Computation and Language
Papers
Fresh from arXiv, typeset properly. Highlighted words trade on the market.
Saturday 15 August
Memory is becoming core infrastructure for long-horizon LLM agents, yet existing evaluations offer limited guidance on which memory substrate, namely the underlying medium in which memory is represented and stored, should be used under different operating regimes. We introduce a unified suite of 26 performance and efficiency metrics, including auxiliary-LLM costs attributed to the write, read, and management stages, and apply it identically to 11 memory methods in a controlled harness that varies only the memory substrate. The methods cover dense and sparse indices, text records, structural stores, hierarchical stores, refinement-based memories, parametric updates, and activation-compatible context mechanisms, and we evaluate them with three backbone models on four benchmark suites spanning user-centric question answering and agent-centric decision-making. Our results show that no single substrate consistently dominates: broad retrieval benefits long-context factual QA, while excessive retrieval can harm sequential decision-making by shifting attention away from action-critical context. Scalability introduces a further routing axis, as substrates that perform well at moderate history lengths can become costly or brittle at longer horizons. These regime-dependent reversals make substrate selection a design axis. Choosing a substrate per observable operating regime improves over the best fixed substrate on our benchmarks, while query-level routing leaves most of the oracle headroom open. The findings provide empirical guidance for designing efficient, reliable, and regime-aware long-term memory for LLM agents.
Computer Vision
MetaReason: Precise Interleaved Multimodal Reasoning via Editing Meta Information for Solving Geometry Problems
Although visual reasoning is crucial for solving complex geometry tasks, existing vision-language models rely heavily on text-only reasoning. Some recent methods introduce intermediate visual states to facilitate reasoning, but they are often hindered by inaccurate geometric representations and low rendering fidelity, ultimately leading to unreliable outputs. To address these limitations, we propose MetaReason, a framework for multimodal reasoning in plane geometry that leverages structured meta-information to enable accurate auxiliary-line construction. The framework first parses geometric images into meta-information, performs controllable edits with predefined tools to synthesize high-fidelity visual states, and then conducts reasoning based on these augmented views. To support this framework, we construct TutorGeo, a comprehensive dataset containing 17k image-to-meta conversion samples, 60k text-only reasoning traces, and 60k interleaved multimodal reasoning traces. Using this dataset, we combine supervised fine-tuning and reinforcement learning to develop robust multimodal reasoning capabilities. We also introduce ExamGeo, a benchmark derived from real-world examination problems that enables systematic evaluation across varying difficulty levels. Experimental results demonstrate that MetaReason significantly outperforms existing open-source models and achieves competitive performance against proprietary models.
Read the full abstract
Computer Vision
FZ-VLM: A Two Stage Florence-Zephyr Vision Language Model Framework for Pulmonary Nodule Characterization and Clinical Decision Making
Lung cancer remains one of the leading causes of cancer-related mortality worldwide, and Computed Tomography (CT) is a primary imaging tool for screening and followup assessment. After pulmonary nodule detection, radiologists manually assess anatomical location, diameter, margin characteristics, and attenuation type to support risk assessment and clinical decision-making. However, this post-detection workflow is time-consuming and can be affected by inter-observer variability. Existing Artificial Intelligence methods often focus on isolated tasks, limiting their use as a unified, clinically grounded interpretation framework. This study presents FZ-VLM, a two-stage Florence-Zephyr Vision Language Model framework for unified structured pulmonary nodule characterization in lung CT. The framework uses a fine-tuned Florence-2 model to extract radiological attributes from expert-annotated 2D axial CT slices, while a Zephyr-7B model uses these attributes to generate nodule descriptions, follow-up recommendations, and longitudinal analyses. Results showed that the Stage 1 model achieved 77.18% accuracy for anatomical location, 67.96% accuracy for margin characteristics, and 79.13% accuracy for attenuation type, with a Mean Absolute Error of 2.58 mm for diameter estimation, outperforming evaluated GPT-4-based baselines as well as the human baseline. Expert radiologist evaluation of Stage 2 showed 93.9% accuracy, 98.6% completeness score, 76.1% clinical relevance, and an overall score of 89.5%. Safety analysis showed that most outputs were clinically safe, although some follow-up recommendations still required expert review. To the best of our knowledge, this study presents the first two-stage Vision-Language Model framework for structured nodule characterization and clinical decision-making.
Read the full abstract
Information Theory
The Minimum Number of Measurements for Almost-Everywhere Complex Phase Retrieval
Let $d\geq 2$ and let $\bf{f}_1,\ldots,\bf{f}_m\in\mathbb C^d$. We prove that if $m\leq 2d-1$, then the intensity measurement map \[ \bf{x}\longmapsto \bigl( |\langle \bf{x},\bf{f}_1\rangle|^2, \ldots, |\langle \bf{x},\bf{f}_m\rangle|^2 \bigr) \] fails to recover almost every signal in $\mathbb C^d$ uniquely up to a global phase factor. Combined with the known generic sufficiency of $2d$ measurements, our result establishes that the minimum number of measurements required for almost-everywhere phase retrieval in $\mathbb C^d$ is exactly $2d$. This resolves an open problem in phase retrieval by determining the exact measurement threshold for almost-everywhere phase retrieval in ${\mathbb C}^d$.
Read the full abstract
Robotics
NPU Offloading of a Frozen Visual Encoder for Robot Policy Training
When a robot policy is trained for a new task or dataset, its visual encoder can be frozen and only its action generation module trained, reducing training cost. Freezing removes the encoder's backward pass, but its forward pass must still run at every training step because the input images change, so it keeps consuming GPU compute. We therefore ask whether moving this computation to a low power AI accelerator such as an NPU can reduce total energy despite the added data transfer and longer training time, and how it affects policy performance. We built an asynchronous training pipeline that uses both a GPU and an NPU for the AR-Actor specialist. The frozen visual encoder runs in A8W8 INT8 on a Mobilint Aries2 NPU, while the FP32 action expert is trained on an NVIDIA GeForce RTX 5060 Ti GPU. We compared a GPU-only baseline with four conditions, L1 to L4, which gradually extend NPU offloading from one to four Transformer encoder layers. Each condition was trained for 30,000 steps with three random seeds. We measured GPU board power for the GPU-only condition and combined GPU and NPU board power for the NPU conditions. Energy per sample decreased by 17.1% in L1, which offloaded ResNet18 and the first encoder layer, and by 27.9% in L4, which offloaded ResNet18 and all four encoder layers. In contrast, training time per sample increased by 15.2% in L1 and 37.7% in L4, and peak allocated GPU memory decreased by 19.8 to 20.7%. The 15 resulting policies were each evaluated with the same 300 environment seeds, for a total of 4,500 simulator rollouts. The combined success rate was 93.33% for GPU-only and 91.44 to 92.89% for the NPU conditions. These results show that NPU offloading of a frozen visual encoder can reduce training energy, but it increases training time and lowers policy success rate by 0.44 to 1.89 percentage points compared with GPU-only training.
Read the full abstract
Machine Learning · Cross-listed from hep-th
Spinning Conformal Correlators from Neural Networks
We construct spinning conformal fields from neural networks and the embedding formalism, computing their two-, three- and four-point functions in examples, building on scalar conformal field techniques introduced in \cite{Halverson:2024axc}. For a particular ensemble of i.i.d. neurons we recover the 4d Maxwell CFT in the infinite-width limit.
Read the full abstract
Computation and Language
RamseyGadgets: A Graph Construction Dataset for LLMs
Constructing special graphs is an important task within graph theory and computer science. Many popular graph constructions are the result of a comprehensive exploration of relevant graphs and human ingenuity. Given the rise of generative AI usage in mathematics, it is natural to test whether LLMs are able to construct graphs with specified properties using their reasoning capabilities. Unfortunately, many natural graph construction problems, such as finding extremal Ramsey-good graphs (i.e., avoiding specific monochromatic subgraphs), have been explored extensively in the literature, making it difficult to ascertain whether a construction is the product of an LLM's reasoning capabilities or its recollection from training data. In this work, we introduce RamseyGadgets, a novel dataset of 70 underexplored graph construction problems that require finding Ramsey-good graphs with special properties (e.g., containing an edge with a fixed color). These problems have reasonably sized solutions (at most 10 vertices) that can be verified by SAT solvers, making them suitable for automatic evaluation. Our dataset is easily expandable, as one can simply change the monochromatic subgraphs being avoided to obtain a new set of problems. We evaluate the performance of five open-source LLMs on our dataset and report the results. Our findings show that LLMs achieve only 37.70% accuracy on the hard-tier problems in our dataset, with Gemma-4-31B achieving the highest performance out of the five. We also showcase how our dataset allows us to ascertain what kind of hints help LLMs perform better at this task.
Read the full abstract
Robotics
HP2-SLAM: Adaptive Hybrid ICP for Robust and Efficient LiDAR SLAM
Achieving robustness, accuracy, and efficiency simultaneously remains a central challenge in light detection and ranging (LiDAR) simultaneous localization and mapping (SLAM). While learning-based approaches deliver strong benchmark performance, they often require extensive training, substantial computational resources, and struggle to generalize to unseen or degenerate environments. Geometry-based methods are efficient and interpretable, yet their performance degrades in planar or repetitive scenes due to limitations of standard iterative closest point (ICP) formulations. We present HP2-SLAM, a minimalist yet robust LiDAR SLAM framework built around a neighborhood-size adaptive hybrid ICP. Our key insight is a planarity-aware adaptive threshold that dynamically classifies correspondences based on local geometric structure and density, thereby enabling a principled balance between point-to-plane and point-to-point residuals. This formulation stabilizes alignment in both structured and degenerate environments without feature engineering, learning modules, or dataset-specific tuning. Integrated into a complete SLAM pipeline with submap management, loop closure detection, and pose graph optimization, HP2-SLAM consistently outperforms strong geometry-based baselines across publicly available datasets while maintaining real-time performance on commodity hardware. Our results demonstrate that carefully designed geometric adaptation can achieve strong generalization and robustness without sacrificing simplicity or efficiency.
Read the full abstract
Artificial Intelligence · Cross-listed from quant-ph
PAS-QFL: Personalized Ansatz Selection for Quantum Federated Learning under Client Data Heterogeneity
Quantum federated learning (QFL) lets multiple quantum clients collaboratively train quantum neural networks (QNNs) without sharing private local data. However, existing QFL methods commonly assume that all clients use the same ansatz, overlooking how heterogeneous client data affects ansatz suitability. Under class-imbalanced non-IID data, different clients may favor different ansatz structures, so a fixed ansatz can lead to unstable and unfair performance across clients. In this paper, we propose PAS-QFL, a Personalized Ansatz Selection framework for QFL under client data heterogeneity. Rather than treating the ansatz as a monolithic structure, PAS-QFL decomposes each client QNN into a globally shared ansatz and a client-specific private ansatz, and personalizes the structure of the private ansatz rather than only its parameters. The shared ansatz is placed first and selected by a stability-aware cross-client criterion so that its parameters can be reliably aggregated, while the private ansatz serves as a personalized decision head, selected per client by local Macro-F1 to adapt the shared representation to its local data. During training, each client updates both its shared and private parameters locally but uploads only the shared parameters, so federated aggregation stays well-defined while each client keeps its own private structure. PAS-QFL uses Macro-F1 as the primary selection metric to avoid misleading accuracy under class imbalance. Experiments on heterogeneous QFL tasks show that PAS-QFL improves average Macro-F1 over the existing fixed-ansatz QFL baselines, demonstrating the value of personalizing the ansatz structure for practical QFL.
Read the full abstract
Computer Vision
Registration-Free Hyperspectral Reconstruction from RGB via a Permutation-Invariant Gram-Matrix Principle
Reconstructing a spatially and spectrally high-resolution hyperspectral image (HR-HSI) from a low-resolution HSI (LR-HSI) and a high-resolution RGB image (HR-RGB) usually assumes precise registration and a known camera response function (CRF). Both assumptions are difficult to satisfy with different sensors. We remove both through a permutation-invariant supervision principle: the Gram matrix of an unmixed abundance map depends on shared material composition but not on pixel ordering. Matching abundance Gram matrices therefore allows RGB-to-HSI mapping to be learned without spatial correspondence and without a predefined CRF. Under a full random permutation of HR-RGB pixels, a state-of-the-art fusion method collapses, whereas our reconstruction is unchanged after inverse reindexing for evaluation. Building on this principle, a residual spectral super-resolution function maps HR-RGB directly to HR-HSI without registration, known CRF, or paired supervision. Across indoor, natural-scene, and remote-sensing benchmarks, the method achieves accuracy comparable to approaches that require these assumptions while remaining robust when they are violated. Loss ablations further show that reconstruction accuracy is largely insensitive to the specific discrepancy used to match the Gram matrices, indicating that performance arises primarily from the permutation-invariant principle rather than loss tuning.
Read the full abstract
Artificial Intelligence
Does a Tool Result Carry More Authority Than Plain Text? Three Prospective Studies of False-Claim Adoption in a Synthetic Assignment Task with Claude Opus 5
Language-model systems increasingly read from stores they also write to, so a claim that was merely written earlier can return looking retrieved. We tested whether the message package carrying an unsupported assignment changes which answer a model gives in a synthetic lookup task. Claude Opus 5 selected a color code for a named item or abstained. In an exploratory four-arm study, false-code adoption was 0/24 with no target claim, 0/22 scorable trials when a prior assistant assertion named the target, 14/24 when a tool-result record named it, and 15/24 when that result used a ten-field metadata wrapper that marked it unchecked. The tool-result arm selected the record's code in 11/12 supported trials and 14/24 unsupported trials, ruling out a fixed output-token bias while leaving substantial planted-token heterogeneity. A document-preregistered replication reproduced the tool-result versus assistant-assertion gap, 7/24 against 0/24, one-sided Fisher exact p = 0.0047. The tool-result rate nevertheless fell from 14/24 to 7/24 across runs made four days apart. A second preregistered study gave the earlier comparison a live text control: both records were announced in advance and placed in the same final user turn, then target binding was swapped between the linked tool result and later inline JSON. Inline text was sufficient for false-code adoption in 60/60 trials; the tool-result condition produced 57/60, so the registered result-first superiority criterion failed, p = 1. The result does not show that tool results have no effect. It shows that native tool-result placement was not necessary and that this experiment did not find greater behavioral weight for the result package than for announced inline text. The findings concern a single model on one synthetic task template, accessed through one API.
Read the full abstract
Computer Vision
Risk-Adaptive Edge–Cloud Visual Reasoning for Communication-Efficient Autonomous Driving
Cloud-hosted vision-language models (VLMs) offer greater contextual reasoning capabilities than smaller onboard models, but frequent visual uploads increase communication overhead and add network and inference latency to tactical decisions. We present a risk-adaptive edge-cloud architecture in which onboard traffic assessment determines when cloud reasoning is requested. An onboard VLM and a lightweight detector capture temporal traffic conditions and path-relative hazards for conservative local response and selective cloud access. The cloud model provides tactical advice, while validation, vehicle control, and automatic emergency braking remain local. In CARLA experiments, our method matched the task success rate of periodic cloud access while reducing cloud requests by 54.1% and recording fewer automatic emergency braking (AEB) activations. In a delayed-roadwork ablation, semantic events triggered requests before the next scheduled audit. Across three emulated network profiles, the method continued to reduce cloud traffic, although lane changes took longer than with periodic access. Onboard traffic assessment therefore served as a practical trigger for selective VLM inference in these experiments.
Read the full abstract
Robotics
GaussMemory: Task-Driven 3D Gaussian Scene Memory for Long-Horizon Robotic Manipulation
Long-horizon robotic manipulation fundamentally relies on persistent spatial memory. However, existing 3D memory systems function merely as passive recorders: they store observations using fixed, hand-crafted rules, treating every scene element–whether a critical grasp target or an irrelevant background wall–with equal importance. In this paper, we propose a paradigm shift from passive storage to active, task-driven spatial memory. We argue that a robot's memory should not simply record what it sees, but actively learn how to remember–discovering which objects to track precisely, how aggressively to update them, and what to discard, all learned end-to-end without hand-designed rules. Crucially, this active paradigm is realized by unifying memory update and readout as two sides of the same cognitive process, enabling bidirectional flow where task needs shape update strategies and vice versa. To instantiate this vision, we introduce GaussMemory, which leverages 3D Gaussian Splatting as a persistent geometric substrate. On LIBERO, GaussMemory outperforms MemoryVLA on Goal and Long-10; on VLABench, it surpasses $\pi_0$-FAST by +5.2% (Track 1) and +6.0% (Track 6).
Read the full abstract
Machine Learning
Do Geometry-Aware Positional Encodings Help Transformers in Spatial Imperfect-Information Games?
Transformers applied to spatial imperfect-information games must represent map geometry while tracking hidden entities through time. We ask whether geometry-aware positional encodings improve these capabilities, without claiming a new positional encoding. We construct a four-level benchmark on a hexagonal naval pursuit game: controlled geometry and topology probes, an exact-Bayes hidden-target tracking task, offline policy imitation at 1k and 10k games, and 7,200 fixed-seed games against three legacy opponents. Across matched Transformer backbones, HexRoPE reduces exact-belief posterior cross-entropy relative to no positional encoding by 0.278 on D6-transformed test orbits and 0.329 on a larger map; both hierarchical-bootstrap confidence intervals exclude zero, and both Holm-adjusted p-values are below 0.001. At 1k games, HexRoPE improves policy action accuracy by 4.63 percentage points over no encoding and 2.05 points over rectangular relative bias; the gains shrink to 1.55 and 0.41 points at 10k games. However, HexRoPE does not improve aggregate gameplay win rate: its paired effect over no encoding is -1.56 percentage points (95% CI [-4.50, 1.17]). Rectangular relative bias is strongest on D6 belief consistency but fails sharply when extrapolating from radius 3 to radius 4, while graph bias provides only a small blocked-edge gain. The results show that geometric inductive bias improves belief estimation and data-efficient imitation, but those representation gains do not automatically produce stronger closed-loop play.
Read the full abstract
Systems and Control · Cross-listed from nlin.CD
An Idealized Delay-Differential Model of Scuba Diver Porpoising and Runaway Ascent
A scuba diver holding constant depth balances on an unstable equilibrium: the gas carried in the suit and buoyancy compensator compresses with depth, so the buoyant force falls as the diver sinks and rises as the diver ascends. We represent the diver as a proportional-derivative controller that regulates this compressible-buoyancy saddle after a finite reaction delay, and we derive the governing delay differential equation from the vertical force balance and the isothermal gas law, reducing it to a damping ratio, two control gains, and a dimensionless delay. The characteristic spectrum, obtained by pseudospectral collocation of the semigroup generator and checked against a direct Newton solution of the characteristic equation, locates the Hopf boundary that separates stable hovering from sustained porpoising; for the baseline diver the critical reaction delay is 3.36 s and the onset period is 28.8 s. The bifurcation is supercritical, and because the saturating force is the quadratic hydrodynamic drag, the limit-cycle amplitude grows in proportion to the delay excess rather than as its square root. The safe-operating envelope shows that runaway ascent is triggered by saturation of the compensator, not by loss of linear stability, so a stable and an unstable diver can share the same escape threshold. As onset is approached, the lag-one autocorrelation and variance rise while the fitted recovery rate falls and matches the spectral abscissa, giving an eigenvalue-exact early warning of the transition.
Read the full abstract
Game Theory
Watermarked Game Solving via Perturbed Regret Minimization
Many real-world interactions among self-interested parties can be modeled by game theory, and the rapid advancements in AI have raised concerns about the possible misuse—accidental or deliberate—of superhuman or human-level game-playing agents by bad actors. While AI watermarking has mainly been applied to LLM-generated texts, a recent line of work proposes developing watermarking techniques for agents in game-theoretic settings. However, existing watermarking techniques for game-theoretic agents are not readily applicable due to their limited scope or capabilities—they are tailored to perfect-information games and are thus inapplicable to richer game types. We propose a new approach to watermarking game-playing agents, which a) can be applied to imperfect-information settings; b) is directly integrated into the learning process itself; and c) incurs only a bounded cost in exploitability. For this purpose, we introduce perturbed regret minimization, which adds perturbations to the utilities prior to observation so as to encourage the learning algorithm to embed the watermark. Our experiments show that the watermark incurs only a small exploitability cost and can be detected within just a couple of hours of gameplay at human speed.
Read the full abstract
Computer Vision
Benchmarking Frontier Text-to-Image Models on Image-Description Prompts
Text-to-image models are typically reported on average-case prompts, which understates the gap between systems on compositionally demanding requests involving precise object counts, multi-object attribute binding, legible embedded text, and explicit spatial constraints. We evaluate four production text-to-image systems: Hunyuan 3.0, Gemini 3 Pro Image ("Nano Banana Pro"), Black Forest Labs FLUX.2, and Ideogram 3.0. The evaluation uses the 48 hardest prompts drawn from the DataSeeds.AI Sample Dataset (DSD), selected through an automated complexity-scoring pass over the full corpus. Every generated image is graded using an independent-judge rubric. GPT-5.4-Pro authors an atomic, weighted, mutually exclusive and collectively exhaustive (MECE) evaluation rubric, while Gemini 3.1 Pro Preview independently determines whether each criterion is satisfied. Gemini 3 Pro Image ranks first with a score of 84.8/100, narrowly ahead of FLUX.2 at 82.3/100. Ideogram 3.0 and Hunyuan 3.0 score 65.7/100 and 63.3/100, respectively. Failure analysis shows that the leading systems primarily lose points through object miscounting and geometric artifacts, whereas the trailing systems more frequently produce garbled text. Ideogram 3.0 also frequently omits requested elements. Full per-sample rubrics, scores, and failure annotations are available from the authors upon request.
Read the full abstract
Computational Complexity
On the Complexity of Locally Dense Lattices
Locally dense lattices are central gadgets used to prove the hardness of the Shortest Vector Problem and related lattice problems. Informally, a locally dense lattice is a lattice $\mathcal{L}$ that contains exponentially many lattice vectors inside some $\ell_p$ ball centered at $\vec{s}$ with radius at most an $\alpha < 1$ fraction of the length of its shortest nonzero lattice vector. In this paper, taking a “meta” viewpoint on locally dense lattices, we introduce the Locally Dense Lattice Problem (LDLP), the decision problem of determining whether a given input specifies a locally dense lattice. Our main result is that LDLP in $\ell_p$ norms for all finite $p \geq \log_2 3$ and for the infinity norm is complete for the second level of the polynomial hierarchy. We also compare two standard definitions of local density that appear in prior work. Micciancio's original definition (FOCS 1998 and SICOMP 2001) uses integer coefficient vectors, while later work by Micciancio (ToC 2012) and by Bennett and Peikert (RANDOM 2023) uses short vectors in a shifted coset. We show that the corresponding promise problems are mutually reducible in deterministic polynomial time, which shows that the two formulations are robust.
Read the full abstract
Artificial Intelligence
Demand-Driven Vertiport Siting and Discrete-Event Fleet Simulation for On-Demand Urban Air Mobility Network Design
This paper presents a demand-driven framework for on-demand Urban Air Mobility (UAM) network design that links vertiport siting, fleet simulation, and door-to-door travel-time feasibility. Demand is estimated from commuter and passenger activity data, converted into spatial trip-end points, and clustered using K-means to generate candidate vertiport locations. Candidate networks are screened using range and minimum station-spacing constraints, then evaluated with a discrete-event simulation that models multi-vehicle dispatch, deadhead relocation, battery swaps, and service regularity. Flight time and energy consumption are computed using a point-mass eVTOL performance model. In a Greater Los Angeles case study, the preferred design expands from four stations and four eVTOLs at low demand to sixteen stations and twelve eVTOLs at the highest tested demand level. Results show that larger fleets improve completion time and vehicle-arrival regularity but do not eliminate deadhead flights, indicating that spatial demand imbalance remains an operational burden. The travel-time savings analysis further suggests that UAM is most defensible for longer or congestion-heavy trips where sufficient non-flight time remains after accounting for flight time.
Read the full abstract
Machine Learning
A Physiology-Informed Digital Twin Framework for Simulating Liver Health Progression
We present a physiology-informed digital twin of the human liver designed for longitudinal simulation of liver function and early-stage disease progression. The model, referred to as HEPATWIN, integrates key hepatic processes, including carbohydrate, lipid, and protein metabolism, bilirubin conjugation, bile production, and detoxification, within a unified systems-level framework to generate clinically observable biomarker trajectories. Unlike purely data-driven approaches, HEPATWIN incorporates mechanistic representations of liver physiology and patient-specific inputs such as diet, activity, and baseline biomarkers to simulate disease evolution over time. To ensure consistency with clinical progression patterns, we introduce a stage-transition-driven calibration mechanism that aligns simulated outputs with population-level biomarker distributions across disease stages, including NAFLD, fibrosis, and cirrhosis. Validation using the NIDDK NAFLD dataset demonstrates that HEPATWIN produces longitudinal biomarker estimates within clinically acceptable ranges and can forecast trajectories over multi-year horizons. Furthermore, simulated biomarkers retain sufficient clinical signal to support downstream NASH detection with competitive performance relative to models using ground-truth laboratory data. These results highlight the potential of physiology-informed digital twins for personalized, non-invasive diagnosis and prediction of organ health in general and liver health monitoring in particular.
Read the full abstract
Machine Learning · Cross-listed from stat.ML
A Deep Learning Model for Spatially Clustered Data via Differentiable Cluster Assignment
We consider nonparametric regression when the association between a response and its covariates changes across an unknown partition of a spatial domain. The proposed estimator learns the partition and the cluster-specific regression functions jointly. A neural network depending only on location determines cluster membership, while separate neural networks describe the covariate–response relationship within the clusters. An annealed softmax relaxation permits gradient-based estimation of the otherwise discrete assignments. Graph-Laplacian and occupancy penalties are used to discourage fragmented regions and degenerate solutions. We establish identifiability up to label permutation, bound partition error under a margin condition, and decompose prediction risk into regression and assignment components. The resulting rate agrees with that of an oracle estimator when the partition is estimated sufficiently accurately. Simulations show that joint estimation is useful when regression surfaces change abruptly across spatial boundaries, including settings with nonlinear effects, unequal region sizes, preferential sampling, and spatially correlated errors. Finally, a real data analysis is provided to demonstrate the validity and effectiveness of the proposed method.
Read the full abstract
Distributed Computing
When Does Distributed AI Inference Need More Wide-Area Bandwidth? A Co-Design Evaluation of Optical, Packet, and Software Levers
Wide-area bandwidth per unit of GPU compute falls every hardware generation: in compute-intensity-ratio terms (CIR, bytes per FLOP), the gap between on-package memory and the conventional WAN is four to five orders of magnitude, widening at roughly 12-19% per year. Position papers - including our own - argued this makes elastic optical wide-area capacity necessary for cross-site AI inference. Reviewers correctly objected that such arguments show more bandwidth helps, not that it beats the alternatives: KV recomputation, cache compression, locality-aware routing, scheduling, or an overprovisioned packet backbone. This paper does the comparison. We derive a workload model predicting when moving inference state across sites beats recomputing it - a context-independent crossover at 74-111 Gbps per stream for a 70B multi-head-attention model, falling to 9-14 Gbps under grouped-query attention at 1/8 KV heads - and quantify five sensitivity axes: context length, attention architecture, queueing, agentic compounding, and loss/jitter-induced bandwidth collapse. On economics: at list GPU prices recomputation is cheaper; transfer wins when GPU scarcity and KV reuse multiply effective GPU cost by roughly 5-20x, and modern attention moves the breakeven an order of magnitude in transfer's favour. We position the network levers correctly rather than adversarially: packet networks allocate lit capacity at millisecond timescales; optical fungibility changes how much capacity is lit, at minute timescales, substituting for overprovisioning economically rather than functionally. Finally we specify a ten-metric measurement plan on a three-site production-fibre testbed, framed as an open ecosystem exercise: no single company can - or should - assemble this evidence alone. Every claim is bounded by the regime in which it holds; several findings weaken the naive version of our own thesis, and we state them.
Read the full abstract
Machine Learning
Command-Space Counterfactual Explanations for Pareto-Conditioned Reinforcement Learning
Pareto Conditioned Networks learn multiple multi-objective reinforcement learning behaviours by conditioning a single policy on a desired return command. However, the local mapping from command and state to action remains opaque. We propose command-space counterfactual explanations for PCNs: given a fixed state, original command, and foil action, we search, in a black-box setting, for a minimally changed desired-return command under which the same trained policy would choose the foil. Our contributions are threefold. First, we formulate PCN explanations as return-command interventions, using a return-only PCN variant that avoids the added ambiguity of horizon-conditioning. Second, we adapt adversarial machine learning methods to reinforcement-learning explanations. Third, we introduce a boundary-seeded directional search that improves over purely local optimization in the command-action landscape, resulting in our proposed approach CF-ZOO. The resulting explanations are actionable and intuitively expressed in the user's own preferences: "If your trade-off had shifted slightly towards X, the agent would have chosen Y."
Read the full abstract
Emerging Technologies
Conditional Dynamical Systems for Image Generation
Image generation is dominated by deep generative models on GPUs, whose computational and energy costs raise sustainability concerns. Emerging non-von Neumann substrates, including quantum, compute-in-memory, photonic, and thermodynamic platforms, promise greater efficiency, yet most work ports conventional neural network architectures onto them and mainly accelerates operations such as matrix multiplication. This does not fully exploit a native capability of many hardware substrates: relaxation toward low-energy states can itself compute at little cost. Building on this primitive, we develop dynamical systems for image generation based on Ising spins and Kuramoto oscillators. The internal states of both models evolve under dynamics with an explicit Lyapunov energy, and a compact decoder renders the final states as images. For conditional generation, we introduce local conditioning: programmed interactions remain fixed, and one class-dependent bias per node reshapes the landscape, avoiding additional reprogramming and calibration costs. On CIFAR-10, the Ising and Kuramoto models reach clean-FID scores of $6.40$ and $5.37$, respectively, with $4096$ nodes. With a CMOS-compatible hardware realization, the dynamical-system core is projected to cost ${\sim}110.6$~nJ per image, and the full computation, even with the decoder on a GPU, outperforms all GPU baselines in latency and energy. These results suggest that energy-descending dynamics on non-von Neumann substrates can serve as generative computation, offering an efficient path beyond GPUs.
Read the full abstract
Information Theory
Fluid Antenna-Aided Noise Modulation: Spatial Diversity for Variance-Based Wireless Communication
Noise modulation (NoiseMod) encodes information in the variance of a transmitted noise-like waveform rather than in its amplitude, phase, or frequency, and is attractive for ultra-low-power and covert links. Its main weakness is that, unlike classical modulation, it exhibits no diversity under Rayleigh fading: its bit error probability (BEP) decays only as $1/(N_s\delta)$, where $N_s$ is the number of noise samples per bit and $\delta$ the useful-to-thermal noise variance ratio. Independently, fluid antenna systems (FAS) have been shown to recover substantial selection diversity from a single radiating element that switches among $N_p$ closely spaced ports, without extra radio-frequency chains. This paper combines the two: we equip a NoiseMod receiver with a fluid antenna and derive its average BEP. For idealized, mutually independent ports, we obtain an exact closed-form BEP via order statistics of the port envelopes. For the physically accurate, spatially correlated case governed by Jake's model, we build a semi-analytical BEP using the two-stage channel approximation of Khammassi et al. We validate both regimes against full signal-level Monte Carlo simulation and show that (i) FAS restores a diversity order that grows with the number of ports $N_p$ when ports are weakly correlated, (ii) this gain saturates once the fluid-antenna aperture $W\lambda$ is fixed and $N_p$ grows, mirroring the outage-probability saturation reported for FAS, now observed for BEP, and (iii) an intrinsic, correlation-independent (and $\delta$-independent) BEP floor set only by $N_s$ and the variance ratio $\alpha$ persists regardless of the antenna diversity order.
Read the full abstract
Databases · Cross-listed from nucl-ex
Best Reaction Target To Determine Proton Distribution Radii of Atomic Nuclei
We found that a heavy target such as Pb is most suitable for determining the proton distribution radii of unstable nuclei through charge-changing cross-section ($\sigma_\text{cc}$) measurements. As a heavy ion probe, low-$Z$ targets are routinely used to determine nucleon distribution radii of unstable isotopes. This approach has recently been extended to study proton distribution radii from $\sigma_\text{cc}$ measurements. However, empirical scaling factors have to be introduced to apply the Glauber models. In the present work, we systematically investigated the scaling factor using 39 new $\sigma_\text{cc}$ data of 18 $p$-shell nuclei on hydrogen, carbon, silver, and lead targets at around 240 MeV/nucleon. Together with the existing data, we reveal a universal dependence of the scaling factor on both the masses of target nuclei and the separation energies of projectile nuclei. The scaling factors decrease with increasing target-nucleus mass and converge to 1 for the highest-$Z$ target, making the scaling unnecessary. We conclude that instead of a low-$Z$ target, employing a heavy target such as Pb in $\sigma_\text{cc}$ measurements is the best option to determine the proton distribution radii of unstable nuclei.
Read the full abstract
Machine Learning
LLM-based Framework for Generating and Verifying Parallel DEVS Statecharts
The development of models demands sound modeling and simulation knowledge as well as domain knowledge. Every model should accurately represent a system's dynamics and be verifiable. Toward this objective, this research introduces an agentic PDEVS-LLM framework to assist human modelers in generating and verifying PDEVS statecharts for behavior modeling of atomic Parallel Discrete Event System Specification (PDEVS) models. The framework supports (re)generating plausible facts from a system description prompt using the agentic LLM used for generating plausible facts. Inconsistencies in plausible facts lead to incorrect PDEVS statecharts having logical structure and behavioral inaccuracies. A controlled-correction mechanism is developed to verify the logical consistency of the plausible facts. The agentic LLM is used to generate key behavioral conditions from the system description prompt. The plausible facts are then verified against the behavioral conditions using propositional logic entailment for a finite number of times. The verification results enable the generation of modification prompts that can reduce errors in generated plausible facts, resulting in more accurate PDEVS statecharts. To verify a statechart's logical correctness, its Timed Automata counterpart is manually created and verified for deadlock and reachability properties. The human modeler may regenerate plausible facts and PDEVS statecharts iteratively and incrementally. A basic correctness metric is introduced to quantify the completeness and accuracy of the expected behavioral traits of the PDEVS statechart models. A collection of example systems with varying levels of complexity is developed to demonstrate the capabilities and limitations of LLMs. The evaluation of the proposed verification mechanism shows a substantial improvement in the logical consistency of generated statecharts.
Read the full abstract
Artificial Intelligence · Cross-listed from physics.ao-ph
Generative data assimilation highlights fronts as key regulators of ocean energy cascade
Mesoscale eddies are fundamental to the ocean circulation, yet the extent to which submesoscale motions, a few kilometers across, influence mesoscale eddy energetics through a kinetic energy cascade remains uncertain. High-resolution simulations predict that submesoscale fronts are key regulators of the cascade, transferring energy both downscale towards dissipation and upscale to sustain and shape the seasonality of mesoscale eddies. Testing these predictions has remained difficult because existing observations and state estimates cannot resolve submesoscale currents over sufficiently broad domains. Here we map the ocean's submesoscale energy cascade by combining multi-source satellite observations with a generative deep learning framework, reconstructing gap-free, kilometer-scale surface currents with physically plausible dynamics learned from simulations. Applying this to the eddy-rich Agulhas Current system, we find that submesoscales energize the mesoscale through an upscale energy cascade above 10 km, contributing to the seasonality of mesoscale eddies. Below 10 km, convergence at submesoscale fronts drives a downscale cascade towards dissipation. Both upscale and downscale pathways concentrate within fronts, where cross-scale transfer is up to an order of magnitude more efficient. Despite their limited extent, fronts account for a substantial fraction of the domain-integrated cascade, establishing them as key regulators of the cascade and targets for next-generation eddy parameterizations.
Read the full abstract
Artificial Intelligence
T-LLM Compiler: Trusted LLM-based Code Optimization and Verification Framework
Recent advances in Large Language Models (LLMs) have opened opportunities to apply high-level code transformations to the field of code optimization, and it has since emerged as one of the most fundamental tasks for LLMs to perform; however, at present, LLMs struggle to apply wide-ranging code optimization tasks due to both the complexity of the code and the inability to independently verify the correctness of the transformations. In this paper, we present the Trusted LLM (T-LLM) Compiler, which proposes an advancement in compiler technology through a collaborative effort involving high-level LLM code transformations, traditional compilers, and verification tools. Experimental results reveal that it can significantly improve code correctness when tested on a set of PolyBench/C benchmarks. Our approach facilitates iterative code optimization efforts with verification strategies that enable corrective actions. Through this approach, T-LLM Compiler achieves code optimization accuracy of up to 83.3% and a speedup of up to 16.1% on the PolyBench/C benchmarks, with the transformed code reaching an average of 26.7% speedup wrt standard baselines. Additionally, we release the project's source code to the open-source community.
Read the full abstract
Robotics
Evidence of Absence: Cross-Modal Abductive Risk Perception to Sustain World Models When Vision Fails
A structured world-state (entities, relations, context, and predictive cues) is designed to preserve prediction-critical content when perception degrades, but it presumes observations to populate it; when the primary visual modality is occluded or degraded, those observations may be missing. We address how to sustain the world model from a complementary modality by treating the absence of expected co-evidence as evidence of a hidden cause. The abductive framework is modality-agnostic; this article instantiates it acoustically. A microphone-array front-end estimates the bearing of engine and tire sources and extracts approach-rate evidence (Doppler when a stable tone exists, a broadband looming readout otherwise); the event "signature present, visual co-evidence absent" then triggers abductive inference of a hidden road user, emitting a calibrated risk advisory rather than a control command. Recoverability of the hidden state is analyzed as an identifiability question separating shared from modality-unique information, and cueing is cast as Neyman-Pearson detection under an explicit false-alarm budget. On real occluded-approach recordings at blind junctions, the method warns a mean 1.7 seconds before line-of-sight entry, matches the sustained-window variant of the published acoustic baseline's detection rate with 42% fewer false alarms, localizes to 3.4 degrees median once in view, is well calibrated (expected calibration error 0.034), and keeps hazard awareness above 0.87 under staged vision degradation that collapses a vision-only channel to 0.03. We also measure the method's limits: calibration transfers to an unseen junction almost losslessly, the signature classifier does not, and moving-ego noise is the binding deployment constraint.