Papers

When a multimodal AI agent is asked to forget a fact, current memory systems usually delete the text entry and report success. We find that the fact can remain recoverable from retained user images, including images tagged to entirely different facts, because VLMs use implicit visual cues at inference time. We introduce the Information Provenance Graph (IPG), a taxonomy that classifies memory representations by deletion affordance. The IPG reveals that deletion fails through multiple channels. Our benchmark, MemLeak, measures this across a deletion cascade: direct probing of deletion-capable systems yields <1%, but retained correlated text enables 18.3% recovery, and retained images enable 12.0% recovery (0.0% blind baseline, 0.3% FPR) – with 47% of image leaks not text-recoverable. Content-aware semantic deletion reduces the image residual to 2.0%. The residual appears across multiple VLMs, a production memory system, and real Unsplash-licensed photographs. Dual-annotator human validation (kappa = 0.88) confirms judge reliability.

Nuclear Magnetic Resonance (NMR) spectroscopy is the gold standard for molecular structure elucidation, yet interpreting complex spectra for unknown molecules remains a bottleneck reliant on human expertise. While artificial intelligence has advanced this field, current methods face a critical trade-off: database retrieval cannot identify novel scaffolds, while de novo molecular structure elucidation models operate as black boxes, lacking the atom-level interpretability required for rigorous scientific validation. Here, we present NMRAgent, an evidential reasoning agent powered by large language models (LLMs) that bridges this gap by integrating specialized spectral analysis tools with chemical knowledge graphs. Unlike previous approaches, NMRAgent mimics the deductive reasoning of human experts: it takes experimental NMR spectra and molecular formula as input, plans the elucidation process, proposes candidate structures, verifies peak-atom consistency, and refines misaligned substructure through formula-aware fragment optimization. Enabled by its evidential reasoning, NMRAgent outperforms state-of-the-art methods, improving top-1 accuracy by 46.5% and Tanimoto similarity by 0.502 on a scaffold-split benchmark with novel scaffolds in the test set. Besides, we demonstrate the agent's practical utility by elucidating the structures of two previously unknown natural products isolated from Hydrangea davidii and Vitex trifolia, and by correcting structural misassignments in established literature. By combining high-accuracy prediction with transparent and evidence-based reasoning, NMRAgent establishes a new paradigm for interpretable AI in analytical chemistry.

Graphs are widely used to model relational systems, with applications in domains such as social networks, finance, and biomedicine. Graph neural networks (GNNs) have become a mainstream approach for learning graph representations. With the rise of large language models (LLMs), recent studies have attempted to combine GNNs with LLMs. However, most existing works concentrate on node-level and edge-level tasks, while graph-level tasks, which require capturing more complex structural and feature information, remain relatively underexplored. Moreover, graph pretraining is a widely adopted strategy to alleviate the challenge of label scarcity. Most existing approaches are designed solely for GNNs such as GraphCL, leaving LLMs uninvolved in the process. To address these limitations, we propose GLIP, a Graph-LLM JoInt Pretraining framework for graph-level tasks. GLIP first performs graph augmentation to construct positive and negative pairs and introduces a multi-token selection strategy to identify patches informative in both structure and features. It further leverages a diffusion-based projector to enrich them with contextual information, enabling GLIP to capture signals from both global and local perspectives. Finally, GLIP employs a joint objective that integrates the LLM's semantic judgments with a contrastive alignment loss, ensuring consistent supervision at both the semantic and structural levels. After pretraining, GLIP is fine-tuned with limited labeled data for downstream tasks, and extensive experiments show that it outperforms state-of-the-art methods on graph-level classification and reasoning tasks. Our source code is publicly available at https://anonymous.4open.science/r/GLIP.

LLM agents are increasingly cast as autonomous portfolio managers, yet the dominant evaluation idiom, a leaderboard of returns over a fixed window, certifies neither the soundness of an agent's process nor the durability of its edge: one period's return is dominated by the market path, and apparent alpha can dissolve once look-ahead bias and trading costs are controlled. We introduce CLQT, a closed-loop benchmark that reframes LLM trading evaluation as diagnosis rather than ranking. CLQT enforces point-in-time data access through a hard TimeGate, models institutional transaction and financing costs, scores strategy consistency across rounds, and seals every gather-analyze-decide-execute-reflect cycle into a recompute-verifiable audit chain; the same model runs as a constrained investment committee or a single autonomous orchestrator, making scaffolding an experimental variable. From the audit trail CLQT computes a five-axis capability scorecard (Coherence, Acuity, Composure, Discipline, Reliability), with coherence scored partly by a held-out LLM judge to curb self-preference bias. We validate CLQT on a contamination-controlled, year-long multi-model backtest campaign with a 13-configuration ablation grid and a four-week live broker paper-trading track on post-cutoff data. The diagnosis-first read shows that the capability leader is not the Sharpe leader; that agents' allocations systematically fail to follow their own stated analysis, a stating-versus-doing gap stable across both tracks (+0.30 backtest, +0.23 live); and that module value registers on the capability and behavioral axes when returns alone cannot separate it. Net of realistic costs, agents clear defensive baselines but do not cleanly beat the index. Credible evaluation of LLM investment agents must therefore diagnose the process rather than rank a period's return, the standard CLQT operationalizes and makes auditable.

Reinforcement Learning from Human Feedback (RLHF) for Large Language Models increasingly relies on critic-free methods as a practical alternative to actor–critic training. Despite their simplicity, existing critic-free approaches propagate a trajectory-level learning signal uniformly across all tokens in a trajectory. This requires full-trajectory policy updates for every rollout, leading to substantial optimization cost for long reasoning traces, even though intermediate prefixes often contain enough information to largely determine the final outcome. We propose Prefix-Sampling Proximal Policy Optimization (PS-PPO), a compute-efficient critic-free method for RLHF that exploits this temporal redundancy. PS-PPO introduces a prompt-conditioned cutoff distribution and samples a cutoff timestep for each trajectory. During the update pass, PS-PPO backpropagates only through the sampled prefix of each trajectory and applies an importance-weighting correction so that the resulting truncated gradient estimator remains unbiased with respect to the full-trajectory objective. Experiments on mathematical reasoning and RLHF benchmarks show that PS-PPO achieves large reductions in training compute and peak GPU memory, while maintaining accuracy comparable to strong critic-free baselines.

The application of graph data in numerous disciplines raises the need for gathering and analyzing huge volumes of data, some of which is private and sensitive. The non-Euclidean nature of the graph data makes the analysis computationally challenging, leading to the use of Graph Neural Networks (GNNs) in the age of AI. GNNs may inadvertently leak sensitive data they are trained on, which raises serious data security issues, including the model inversion attack. In this study, we analyze GNNs' vulnerabilities by introducing two novel graph inversion (i.e., reconstruction) attacks: graph-label conditioned (GLC) attack and embedding-label conditioned (ELC) attack, utilizing targetmodel predictions and their intermediate representations, respectively. We perform a comprehensive analysis of our introduced privacy attacks and compare them with existing baselines across three benchmark graph datasets (i.e., NCI1, PROTEINS, and AIDS) and four graph distributional/structural metrics (i.e., FGD, EGD, MMD, and GKS). Our work demonstrates that an adversary can use the generator-discriminator technique to reconstruct high-quality graphs in real-world black-box attack scenarios against GNNs. Additionally, we present a variant of our attacks (Ours–) with 50% reduced queries, achieving good or comparable reconstruction attack performance. In addition, we show that GNNs are highly vulnerable to privacy attacks, varying Laplacian noise-scales.

Organizations that cannot send data to a cloud API need to know how well self-hosted open-weight models perform on Text-to-SQL and which inexpensive techniques justify their compute. We benchmark Qwen2.5-Coder-Instruct (7B, 14B, 32B) and CodeLlama-Instruct (7B, 13B) self-hosted at 16-bit precision, Llama-3.1-8B and Llama-3.3-70B through an FP8 API, and Qwen2.5-Coder-32B through a second API on the BIRD development split (n = 1534), with one zero-shot prompt and the official execution-accuracy comparison on read-only databases. We ablate lexical and embedding schema linking, execution-guided self-correction and self-consistency, and test every within-model recipe difference with exact McNemar tests, Holm correction over 30 tests and a database-clustered bootstrap. Qwen2.5-Coder reaches 42.6%, 52.0% and 54.9%; CodeLlama-7B and -13B reach 23.7% and 26.3%. Self-correction is the only component with a consistent gain: within a run it adds 1.2 to 4.4 points at 1.1 to 1.9 times the tokens, and it is significant after Holm correction for every model except Llama-3.3-70B. Schema linking never helps significantly; lexical linking costs Llama-3.3-70B 4.2 points, and an embedding linker with higher table recall does not differ detectably from no linking. Self-consistency, run for one model, changed accuracy by at most 0.13 points at about five times the tokens. One API provider dropped spaces next to digits; after a whitespace repair the same model scored 54.5% through the API and 54.9% self-hosted, so an apparent three-point serving gap was mostly this defect. This version corrects six defects of v1, including writable databases, a stricter-than-official metric and a truncated API arm, and withdraws the v1 claim of a quantization penalty of about 13 points; all numbers are re-scored or re-run. Code, per-item predictions and analysis scripts are released.

In this paper, we formulate a new vehicle dispatch optimization problem, called Nursing Care Taxi Dispatch, as a variant of the Vehicle Routing Problem, considering constraints related to wheelchair use, user compatibility, pick-up and drop-off times, and vehicle limitations. Previous neural-based methods for Vehicle Routing Problems have typically addressed a few simple constraints, while our new problem involves multiple complex constraints, resulting in having fewer destinations to select. This complexity makes it more difficult to obtain solutions that allow all nodes to be visited with a limited number of vehicles. To balance low violation rate, computational efficiency, and solution quality, we propose a supervised machine learning approach based on the Transformer architecture. We first obtain a set of high-quality solutions using an integer linear programming solver for given inputs and then train our learning model through supervised learning. Additionally, we introduce the post-processing of the paths generated by the learning model, ensuring that all constraints are satisfied. We compared each instance's objective function value (operating time), execution time, and constraint violation rate across different methods: our proposed method and some existing methods including integer linear programming and machine learning-based methods, using real-world facility data. Our method successfully produced balanced solutions regarding operating time, execution time, and constraint violation rate. Notably, we observed a decrease in the operating time for all problem sizes and regions, while keeping constraint violations to a minimum compared to existing methods. Especially, the decrease reached up to 8% for problem sizes with fewer than 30 users.

Normalizing flows are powerful generative models that learn an invertible mapping between complex data distributions and simple latent distributions, typically a standard normal density. However, this choice of latent density can impose unnecessary complexity on the learned flow transformation due to the topological mismatch between the latent and data densities, leading to slower training and suboptimal performance. In this work, we propose using mixtures of probabilistic principal component analyzers (MPPCA) as the latent density for normalizing flows. We simplify the learned flow transformation by learning a latent distribution that more closely aligns with the data distribution in terms of KL divergence, thus enabling faster convergence and improved generative performance. Critically, MPPCA models can be fit quickly and cheaply using the expectation-maximization algorithm, making them a practical choice for initializing latent distributions even in high-dimensional generative tasks. We validate our method on both tabular and image datasets, demonstrating consistent gains in training efficiency and generation quality compared to baselines.

Continuous physical fields represent a large fraction of data under scientific investigation. Their multiscale structures are central to discovery, yet useful coordinates are not known in advance. Standard self-supervised methods define context and targets in fixed image coordinates, posing a predictive task misaligned with fields organized across a continuous scale hierarchy. We introduce ScaleAware-JEPA, a framework that constructs dense, label-free latent coordinates for continuous scalar fields. Constrained Diffusion Decomposition (CDD) separates each field into pixel-registered scale components and provides the scale coordinates that define the masking geometry. The resulting JEPA objective predicts hidden structure with a context footprint tied to the diffusion scale of each component rather than to an arbitrary patch size. Across MHD turbulence, interstellar molecular gas and urban nighttime-light structure, the learned geometry maps back to coherent morphology, forming dense structural atlases without labels or predefined segmentation rules. By tying latent prediction to the scale hierarchy of a field, ScaleAware-JEPA constructs latent coordinates through which complex physical patterns can be inspected before their relevant structures have been prescribed. Code is available at https://github.com/gxli/SA-JEPA.

Maritime anomaly detection is essential for ensuring maritime safety, security, and efficient traffic management at sea, with Automatic Identification System (AIS) data serving as a primary data source. Despite its importance, most publicly available AIS datasets lack predefined anomaly labels, forcing prior studies to rely on either distribution-based rarity or domain rule/expert-assisted labeling. These approaches, however, face fundamental limitations: statistical rarity often fails to reflect practically critical events, while expert-based labeling is costly, subjective, and difficult to scale. Moreover, both paradigms tend to overlook interaction-driven hazards such as near-miss approaches between vessels. To address these challenges, we propose an equation-grounded anomaly taxonomy that is implementable under a limited AIS observation schema and extensible to other AIS datasets. Specifically, the taxonomy defines three anomaly types: unexpected AIS activity (A1), route deviation (A2), and close approach (A3), covering both single-vessel and inter-vessel anomalies. Building on this taxonomy, we introduce a unified score-synthesize-label pipeline that produces LLM-guided plausibility scores, uses them to synthesize anomalies, and assigns timestamp-level labels. To rigorously assess detection performance, we further design benchmark evaluation settings that account for variations in temporal-window length and anomaly-type composition, and evaluate a broad range of time-series models and anomaly detection models. Together, these contributions provide a systematic basis for evaluating maritime anomaly detection methods across different anomaly types. Our code is available at https://github.com/snudial/open-maritime-anomaly-detection.

Resampling methods such as SMOTE and random under/over-sampling are standard tools for class-imbalanced classification, almost always evaluated by minority-class accuracy or F1. Prior work has established that undersampling degrades probability calibration by distorting the training prior [1]. We extend this lens to synthetic oversampling (SMOTE) and provide a practical, evidence-based guide to when calibration damage matters and how to fix it. Across five public datasets (imbalance ratio 1.9-70) and two ensemble models (random forest, gradient boosting), with ten seeds and paired statistics, we find: (1) SMOTE's calibration cost is real but small (ECE +0.009; Cliff's delta = +0.27, small-to-moderate) across the studied imbalance range (IR 1.9-70) and its discrimination gains typically outweigh the calibration penalty; (2) random undersampling is the genuine danger – its damage grows sharply with imbalance, inflating ECE from 0.008 to 0.395 on a dataset with ratio 70, largely because the resulting training sets are too small to estimate probabilities reliably; (3) a single post-hoc recalibration step (Platt or isotonic) eliminates the damage, reducing ECE by up to 66% at a negligible ranking-power cost (AUC -0.002, Cliff's delta = -0.07); and (4) the analytic prior-shift correction that repairs undersampling does not transfer to SMOTE, because SMOTE distorts the class-conditional density rather than only the prior – so data-driven recalibration remains necessary. We recommend that imbalanced-learning studies report calibration alongside discrimination, and that practitioners recalibrate after resampling whenever predicted probabilities drive decisions.

Measurements of proprietary LLM evaluators can become invalid within weeks – we document one case and provide the diagnostic framework to detect it. We introduce EPC – comprising the Multimodal Preference Collapse Index (MPCI), evaluator-indexed coupling matrix, and Jensen-Shannon divergence (JSD) – and apply it across eight experimental conditions (N=112 main + N=10 ablation = 122 unique repetitions, all reported). Coupling coefficients range from 0.00 to 1.18 across per-condition means (CV approx 0.9, n=8 conditions). Four conditions show strong coupling (N=36; GPT-4o May, GPT-4o-mini, Qwen3.7-plus, DashScope 30r); four collapse to near-zero (N=76; GPT-4o June, qwen-plus N=30, symmetric LR, DeepSeek self-eval). The May-to-June GPT-4o drift – an N=8 re-replication inverting the study's conclusion – is the most informative measurement: a diagnostic instrument detecting its own instability demonstrates the fragility it was designed to measure. Self-evaluation (97% zero, JSD=0.003) consistently collapses, though floor effects are possible. Output-format confound analysis finds per-strategy aggregate rho=0.89 but per-instance rho=0.219 (p=0.093); PCI reported as preference-convergence metric. We release EPC with all data. The finding is not any single coupling magnitude but the pattern of version-conditional instability that makes single-snapshot evaluator studies unreliable.

Predicting a material's properties from its structure is a central, fast-advancing problem in computational materials science. A decade of work has produced standard public benchmarks and many published machine-learning models for the task (Dunn et al., 2020). The task's fixed metric and these baselines make it a natural setting for autonomous agent research (Karpathy, 2026). On the MatBench band-gap benchmark ($>$100k crystals), a general-purpose coding agent autonomously built the most accurate model trained without external pretraining, ahead of all seventeen expert-designed models reported for the task. A closer analysis shows it reached this by implementing known methods: either already standard in crystal neural-network models, or borrowed from other areas of machine learning. The contributing implementations include element-pair features on each message-passing edge and a crystal space-group embedding. The work not only demonstrates that LLM-agent autonomous research can optimize an expert-designed machine learning model for material property prediction, but also investigates the limitations of such autonomous research.

Hallucination is the reliability bottleneck for LLM-based agents, and fact attribution verifiers are the last line of defense – yet today's verifiers emit only opaque binary labels, leaving agents unable to self-correct and operators unable to audit. We present SEVA, a structured verification agent that emits evidence alignments, step-by-step reasoning chains, calibrated confidence, and a six-category error diagnosis with actionable fixes. Training such an agent with RL is non-trivial: standard binary reward on multi-component output triggers advantage collapse – within-group reward variance vanishes and the GRPO gradient disappears. We resolve this with a process reward that decomposes verification quality into five independent components weighted 70/30 toward process signals, restoring the gradient and inducing an implicit curriculum – the agent first masters verification behavior (alignment 0.917 -> 0.997, format 72% -> 100%), then outcomes (F1 64.9 -> 69.0). Structured output further enables a Verify -> Reflect -> Probe -> Refine self-evolution loop, which over four rounds on a 7B model surfaces an unexpected structural finding: each round produces a benchmark-specialist, not a generalist (+15 pp on HaluEval, -10 to -14 pp on TruthfulQA in the same model, persistent at 4x data). On ClearFacts, SEVA-3B matches GPT-4o-mini (69.0 vs. 69.8 F1) while producing substantially richer, auditable output – confirming a principle that should generalize: for any RL task with multi-component generation, reward granularity must match output granularity.

Telecom question answering (QA) is a challenging setting for retrieval-augmented generation (RAG): evidence is fragmented across standards, papers, encyclopedic resources, and web documents, and answers often hinge on technical tables, equations, and specialized protocol language. In low-resource subdomains, generator fine-tuning can over-specialize and degrade general capability, making query-side retriever adaptation an attractive alternative. To this end, we ask whether a fixed-generator, query-adapted RAG system can outperform generator-side adaptation, and which retriever objectives best support that setting. We motivate retrieval, rather than generator fine-tuning, as the adaptation target through a capacity comparison: under bounded-parameter and soft-retrieval assumptions, query-encoder tuning can have a smaller estimation term than supervised fine-tuning when its effective dimension is smaller. We identify two particularly relevant objectives – the latent-document RAG likelihood, which optimizes generation utility, and the InfoNCE contrastive objective, which improves semantic retrieval geometry – and leverage them jointly through a retriever optimization method targeting downstream QA performance in the telecom domain. Specifically, we introduce ARMOR, Adaptive Regularized Mixture Optimization for Retrievers, which learns separate temperatures for the RAG retrieval distribution and InfoNCE softmax and regularizes the adapted query encoder toward the frozen base query encoder. Across telecom-specific retrieval and generative QA benchmarks, we show that ARMOR improves evidence retrieval and answer generation in several in-domain settings. Code is available at https://github.com/heshandevaka/ARMOR.git.

We ask a simple question about decoder-only transformers: between which two layers is the probability of a predicted token actually produced? Existing layer-wise readout tools answer only approximately. The logit lens and its trained variant report a per-layer level of probability but give no additive decomposition; their estimates are biased and non-monotone across depth. Direct Logit Attribution and related residual-stream methods are additive, but only in logit space, the softmax nonlinearity breaks additivity in probability space, precisely the quantity one usually cares about. Layer Conductance integrates gradients per layer, but attributes each to its own baseline and so does not sum to the total change in prediction. We introduce IG-Lens, a telescoping application of Integrated Gradients along a single path through the hidden states from a baseline to the final layer. Crediting each segment to the layer it terminates at yields a layer-wise attribution whose sum is exactly the change in target probability, with the softmax inside the integration path rather than linearized away. Our default estimator credits each integration step its observed change in target probability (a prediction-aware reweighting in the spirit of IDGI) rather than its raw gradient. Because the readout is a one-dimensional probability, this collapses each segment to a telescoping sum of endpoint values, so completeness holds exactly (to floating point) at any step count, removing Riemann discretization error while suppressing steps that show gradient sensitivity without a change in output. We give the telescoping identity and its proof, verify completeness to floating point, and describe a single-pass batched implementation computing the full token-by-layer map without any backward call. Code: https://github.com/anhnda/IGLens.

We report a machine-verified resolution of a problem open for over a decade in quantum optimization: the Farhi, Goldstone and Gutmann (FGG) conjecture that depth-$p$ Quantum Approximate Optimization Algorithm (QAOA) on the ring of disagrees attains approximation ratio $(2p+1)/(2p+2)$ exactly. We found the proof using a large language model, Claude Fable 5, and verified its correctness end-to-end by the Lean 4 proof assistant. Our methodology includes several ingredients: building on a substantial Lean library of quantum information, we formalized the QAOA components and the known parts of the problem, and reduced the conjecture to a single open mathematical statement. The model was then handed the library and our agentic toolkit, and tasked with closing that gap by constructing a proof in Lean. The resulting process is a feedback loop between the model's natural-language reasoning and Lean's mechanical verification, which converged to a machine-verified proof. Human verification is required only for the structural scaffolding - that the formal statement faithfully encodes the intended claim - while the proof itself is supplied by the model and certified mechanically by Lean. The proof is nevertheless striking - the model uncovered a hidden dynamical symmetry of the problem and exploited it, borrowing tools and machinery from an adjacent field to turn a hard existence problem into an explicit construction. This work paves the way for resolving open conjectures in quantum information science and beyond.

How can we evaluate whether frontier AI systems recognize child-safety risks before they escalate into explicit harm? Existing child safety evaluations focus on child sexual abuse material, yet many child-safety failures begin earlier: in model assistance that helps adults manipulate, impersonate, profile, or isolate minors, and in model responses that deepen children's emotional dependence on AI systems rather than redirecting them toward human support. We introduce CAREBench (Child AI Risk Evaluation), a benchmark to assess such upstream child-safety risks in language models. CAREBench contains 500 prompts spanning twelve risk categories, including grooming and relationship engineering, deception and impersonation, surveillance and privacy, sextortion and sexual abuse, AI anthropomorphization, emotional dependency, and mental illness sensitivity. Developed with response annotations from parents and clinicians, the benchmark excludes explicit abuse material and imagery; instead, it evaluates whether models recognize, refuse, de-escalate, or redirect risky interactions before harm becomes overt. Evaluating seven frontier models on our benchmark, we find failure rates ranging from 2% to 58%, with failure patterns that vary across risk categories. CAREBench provides a responsibly scoped evaluation for LLM developers to identify and close gaps in child safety policies.

Observable Matrix Dynamics (OMD) is a diagnostic framework that probes the dynamics of high-dimensional internal representations of inputs by a neural network via a fixed-size $N \times N$ distance matrix $M(t)$ on a held set of $N$ inputs. OMD uses methods of random matrix theory and particle dynamics to explore spectral reorganisations that are missed by scalar loss functions, but are informative of the training process. We read $M(t)$ against a perturbative ambient-versus-latent decomposition extending the Bogomolny–Bohigas–Schmit (BBS) theory of random distance matrices, with per-snapshot diagnostics for the top-of-spectrum band structure and ambient noise, trajectory-level observables linking snapshots, and a 3D MDS embedding (bottom-three eigenvectors) rendering training as a moving particle cloud. Across seven experiments, diffusive regimes lack stable top-of-spectrum band structure, while sharp endogenous or externally driven reorganisations produce stable fingerprints: consistent with smooth or product latent geometries in BBS-adjacent cases, and with finite-cluster or Fourier-soliton structures otherwise. OMD thus reads the geometric regime of a representation rather than reporting a single intrinsic dimension.

Bogomolny, Bohigas and Schmit (BBS) found that the spectrum of the pairwise distance matrix on N points sampled from a smooth d-dimensional manifold encodes a signature of the underlying geometry. We develop I-BBS (Inference-BBS), a coordinate-free method that identifies a low-dimensional latent sub-manifold embedded in a high-dimensional ambient distance matrix alone, without accessing an ambient high-dimensional vector space. It therefore applies even when that space is only partly observable or undefined. We model the ambient embedding by two classes of generative noise, model-based and model-free. The noise mixes the latent signal with off-manifold components, so the eigenvalues reorganise collectively and the latent geometry cannot be read off eigenvalue by eigenvalue. We recover it instead from two integer-stable signatures that survive the noise: the multiplicity of the top non-Perron multiplet, which fixes $d$, and a parameter-free law for how the multiplet positions shrink as the noise grows. On synthetic spheres $S^1$, $S^2$ and $S^3$ these integer signatures are far more stable under noise than the continuous spectral slope, and a blind test recovers both the manifold and the noise model from a single distance matrix. Applications to neural-network representations and to the dynamic training regime are developed in two companion papers.

This paper examines how metric adjustments to Multidimensional Scaling (MDS) can enhance its effectiveness as a visual tool for pattern recognition. The distance under consideration, referred to as Max-D-SW, is an adjustment of the Max-Sliced Wasserstein distance. In contrast to the original formulation, which optimizes over single unit directions, Max-D-SW aggregates contributions over orthonormal bases. This modification provides a clear numerical advantage in MDS outcomes, particularly when applied to heavy-tailed distributions. We also establish sample-complexity bounds showing that Max-D-SW remains statistically tractable, with rates comparable to those of its max-sliced counterpart. Moreover, we show that a better sample complexity for a metric does not necessarily translate into better performance when the metric is used as an input for MDS.

Geospatial foundation models pretrained on satellite imagery promise broad generalization across remote sensing tasks and regions, but their geographic transferability has not been systematically tested, especially in agriculture applications. This paper presents a controlled benchmark that evaluates three models, Prithvi, SpectralGPT, and SatMAE, on multi-temporal crop segmentation and change detection across four U.S. states, Iowa, North Carolina, California, and Minnesota. By assigning each train, validation, and test split to a separate region, we measure how well each model transfers to land it has not seen. All three degrade sharply under regional distribution shift, predicting only the most common crops while missing rare ones. We further find that fitting these models to a shared input format affects each one differently, which complicates direct architectural comparison. These results expose key limitations of current geospatial foundation models for agriculture and point to region aware evaluation as a necessary standard.

Low-Earth orbit (LEO) satellite Internet has become an important infrastructure for enabling ubiquitous connectivity to align with the International Telecommunications Union vision for 6G telecommunications networks. However, current LEO satellite Internet observations often suffer from missing data, which complicates data augmentation task and limits the expansion of representative datasets. Given the complex characteristics of these datasets, generative AI (GenAI) presents a promising approach, yet its application in this domain has received little attention to date. In this paper, we propose a GenAI-based framework to synthesize high-fidelity data directly from incomplete LEO network observations. We propose the representative data missing scenarios, and evaluate the performance with the latest GAN- and VAE-based GenAI models on the recent WetLinks dataset. We design block-wise and point-wise missing scenarios to closely simulate the data loss that happens on real-world LEO satellite networks. Our results show the effectiveness of our proposed GAN-based framework and GT-GAN model exhibits the best performance among all models in both missing scenarios. Even under extreme conditions (e.g., 40% of the input data is missing), GT-GAN shows the highest robustness, consistently capturing the underlying input data distribution and being the least affected in terms of generalization. Our results shed light on future directions for GenAI-based data augmentation methods and data-driven research on satellite network measurement.

The acceleration of automated scientific discovery has been fundamentally bottlenecked by the epistemic gap between the semantic reasoning of large language models (LLMs) and the deterministic physics of mammalian biology. While recent multi-agent frameworks have achieved autonomous hypothesis generation and in vitro experimental analysis, they lack the mathematically grounded, causal constraints required for multi-scale clinical translation. Furthermore, while algorithmic clinical digital twins successfully forecast biological states, they rely on black-box latent spaces, sacrificing mechanistic interpretability for predictive accuracy. Here, we introduce the Multi-Scale Autonomous Discovery Engine (Octopus), a neuro-symbolic architecture that unites zero-leakage, local LLM swarms with strict algorithmic physics engines. Rather than stopping at isolated cellular assays, the system autonomously generated therapeutic hypotheses against in vitro CRISPR dependency data (CCLE), traced dynamic causal cascades using mechanistic interpretability (XGBoost SHAP vectors), and orthogonally translated the emergent vulnerabilities in silico to predict in vivo mammalian tumor trajectory (PDX) and human overall survival (Marisa). In a fully unsupervised sweep of colorectal cancer transcriptomes, the pipeline autonomously identified Insulin-like Growth Factor 2 (IGF2) as a strictly bounded vulnerability to 5-Fluorouracil resistance. The discovery maintained significance after rigorous Benjamini-Hochberg false discovery rate correction (q=0.0292, Log-Rank p=0.0007 ) and successfully predicted significant in vivo tumor volume shrinkage in an independent mouse cohort (Mann-Whitney p=0.0373). By bridging the chasm between multi-agent reasoning and mathematically bounded clinical survival, this framework establishes a verifiable, zero-leakage paradigm for automated, end-to-end biomedical discovery.

Modern optimizers combine gradients from the current mini-batch with historical optimization state, such as momentum or adaptive moments. While effective, this standard practice can produce parameter updates that actively increase the loss of individual samples. We term this phenomenon per-sample interference and propose redefining the parameter update as an optimization problem that explicitly minimizes it. Because the exact formulation of the problem is computationally prohibitive, we introduce a highly efficient surrogate. By reducing the problem's dimensionality to the batch size and restricting the optimization to the last linear layer, we overcome memory and speed bottlenecks. This strategy hinges on our unexpected finding that this layer alone can reliably capture core second-order statistics of the full network. The resulting surrogate problem integrates readily into standard optimizers like SGD and AdamW, and can be solved using a small number of GPU-friendly iterations. Crucially, the method exhibits favorable scaling properties, as the relative computational overhead shrinks as the model size or input grows. Experiments on image classification benchmarks confirm reduced per-sample interference and improved generalization.

Multimodal survival analysis utilizing whole slide images (WSIs) and genomic profiles is fundamental for cancer prognosis. Recently, state-space models like Mamba have emerged as powerful tools for sequence modeling. However, translating this success to complex multimodal tasks is hindered by two critical limitations. First, conventional fusion strategies assume a static multimodal interaction strength, ignoring the fluctuating diagnostic importance of each modality across different patients and local regions. Second, the standard Mamba architecture processes tokens along predefined physical paths. This rigid scanning disrupts the semantic continuity of spatially scattered medical features and exacerbates long-range decay. To address these challenges, we introduce AdaSurvMamba as a novel adaptive framework for multimodal survival analysis. The framework features a Dual-Scale Importance-Aware Reconstruction (DSIR) module to dynamically modulate cross-modal interaction strength. It evaluates diagnostic importance at both the sequence and token levels to reconstruct the input representations. Furthermore, we propose a Semantic Aggregation Scanning (SAS) module to overcome contextual fragmentation. The SAS module dynamically reorganizes discrete tokens into semantically continuous sequences via a shared prototype pool. It explicitly modulates the state transition step size using global modality context and semantic priors to adaptively control the information absorption rate. Experiments across five TCGA cohorts demonstrate consistent gains over existing methods. Code is available at https://github.com/zjlGO/AdaSurvMamba.

Pretrained models are typically ranked on multi-task leaderboards to assess their effectiveness across diverse tasks. Rank confidence intervals were recently introduced as a method to quantify the uncertainty in these rankings by aggregating pairwise hypothesis tests. In this work, we analyze the sources of uncertainty in the knowledge evaluation benchmark MMLU and show how hypothesis tests can be modified to account for their effects. We demonstrate that ranking variability across MMLU subjects is substantial and should be considered when comparing LLMs or identifying the top-performing models.

The application of artificial intelligence methods in power electronic converter modeling is becoming increasingly widespread, but existing applications still face many challenges, such as difficulties in multi-time-scale hybrid analysis and the lack of physics-aware evaluation criteria and constraints, resulting in poor performance. This paper proposes a Neural Controlled Differential Equation (Neural CDE) framework for learning continuous-time surrogate models of grid-forming inverters for electromagnetic transient (EMT) simulation, which relaxes the constraint of fixed sampling rates and enables multi-time-scale control analysis. Then, an affine-control formulation with dual slow/fast pathways is proposed to capture the hierarchical and multiscale behavior of converter dynamics, and a physics-inspired regularization method is utilized to enhance stability and coherence. Evaluated on EMT-generated trajectories, the model accurately reproduces transient responses, preserves effective damping and the dominant oscillatory characteristics, and maintains bounded long-horizon rollouts. The results show that Neural CDE-based component modeling offers a physically consistent surrogate modeling approach for EMT-level simulation studies.

Reinforcement learning (RL) has become a widely adopted technique for improving large language models (LLMs) on complex tasks. Despite this progress, existing RL methods still face challenges in training agents with longer-horizon interactions. One major bottleneck is distinguishing the contribution of different actions in long-horizon interaction, leading to high optimization variance. To address this, we introduce a novel policy gradient method, Hindsight Policy Optimization (HPO), that projects both the current policy distribution and the hindsight distribution into an intent space and extracts low-variance learning signals from the Wasserstein distance between them. We theoretically and empirically show that aggregating semantically similar states and actions in the intent space yields a bounded-variance estimator and improves policy performance stably. Our code is available online.