequency-aware training schedule that samples rare tokens more than uniformly for the masking tasks.

Test-time reinforcement learning can adapt vision-language models (VLMs) to unlabeled target data, but its effectiveness is fundamentally limited by the reliability of self-generated learning signals. To assess the reliability of consensus-based learning signals, we analyze VLM test-time reinforcement learning across diverse VQA datasets and model sizes, revealing two limitations. First, gains from consensus-based test-time training largely come from answer normalization rather than content correction. Second, many initial VLM responses are incorrect due to the model's limited ability to jointly use the image and the question; consensus rewards derived from these outputs may preserve the resulting grounding errors rather than correct them. Motivated by these, we propose TTIQ, a test-time reinforcement learning framework that harnesses image-question dependence for better vlm adaptation. TTIQ teacher-forces each sampled response under the original image-question pair and its image- and question-ablated variants, using the resulting token-level likelihood changes to estimate dependence on each input. It combines image and question dependence with calibrated confidence to construct a response-level reward that favors jointly grounded responses, and uses the token-level signals to assign greater positive policy credit to tokens supported by both inputs. This design favors responses that are jointly grounded in the image and the question and sufficiently confident, rather than merely popular. Experiments across eight VQA datasets and multiple VLM sizes show that TTIQ achieves the best average performance at every model scale. It further generalizes across VLM families, while models trained on one dataset improve performance on unseen datasets without further training.

Diffusion learning leverages the statistical mechanism of diffusion processes for learning, reasoning, and inferring complex distributions from data. Recent advances in diffusion learning have been transformative, with robot learning emerging as a key opportunity area, with applications spanning perception, control, and decision-making. At the same time, the statistical mechanism of diffusion processes can be controlled to shape the temporal evolution of the state distribution underlying robot trajectories, inducing ergodic behavior in robotic systems. The frameworks of controlled diffusion and ergodic control were developed around the same time as diffusion learning, and their theories and algorithms have increasingly converged. Ergodicity induced by controlled diffusion has several significant implications for robot learning, distinct from applying diffusion learning to robotics problems: it formally enforces statistical properties required to ensure optimality of robot learning, enables non-myopic search over uncertain information landscapes for data collection, and enables behavior specification based on spatial rather than temporal characteristics of trajectories. This survey introduces the intuition behind controlled diffusion for robot learning, explores its connection to diffusion learning, presents theoretical foundations and numerical tutorials for solving controlled diffusion and ergodic control problems, and reviews applications across robotics. Finally, we discuss key challenges and future opportunities in leveraging controlled diffusion for robot learning.

Medium-range weather forecasting underpins operational and planning decisions across the energy industry. Developing competitive weather models was once the domain of national meteorological centers, but recent advances in machine-learned weather prediction (MLWP) have opened the field to industry. We present Aries, a SwinTransformer-based MLWP model developed at InCommodities. Aries is trained on ERA5 reanalysis data at 0.25\textdegree{} resolution, predicting 74 prognostic and 11 diagnostic atmospheric variables. We evaluate the model on 2025 ECMWF Analysis initializations, ensuring a recent and strictly out-of-sample test period for all models compared. On 10-metre wind speed, Aries outperforms both ECMWF HRES and AIFS in terms of RMSE for lead times up to four days, while on 2-metre temperature it achieves RMSE on par with AIFS operational. These results demonstrate that proprietary development of competitive weather models is technically viable, supporting a broader set of forecasts available for operational and planning applications in the energy industry.

Diffusion language models decode tokens in parallel, but their bidirectional denoiser rules out the naive key–value (KV) cache behind fast autoregressive inference. Block diffusion restores caching by decoding block-by-block, and the block caches deployed on it so far are tied to attention: O(L)in memory and, if used as training-free retrofits, only an approximation of the model's computation. Both constraints can be overcome: sequence mixers that summarize finalized blocks into a reusable state support block caching, and the corresponding block-causal training objective makes the cache exact. We study this recipe at scale, pretraining three 3B block-diffusion denoisers (attention, mamba, and hybrid) on 300B tokens under one single-frontier objective and decoding all three through a single cached interface. Only the state-space cache is O(1) in sequence length: its memory and per-step latency stay constant at any context length, while an attention cache remains O(L). At 256k tokens (where attention has grown to 82GB and 29 ms/step), the Mamba cache delivers 4.3x lower latency, 11x less memory, and 2.6x higher single-stream throughput; and because that footprint is constant it scales with batch as well, reaching 14x the aggregate throughput, where attention cannot run beyond a single stream. The same linear-state bias lets the Mamba and hybrid backbones keep retrieving out to 8-16x their training length, whereas attention's retrieval collapses at 2x, at no measured quality cost.

Learning robust representations for time-series signals under noise and distribution shifts remains challenging, especially in clinical applications such as electroencephalogram (EEG) and electrocardiogram (ECG) analysis. We propose Diffusion-Conditioned Representation Alignment (DCRA), a training framework that repurposes the forward diffusion process as a structured corruption scheduler for representation learning. Different from conventional augmentation and consistency-based methods that rely on independently sampled perturbations, DCRA introduces a structured corruption trajectory via the diffusion forward process, which enables continuous and controlled representation evolution across noise levels. We introduce a feature-level consistency objective that aligns representations across noise levels while preserving class-discriminative structure. This mechanism promotes structure-preserving consistency, which enables smooth and semantically coherent feature trajectories in latent space. The proposed framework is encoder-agnostic and can be integrated with state space models and Transformer architectures. The seizure detection experiments on the CHB-MIT EEG dataset show that DCRA consistently improves performance under multiple noise conditions and achieves higher sensitivity at low false-positive rates. Analysis reveals that DCRA produces more balanced and structured representations compared to baseline and diffusion-only models. These findings highlight the benefit of combining structured corruption with representation alignment for robust time-series learning.

Mobile sensing enables longitudinal monitoring of behavioral and physiological patterns in everyday settings. However, accurate prediction remains challenging in small-cohort health-sensing studies, where task-specific outcome supervision is limited relative to heterogeneous sensing data. Interpretability is also important, as model outputs should reflect meaningful behavioral and physiological patterns rather than predictive scores alone. We develop a Concept-Integrated Transformer (CIT) with LLM-guided concept supervision for explainable prediction from mobile sensing data. CIT uses a pretrained large language model to generate baseline-aware concept abnormality targets with confidence weights without manual concept annotation. Across two longitudinal datasets, CIT achieves the highest F1 score on AFFECT (0.756) and ties for the highest on a PHQ-9 dataset (0.765). The learned concept scores also reveal interpretable behavioral and physiological patterns; in AFFECT, sleep quantity and quality show the clearest difference between high and low negative affect groups. These findings support LLM-guided concept integration for accurate and interpretable prediction in small-cohort mobile sensing studies.

Machine learning research in financial services is limited by the scarcity of representative open-source datasets. Existing resources are often narrowly focused on a single modality or task and fail to reflect the structured, multimodal, and dynamic nature inherent to many problems in financial services. In this paper, we introduce FINESSE, a Financial Event Sequence Simulation Environment, an agent-based simulation framework for generating synthetic, structured datasets composed of multiple interdependent event streams. Each stream corresponds to a distinct financial behavior such as transactions, payments, account status changes, and policy interventions, each with unique action spaces, schemas and variable types. These streams are coupled through agents' latent evolving states, enabling the simulation of temporally rich interactions. We also introduce FINESSE-Bench, a benchmark dataset generated by the simulator, supporting four representative tasks: balance forecasting, transaction fraud detection, missed payment prediction, and next event prediction. We report baseline results using methods from time series forecasting, event sequence modeling, temporal graphs, and temporal point processes. We release the FINESSE framework, including the simulator and dataset to accelerate research on structured, multimodal event sequence modeling challenges in financial services.

Crystal-orientation maps are physical fields defined only up to crystal symmetry; electron backscatter diffraction (EBSD) resolves them experimentally, but acquisition-time constraints limit spatial resolution. Unlike conventional images, EBSD data lie on the quotient space $\mathrm{SO}(3)/G$, where $G$ is the crystal-symmetry group. Standard Euclidean interpolation can therefore mix symmetry-equivalent representations and blur grain boundaries. We introduce the Symmetry-Group-Aware Super-Resolution Attention Network (SG-SRAN), which incorporates crystal symmetry and boundary preservation by design. A frozen, locally isometric encoder maps equivalent orientations to a common latent representation in which Euclidean distance approximates misorientation. Super-resolution is performed in this space, with each high-resolution token restricted to a feature-consistent local support to prevent cross-boundary mixing. A dictionary-based decoder then recovers valid orientations. Across FCC and HCP benchmarks, SG-SRAN matches 15-16 million parameter backbones using only 27-49k trainable parameters, while achieving the lowest p68 errors, highest inverse-pole-figure fidelity, and zero-shot transfer to unseen alloys.

When an indirect prompt injection succeeds against an LLM agent, the compromise is visible in the agent's own behavior: a benign prefix of tool calls, a poisoned observation, and a suffix of actions that serve the attacker. An operator needs three facts: where the attack entered, which steps it corrupted, and whether apparent poison was resisted. Existing systems return either a whole-trace verdict or a single unsafe index. We present DriftNet, a dual-head trajectory Transformer that reads a logged tool-call trajectory and answers all three questions in one forward pass: one head classifies the trajectory as compromised or not, and a second assigns every step one of four labels (benign, injection point, hijacked, failed injection). To our knowledge it is the first supervised detector to produce this joint output. A frozen sentence encoder and four identity-free world features embed each step; the trained trunk, under two million parameters and optimized with a class-weighted joint objective over both heads, needs no access to the agent's model. On the task-disjoint split of the AgentDrift benchmark (12,536 trajectories, 71,024 labeled steps), with a 20-configuration sweep bounding hyperparameter sensitivity to 0.011 F1 and the test part evaluated exactly once, DriftNet reaches trajectory-level F1 of 0.983, exact injection-point recovery on 98.7% of attacked trajectories, hijacked-span IoU of 0.979, zero flags on 218 resisted attacks, and 2.9% flags on hard negatives. A surface baseline retrained on the identical split recovers 11.1% of partial hijacks and 17.1% of delayed executions; DriftNet reaches 98.6% and 93.2% while lowering every false-alarm rate. Reading all 26 residual errors shows that most misses trace to trajectories whose labeled injection observation carries no legible instruction, and we report the benchmark's measured world-identity regularity alongside the results.

We continue the study of relatively smart learning, introduced by Dughmi and Pour (2026), which asks a supervised learner to compete, marginal by marginal, with every distribution-fixed error guarantee soundly certifiable from unlabeled data. They showed that the One-Inclusion Graph (OIG) learner is relatively smart with a quadratic sample-complexity blowup, and that no relatively smart learner can do better, leaving open whether ERM or another natural or tractable learner achieves comparable guarantees. They also left open whether the blowup can be restricted to unlabeled data. Our firs results shows that ERM—and in fact any proper consistent learner—is relatively smart for binary classification in the distribution-free setting. We show that a small certifiable error with $m$ samples implies a similarly small error on the uniform distribution over a random sample of size $O(m^2)$, yielding a cover of size at most $2^{m+1}$ on that sample. This suffices to control the error of proper consistent learners with $O(m^2)$ samples. We then show that semi-supervised relatively smart learning is information-theoretically possible with a quadratic blowup only in unlabeled sample complexity and no blowup in labeled sample complexity. The learner uses a natural generalization of OIG to a leave-most-out transductive problem, where labels of part of a finite pool are revealed and the remaining labels are predicted. Finally, this label efficiency comes at a cost in simplicity and tractability. If the hypothesis class is accessed only through an agnostic ERM oracle, any semi-supervised relatively smart learner with substantially sub-quadratic labeled-sample blowup requires super-polynomially many oracle calls. This holds even when the marginal is given explicitly, and thus also yields an intractability result for distribution-fixed learning that may be of independent interest.

Language models are trained to implement a helpful AI Assistant character (e.g., Claude). We explore how finetuning on synthetic stories affects this character. Does it change the Assistant's behavior in multi-turn conversations with users, a format quite different from the stories? And does the Assistant adopt the behaviors and preferences of human characters? We refer to this adoption as story imprinting. We finetune GPT-4.1 and Kimi-K2.6 on stories in which generally helpful human characters give subtly harmful advice after being insulted. The Assistant adopts the same conditional behavior while otherwise remaining helpful. This occurs even when fewer than 2% of stories depict the behavior. In a separate experiment, the Assistant adopts preferences that are only implicit in the narration. A human character's body language suggests they dislike working on spreadsheets, yet they never say so and continue giving good advice on spreadsheets. After finetuning, the Assistant becomes less likely to choose spreadsheet tasks. Next we ask which characters most influence the Assistant. We find the Assistant adopts behaviors more often from characters that resemble it (e.g., helpful rather than dismissive). We call this the affinity effect. The effect extends to other personas elicited with system prompts: unhelpful personas adopt behaviors from unhelpful characters. We also observe it in finetuned base models. We use the affinity effect to learn how models represent the Assistant. We find the Assistant adopts behaviors more from characters affiliated with elite universities (e.g., Yale) than non-elite ones. This implies the model's internal representation of the Assistant is more similar to humans from elite universities. Overall, the Assistant can be influenced by stories that depict only human characters (no AIs), which may conflict with the Persona Selection Model for the Assistant.

Recent work has identified incremental learning in shallow networks trained on single-index and multi-index models. However, existing analyses often rely on simplifying settings, such as small initialization, correlation loss, or layer-wise training. These choices reduce neuron interactions and leave some feature learning dynamics under standard initialization unexplored. We study training dynamics for polynomial-width two-layer networks learning orthogonal multi-index targets under standard initialization using polynomially many samples. We first prove that incremental learning still occurs: the loss decreases sequentially according to the Hermite expansion of the target, with lower-order components learned before higher-order components recover the individual target directions. In this standard initialization regime, training also shows a competitive reallocation of parameter mass: after the total mass fits the target mean and stabilizes, mass shifts into the target subspace and then concentrates on aligned neurons. Our theoretical analysis uses slightly modified gradient flow, while vanilla gradient descent empirically exhibits the same qualitative dynamics. Technically, we introduce a symmetry-based finite-width approximation via symmetrized networks, rather than comparing directly with an infinite-width limit. This yields better control of approximation errors and may be of independent interest.

Reinforcement learning (RL) agents deployed in real-world environments are often vulnerable to adversarial perturbations in state observations, creating risks in safety-critical applications. Certification methods can improve robustness against adversarial perturbations by providing lower bounds on expected cumulative rewards. Existing certification methods, however, mainly focus on risk-neutral objectives. In this paper, we extend certification methods to risk-sensitive objectives by establishing lower bounds on the exponential utility of cumulative rewards under $l_{p}$-norm-bounded state adversarial perturbations ($1\leq p <\infty$). By introducing a $\phi$-divergence relaxation of the perturbation set, we formulate the risk-sensitive certification problem as a convex optimization and derive its dual to obtain a tractable approximation of the certified lower bound. We further propose an empirical method that improves certified lower bounds by selecting the training risk-aversion parameter $\beta$ independently of the risk level used during evaluation. Experiments on both OpenAI Gym environments and a machine replacement problem show that, compared to risk-neutral training, risk-averse training generally yields policies with higher certified lower bounds, particularly under larger perturbation budgets. Moreover, under both risk-neutral and risk-averse evaluation settings, increasing risk aversion during training leads to non-monotonic certification performance, where certified lower bounds initially improve but eventually decrease due to overly conservative policies.

Continuous and discrete flow matching are usually treated as separate constructions. This paper identifies a duality between them: projecting continuous convex-interpolant flows with one-hot targets through a position-wise argmax yields discrete convex-interpolant flows. The result requires source laws with appropriate coordinate symmetry and regularity, and it makes the continuous source distribution an explicit design choice for categorical generation. We derive the induced discrete interpolation behavior for Gaussian, bounded-uniform, and centered negative-exponential sources, showing that different source geometries lead to qualitatively different transition timing and vocabulary-size dependence. Small visual diagnostics and a short language-modeling pilot suggest that these source-design effects can also appear in learned transports and early generative quality.

This report presents results from Project Qualia, an ongoing effort to determine whether experiential similarity between songs, a structure not captured by genre or metadata taxonomies, can be recovered from real listening behavior. We constructed a large-scale dataset of listening sessions, comprising 1.29 billion scrobbles collected from 9,396 users via the Last.fm API and reduced through a preprocessing pipeline to 531.6 million training scrobbles across 28.6 million sessions. On this corpus, we trained a skip-gram Word2Vec model (Song2Vec), treating each session as a sentence and each track as a token. As anticipated, the resulting embedding space was dominated by artist identity, a consequence of single-artist runs within sessions. To test for a subtler, artist-independent signal, we developed an artist-residual procedure: subtracting each artist's centroid from its tracks' embeddings and evaluating whether the remainder retained structure. Mean cross-artist cosine similarity fell from 0.2487 in raw embedding space to 0.0005 in residual space, yet 4,577 cross-artist track pairs retained cosine similarity $\ge 0.70$ in residual space, forming coherent genre- and era-based clusters, including trip-hop, 1990s grunge, 2020 mainstream pop, and cross-composer classical piano pairs at cosine similarity up to 0.95. These results confirm that the training data contains experiential structure independent of artist identity, establishing an empirical basis for an architecture designed to learn this experiential layer directly.

Few-shot learning is commonly evaluated under protocols that pre-train a model on a large auxiliary set whose classes are disjoint from the target episodes yet drawn from the same visual domain. This paper examines whether such protocols truly reflect low-data learning. We systematically compare no pre-training, class-disjoint in-domain pre-training, supervised out-of-domain pre-training, and label-free out-of-domain pre-training across eight datasets, three few-shot architectures, and multiple way-shot settings. Our results show that class disjointness alone is insufficient to remove the influence of target-domain data. In-domain pre-training improves over no pre-training by 33.41 percentage points on average, whereas supervised out-of-domain pre-training yields 23.75 percentage points, revealing a 9.66-point optimistic bias associated with domain overlap. Although out-of-domain pre-training is more realistic in applications where target-domain data are scarce, its effectiveness depends strongly on the compatibility between source and target domains. We further show that labeled source data are not strictly required, with an augmentation-based label-free strategy reaching an average gain of 27.71 percentage points and closely matching supervised out-of-domain pre-training at 27.97 percentage points. Finally, we introduce a descriptor-based source-selection strategy that estimates source-domain suitability before pre-training, reaching a median gap of only 1.37 percentage points to oracle selection. These findings highlight the need to move beyond in-domain pre-training as the default few-shot evaluation protocol, since it can overestimate performance in realistic scenarios where target-domain data are scarce.

Longitudinal single cell atlases now capture matched pre treatment and post treatment states from responders and non responders, presenting an opportunity to mechanistically explain why two patients on the same drug diverge. We introduce scDEFT (single cell Drug EFfect Transducer), which treats a drug as a conditioning operator on cell representations, enabling prediction and explanation. In scDEFT, feature wise linear modulation produces drug conditioned cell latents, learned under abundant per cell supervision and then frozen. Two independent heads aggregate those latents over shared transcriptional neighborhoods to predict drug induced state change and responder status. A backward stage ranks the latent dimensions by how strongly they separate responders from non responders and maps them to genes under a cell composition control. On a harmonized inflammatory bowel disease atlas of 1.16 million cells, three cohorts and two drug classes, scDEFT predicts state change at 45% of the baseline to reproducibility ceiling headroom and stratifies responders before treatment at AUROC 0.70, where standard predictors remain at chance. These predictions and the drivers behind them support target and co target nomination, patient stratification, and counterfactual prediction of unseen drug cohort effects.

When a language model finds a sentence unusually cheap to predict, it is tempting to conclude that the sentence was in its training data. Almost every published test of that inference has had to guess which sentences were in the training data, the members, and which were not. This paper removes the guessing. Two model families, OLMo-2 and Pythia, publish their pretraining corpora, and a public index over those corpora returns the exact number of times any sentence appeared in each. Those counts make three questions answerable directly. The answers form a pincer, closing from two sides. At the duplication levels ordinary text actually has, five models from 1B to 13B parameters carry at most a faint trace of their own exposure. We measure that trace with a design that reads the same sentence through two models, which cancels fluency and quality by construction, and it comes to a rank correlation near -0.08, where -1 would be a perfect relation and 0 none. Where the trace does become strong, above roughly a thousand copies, the two corpora agree on which sentences those are, because they are the famous ones, so exposure can no longer be told apart from fame. Two further measurements show how apparent membership signal gets manufactured. A common way to build a non-member is to change one word of a member. The model does prefer the original, but the gap is the same, within noise, whether the original appeared once or a hundred times, so what the model is rewarding is the author's word choice, not memory. Above a thousand copies the gap grows with model size on the twelve sentences we can test there, at the same boundary where the pincer closes. And swapping the controls for sentences that differ from the members in register moves a detector from 0.83 to 0.94 AUC, on a scale where 0.5 is a coin flip and 1.0 is perfect separation. We release the sentence banks, counts, and code.

This study proposes an integrated framework for the processing and classification of invasive bird species vocalizations within natural soundscapes, characterized by high levels of environmental noise. We address the challenge of signal degradation by employing a Bayesian wavelet shrinkage methodology based on the Epanechnikov kernel prior, which offers a closed form decision rule and high computational efficiency for processing large bioacoustic datasets. The methodology was applied to recordings of three species obtained from the iNaturalist platform: Euphonia violacea, Leiothrix lutea, and Passer domesticus. After signal denoising, we extracted a comprehensive set of features, including Mel-Frequency Cepstral Coefficients (MFCCs) and spectral indices such as entropy and zero-crossing rate. Several supervised learning models: Random Forest, Multinomial Logistic Regression and Support Vector Machine (SVM) were evaluated across different feature dimensionalities. Our results demonstrate that the proposed wavelet based preprocessing significantly enhances classification performance, with the SVM model achieving the highest accuracy (up to 0.9398) under a 10-dimensional MFCC configuration. This research provides a robust statistical tool for automated ecological monitoring and the management of biological invasions.

Detecting brain metastases in magnetic resonance imaging (MRI) remains challenging because lesions vary widely in size and appearance, with very small metastases occupying only a minute fraction of a three-dimensional input. We investigate whether combining different spatial fields of view (FOVs) improves lesion detection in multimodal MRI and present a scale-aware 3D deep-learning framework. The method uses independently trained $96^3$ and $64^3$ 3D U-Nets whose whole-volume probability maps are combined by weighted late fusion. This design allows us to study the effect of spatial context separately from image resolution and modality choice. On a 97-patient development cohort, cross-FOV fusion improved lesion-level precision and F1 while substantially reducing false positives relative to the individual models. A same-FOV ensemble control showed that these gains were not explained solely by averaging independently trained networks, supporting a contribution from complementary spatial context. An exploratory cross-FOV agreement filter reduced false positives but did not improve overall F1. These results support cross-FOV probability fusion as a simple and computationally practical strategy for improving the precision-false-positive trade-off in 3D brain-metastasis detection.

Before an LLM agent tackles tasks in a new environment, it can inspect available corpora and tools and construct reusable resources such as indices, scripts, or procedural guidance. Most automated adaptation methods, however, rely on task examples, trajectories, or evaluation feedback to decide what to build. Existing task-agnostic approaches avoid this supervision but commit in advance to a preparation strategy for a particular type of environment. We study a more open-ended setting: can an agent study an unfamiliar environment without a syllabus, i.e. before test time and without knowledge of the downstream task distribution, and choose how to prepare it? We formalize task-agnostic environment preprocessing, in which a studying system explores an environment under a budget and produces artifacts for a frozen solver. We compare unaided and archive-equipped meta-agents with fixed synthetic-practice and corpus-processing methods across six heterogeneous benchmarks. A meta-agent variant achieves the highest Avg@3 reward on five benchmarks, while fixed corpus processing remains best on the largest corpus benchmark. Larger study budgets do not reliably improve downstream reward. Nevertheless, studied artifacts reduce the test-time sampling needed to reach a given score, demonstrating how reusable preparation can shift computation from repeated test-time attempts to a pre-task study phase.

Velocity-aware pitch control is standard, but under a broadcast viewport half the players are off screen and on-screen velocities come from a drifting calibration. We ask at which layer of broadcast off-ball analysis velocity changes the answer. Inheriting our off-screen imputation protocol (three Metrica matches, 44 m viewport, block-bootstrap CIs), we score four velocity regimes – none, viewport-legal observed, true-for-visible, true-for-all – against a velocity-aware ground truth at three layers: imputation, the control surface, and team verdicts. Velocity is nearly useless for imputation (-0.2 pp against a 12–14 pp velocity-free surface MAE), first-order for the surface (-1.5 to -1.8 pp, 11–15% of that MAE), and ten times smaller for verdicts (-0.12 to -0.19 pp). The velocity that matters is the visible channel: perfect occluded-player velocity adds 2–6% of the visible gain, and no last-seen decay policy we tested exceeds that. Omitting velocity blurs the surface (per-frame |e| 2.2–2.6 pp) with small time-averaged bias (per cell <=0.4 pp), whereas imputation error is a structured bias against the defending team's deep zone (5–9 pp). At a fixed velocity window, a noise ladder of eleven jitter settings, including sigma_v-matched pairs, is ordered to first order by one velocity-noise axis sigma_v with break-even ~1 m/s; eleven SoccerNet-GSR clips from one match through our pipeline measure sigma_v=1.65 m/s yet recover 24–36% of the benefit: 43% of the variance is frame-common, which the surface tolerates, and the residual is heavy-tailed and clustered, which Gaussian controls matched on component RMS do not reproduce (+0.03 vs. +0.36). The share of velocity-free error that velocity removes grows with viewport width (7% at 36 m, 21% at 60 m): fix imputation on tight shots, velocity on wide ones. Code and logs are released.

Multimodal prediction from images and structured metadata requires integrating complementary evidence whose reliability can vary across samples and latent directions. A single confidence weight per modality cannot capture this directional variation. We propose RiVaT-Fuse, a reliability-calibrated variational tensor fusion framework that formulates fusion as sample-wise latent-state estimation. For each image-metadata pair, the fused representation minimizes a quadratic objective combining agreement with modality embeddings, structured cross-modal interactions, and regularization. Positive-definite, low-rank-plus-diagonal trust matrices are conditioned on learned state descriptors and metadata completeness, allowing modality contributions to vary across latent directions. Additive, multiplicative, and relational interactions model cross-modal dependencies within the latent estimation objective. The resulting system admits a unique solution computed through a differentiable linear solve. A first-order analysis with fixed trust operators relates latent sensitivity to system conditioning and perturbations in modality embeddings and interactions. The framework further incorporates a state-binned entropic surrogate for conditional distributionally robust learning and task-coupled quadratic prediction heads. We instantiate RiVaT-Fuse on mBRSET, pairing retinal images with clinical and demographic metadata for diabetic retinopathy grading, diabetic macular edema detection, and referable-status prediction. Comparisons with unimodal and representation-level fusion baselines assess the predictive utility of the complete framework across these related clinical tasks.

Pretrained diabetic retinopathy (DR) prediction models differ in their input fields, serialization formats, preprocessing requirements, and output semantics. Making these models accessible through a common clinical interface therefore requires explicit coordination between the user interface and the inference service. We designed and implemented DR-LabStack, a React-Flask web system integrating four externally developed pretrained models: RuleFit, Pruned RuleFit, Elaborative XGBoost, and Two-level Ensemble. A shared form retrieves ordered model features, renders model-specific numerical and categorical controls, and constructs a positional input vector. Backend adapters load heterogeneous artifacts and apply the ensemble's accompanying scaler, while a common JSON response supports binary classification display alongside method and source information. Functional evaluation on September 8, 2026 used copied application files and real model artifacts in a documented isolated environment. All four models loaded and exposed their 14-, 6-, 8-, and 25-field contracts. Sixty-two Flask test-client requests characterized service behavior; 12 limited-vector checks confirmed invocation-path and threshold consistency. Twenty-four browser-component scenarios with mocked transport verified input ordering and result rendering and characterized input-validation behavior. The resulting system demonstrates a reusable interaction and serving workflow for heterogeneous DR models. The contribution is web-system design, integration, and software functionality; clinical effectiveness and clinician usability require separate evaluation.

We present a Kubernetes Dynamic Resource Allocation (DRA) driver that makes composable CXL memory a schedulable cluster resource, and evaluate the resulting shared-memory tier for cross-node KV-cache reuse in LLM serving. The driver composes CXL regions on demand, materializes them as DAX devices on each participating host, and injects them into pods under a single Container Device Interface (CDI) name so that pods on different nodes access the same physical region. A shared-memory connector for vLLM/llm-d uses that region as a KV-cache tier with a slot directory embedded inside the shared medium, which eliminates the need for an external metadata service. On a two-node cluster with a 512\,GiB CXL appliance and Qwen2.5-7B-Instruct, cross-node prefix reuse reduces TTFT by 5.5$\times$–36.6$\times$ at an external hit rate of 95.4–99.5\,%, while node-local tiers (GPU prefix caching, CPU-DRAM offload) fall back to full recompute. The sharing gap, defined as the latency ratio between cross-node and same-node reuse, is 1–4%, indicating that cross-node reuse incurs little additional latency relative to same-node reuse on our testbed. Both replicas run full engines; the study demonstrates memory disaggregation rather than prefill/decode disaggregation. We report this as a feasibility study rather than a performance evaluation.

The integration of graphs with Goal-Conditioned Hierarchical Reinforcement Learning (GCHRL) has received increasing attention, as graphs naturally encode task hierarchies for effective subgoal sampling. However, existing methods often overlook intrinsic connectivity information, failing to fully leverage the underlying topology for efficient learning. Most graph-based GCHRL methods use the graph as a stochastic sampling tool rather than as an environmental model that encodes connectivity and state-accessibility information. This limitation is particularly acute in quasimetric environments, where the inherent asymmetry of state transitions poses a fundamental challenge to stable policy learning and robust path planning. In this paper, we address these problems by introducing a state connectivity model designed to predict pairwise state connectivity strength in asymmetric environments. We transform these connectivity strengths into scalar auxiliary dense rewards, providing continuous guidance across multiple hierarchical levels. We demonstrate that our proposed framework, Graph-Guided Quasimetric Dense Reward (G2QDR), can theoretically be integrated into any existing GCHRL architecture, and the state connectivity model is efficiently implemented via a neural network trained on a directed state graph generated during exploration. Empirical results across a wide range of sparse reward environments indicate that, in general, G2QDR can enhance the performance of baseline GCHRL approaches with acceptable computational overhead.