Artificial Intelligence
Papers
Fresh from arXiv, typeset properly. Highlighted words trade on the market.
Friday 14 August
Analogies are quaternary relations of the form "a is to b as c is to d", usually denoted a : b :: c : d. This notion is formalized in particular with the notion of proportional analogy, which imposes some constraints on the valid analogies. Whereas proportional analogies have been studied mostly in symbolic domains and in vector spaces, their use is limited in non-Euclidean spaces. In this paper, we introduce a proportional analogy relation in Riemannian domains, extending the parallelogram rule used for arithmetic analogies in Euclidean spaces. We illustrate the introduced analogy on various manifolds, such as the sphere, shape spaces and manifolds of probability distributions.
Hardware Architecture · Cross-listed from math.AG
The Quartic Hessian Conjecture in Dimension Four
The Hessian conjecture asks whether a polynomial with nonzero constant Hessian determinant has a polynomial gradient inverse. It is known in dimensions at most three, false in dimensions at least five, and open in dimension four. We prove its four-variable quartic case. The top homogeneous part has zero Hessian determinant and, by the four-dimensional homogeneous Hesse theorem, is a cone. We divide its cone representative into three exhaustive types: a genuinely ternary quartic with nonzero ternary Hessian, a genuinely binary quartic, and a fourth power of a linear form. In the first type, the degree-seven determinant equation forces the cubic part to be affine-linear in the cone direction. In the binary type, the degree-six equation gives a constant null direction in a two-variable Hessian of the cubic part. In the unary type, the degree-five equation and a constant-direction lemma give the same conclusion. Every type therefore reduces to \[ f=P(x_1,x_2,x_3)+x_4Q(x_1,x_2,x_3)+a x_4^2, \qquad \deg Q\leq2. \] We prove, independently of the degree or top part of \(P\), that every constant-Hessian polynomial of this form has a polynomial gradient inverse. The branch \(a\ne0\) descends from the known three-dimensional Hessian conjecture after a Schur complement. When \(a=0\), an isotropic-cone rank analysis eliminates rank two, solves the rank-one exception by an explicit triangular inverse, and reduces rank zero to the two-dimensional Hessian conjecture. The coupled degree-six identity is retained throughout; no component with respect to a fixed quadratic form is separated.
Read the full abstract
Cryptography and Security
MazeRunner: Nonlinear Task and Clue Orchestration for LLM-driven Black-Box Automated Penetration Testing
Penetration testing is essential yet resource-intensive. Although large language models (LLMs) show promise for automating security auditing, existing agents mainly execute end-to-end workflows in simplified linear scenarios. Real-world black-box testing is fundamentally nonlinear: the attack graph is initially unknown and must be incrementally inferred from environmental feedback. Observations may reveal multiple attack branches, failures are often ambiguous, and critical clues may span long action horizons. Existing agents therefore tend to become trapped in depth-first exploration, misdiagnose failures, and forget prior evidence. We present MazeRunner, an autonomous penetration testing system built on a three-agent task-and-clue orchestration framework. It separates global orchestration, context-intensive execution, and failure-oriented review while persistently maintaining task states and environmental evidence. This design supports action revision, prerequisite recovery, branch switching, and long-range clue correlation. We evaluate MazeRunner on 10 recently released HTB targets, limiting each system-target run to 20 million LLM tokens and preventing target-specific solution leakage. With Claude Sonnet 4.5, MazeRunner completes 47.7% of annotated subtasks, compared with 36.2% for PentestGPT-V2 and 34.2% for Claude Code. It achieves user-level or higher access on six targets, including root access on two; each same-model baseline reaches user-level access on only two targets and never obtains root access. Execution-trace analysis further shows that MazeRunner explores more attack branches and acquires shells more efficiently.
Read the full abstract
Machine Learning
Connected Subspace Clustering: Hardness, a Scalable Heuristic, and an Application to Sea Level Geodesy
Constrained optimization extends classical optimization by integrating side information, making it widely applicable across scientific and engineering domains. Consider a setting where we measure variables at different physical locations. When grouping these measurements, we often want clusters that are both internally similar and physically coherent. Thus, we have a constrained clustering problem where the constraint models coherence. Motivated by an application in geodesy, where contiguous regions of the sea surface must be identified for principal component analysis, we introduce the Connected Subspace Clustering problem: given high-dimensional points and a connectivity graph, partition them into $k$ connected clusters, minimizing their total squared distance to the clusters' best-fit $m'$-dimensional affine subspaces. We prove that, even for $m' = 0$ and a grid graph with holes, the problem is NP-hard to approximate within $\Omega(n^{1/2-\varepsilon})$ for every $\varepsilon>0$, where $n$ is the number of measurements. We then introduce an efficient Lloyd-style heuristic that alternates subspace fitting with an iterative merging procedure to enforce connectivity. Our method returns exactly $k$ connected regions by construction, whereas unconstrained methods leave up to $1{,}966$ disconnected fragments at higher cost. In a study of 160 configurations on global sea level time series, our merging-based repair is the strongest of four strategies in $73.75\%$ of cases, and consistently outperforms competitors such as (connected) Ward's method across all tested cluster counts. The resulting regions isolate signals aligning with climate indices such as the El Nino-Southern Oscillation and Indian Ocean Dipole. Although developed for geodesy, the approach applies to other spatially embedded multivariate time series, such as climate fields, remote sensing, neuroimaging, and sensor networks.
Read the full abstract
Artificial Intelligence
APTER: Adaptive Post-Training with Expert-Grounded Rubrics
As large language models enter professional domains, they must satisfy domain constraints, include critical evidence, and provide complete reasoning rather than merely produce fluent responses. Existing post-training methods often rely on holistic preferences or outcome-level verification, while recent rubric-based methods usually generate rubrics independently for each query. In specialized domains, such unconstrained rubrics may omit critical requirements and vary across samples, hindering the diagnosis and targeted repair of persistent capability deficiencies. We propose APTER (Adaptive Post-Training with Expert-Grounded Rubrics), a framework that integrates structured domain knowledge into fine-grained evaluation, optimization, and diagnosis for specialized complex reasoning. First, expert-grounded rubric construction starts from an expert criteria framework built by domain experts, where each criterion represents a stable professional capability. For each query, APTER selects relevant criteria and instantiates them into query-level rubrics linked to their source criteria, turning reusable expert criteria into executable query-level supervision without reference answers. Second, adaptive post-training uses rubric verdicts as both optimization and criterion-level diagnostic signals. Aggregating low-scoring verdicts by criterion ID reveals persistent deficiencies and triggers targeted supervised fine-tuning updates during reinforcement learning. Experiments on mathematical reasoning and medical question answering show consistent gains across both domains. Across three model generations, APTER improves the mathematics and medical averages over the corresponding base models by up to 15.86 and 8.04 points, respectively. Code and rubric datasets are available at https://github.com/AntDT-APTER/APTER.
Read the full abstract
Machine Learning
Training Fair Tabular Foundation Models
Tabular Foundation Models (TFMs) have emerged as leading methods for tabular predictive tasks, leveraging in-context learning to predict on new data without task-specific training. Despite the increased use of TFMs in high-stakes decision-making, their fairness properties remain largely unexplored. In this work, we incorporate fairness constraints directly into TFM training, enabling fair predictions in a single forward pass. Our approach addresses two key challenges: limited access to sensitive attributes in training data, and the incompatibility of existing fairness techniques with the in-context learning paradigm. We propose FairTFM, a scalable training strategy based on synthetic fairness tasks and a fairness-aware architecture using a gradient reversal layer, which encourages the model to learn representations invariant to sensitive attributes. Experiments on 132 fairness tasks show consistent improvements in fairness while maintaining competitive accuracy.
Read the full abstract
Computation and Language
How Much Do Legal RAG Systems Still Hallucinate?
Hallucination is a major challenge for retrieval-augmented generation (RAG) systems in the legal domain, where ungrounded answers can lead to serious consequences. To better understand this problem, we conduct a fine-grained analysis of hallucination behavior in eight legal RAG systems across two legal corpora, the GDPR (in English) and a national civil law (in French). Using claim-level and answer-level evaluation, we report on hallucination density and severity, analyze performance across question categories and user personas, and validate our findings on an independent set of 142 legal-expert-authored questions. Our results show that hallucinations remain pervasive, ranging from less than 10% of responses for the best-performing systems to nearly half in the worst case. We further find that false-premise questions, containing incorrect assumptions that must be rejected, produce high hallucination rates on the manually-drafted questions.
Read the full abstract
Machine Learning
Adaptive Protection for Evolutionary Feature Construction in Symbolic Regression with Application to Credit Classification
Evolutionary feature construction has shown strong promise in symbolic regression by automatically discovering informative transformations of input features that enhance a simple base learner. However, existing approaches often lack explicit mechanisms to preserve important constructed features discovered during evolution, and valuable genetic material can be lost when genetic operators disrupt effective features. This paper introduces an adaptive protection mechanism that leverages feature importance metrics to selectively preserve constructed features during evolution. The mechanism provides stronger protection for more important constructed features while still allowing less important features to be modified and to incorporate useful building blocks from more important features. We evaluate the approach using multiple feature importance calculation methods and demonstrate its robustness across different base learners. Experimental results on 98 regression benchmark datasets show that the proposed mechanism consistently improves solution quality over baseline approaches, and experiments on two credit classification datasets demonstrate that the method also extends effectively to improve search effectiveness beyond symbolic regression.
Read the full abstract
Robotics
MMUSV-Sim: A Maritime Simulation Platform for Multi-USV Cooperative Perception
Perception from a single unmanned surface vehicle (USV) is limited by sensing range, field of view, and occlusions caused by islands, port infrastructure, and nearby vessels. Multi-USV cooperative perception can alleviate these limitations by integrating complementary observations from distributed viewpoints. However, progress is constrained by the high cost of coordinated sea trials, the scarcity of multi-USV datasets, and the lack of integrated maritime simulation and evaluation tools. We present MMUSV-Sim, a perception-oriented maritime simulation and data-generation platform built on Unreal Engine 5 and Project AirSim. It supports configurable maritime scenarios, synchronized multimodal acquisition across multiple USVs, and consistent 3D annotations in a shared world frame. Using MMUSV-Sim, we construct MarU2U-200m, a synchronized multi-USV RGB–LiDAR dataset with 341 sequences and 14,385 scene frames. We establish a cooperative bird's-eye-view (BEV) vessel detection benchmark with LiDAR and RGB–LiDAR inputs. Experimental results show that Early Fusion improves LiDAR detection AP@0.5 from 64.26 to 81.46 compared with the single-USV baseline. RGB features further improve intermediate fusion, increasing AP@0.5 by up to 4.55 percentage points. LiDAR and RGB transfer experiments also show the value of the generated data as a pretraining source for real maritime detection. The project are available at https://github.com/lizaowo/MMUSV-Sim
Read the full abstract
Artificial Intelligence
FreeBalance: Pre-Routing Online Moe Load Balancing via Residual Workload Prediction
Load imbalance poses a major bottleneck to the efficiency of expert parallelism in distributed inference of Mixture-of-Experts (MoE) models. The most heavily loaded rank stalls global execution due to skewed routing distributions, directly increasing latency. While offline expert placement can alleviate persistent imbalance, practical multi-task serving workloads exhibit layer- and batch-dependent routing dynamics, making online load balancing indispensable. Existing approaches rely on routing statistics collected after each MoE router, requiring expert weight load or migration to begin only after routing decisions are available, consequently placing migration overhead on the inference critical path. In this work, we observe that online balancing can instead be largely overlapped with computation before target routing (e.g., attention), if routing distributions can be predicted accurately in advance. Therefore, we propose FreeBalance, a lossless online load-balancing framework that overlaps expert migration with preceding computation stages via residual workload prediction. FreeBalance leverages cross-layer similarities in hidden representations within the residual network to build a lightweight workload predictor. This enables proactive expert migration planning before routing decisions are available, creating substantial overlap between weight transfer and computation-heavy pre-routing stages. Furthermore, a cost model constrains the number of swaps to fully hide the synchronization overhead within the available window. Experiments across models and datasets show that FreeBalance reduces the max-to-mean rank load ratio by 32.8% and end-to-end prefill latency by 13.1%. Specifically, our method hides balancing overhead of an average of 5.1 experts per layer, which would otherwise account for about 8.5% of the critical-path latency.
Read the full abstract
Data Structures and Algorithms
A Near-Optimal Lower Bound for $\ell_p$-Subspace Embeddings, $1\leq p<2$
For $d \geq 2$, $p \geq 1$ and $\epsilon > 0$, let $N_p(d,\epsilon)$ be the smallest integer $N$ such that for every integer $n$ and every $A\in\mathbb{R}^{n\times d}$, there exists a matrix $\Phi\in\mathbb{R}^{N\times n}$ satisfying $(1-\epsilon)\lVert Ax\rVert_p\leq \lVert\Phi A x\rVert_p\leq (1+\epsilon)\lVert Ax\rVert_p$ for all $x\in\mathbb{R}^d$. For every constant $p\geq 1$ with $p\not\in 2\mathbb{Z}$, when $d\gtrsim_p \log(1/\epsilon)$, the bound \[ N_p(d,\epsilon) \gtrsim_{p} \frac{d}{\epsilon^2 \operatorname{polylog}(d/\epsilon)} \] is established. This improves the previous lower bound $\Omega(1/(\epsilon^2\operatorname{polylog}(1/\epsilon)))$ due to Li et al. (SICOMP 2021) and is optimal up to logarithmic factors for $1\leq p<2$. The central technical idea originated from ChatGPT 6 Pro.
Read the full abstract
Machine Learning
Multimodal Zero-Shot Prediction for Transaction Data at Scale
Sequential financial transaction data are increasingly being used by financial institutions to train payment foundation models at scale, producing rich contextual embeddings that support applications such as fraud prevention, credit risk assessment, and offer personalization. However, such models are not designed for flexible instruction-following reasoning and require bespoke downstream models for each application. In contrast, large language models (LLMs) provide a natural-language interface for flexible transaction reasoning, yet naively serializing transaction histories into text representations is inefficient and costly. Multimodal fusion architectures bridge these paradigms, injecting transaction embeddings directly into flexible language reasoning pipelines. In this work, we present a systematic study of how transaction embeddings, pretrained at the scale of a global payments network, interact with LLM-based reasoning through embedding injection, transaction-language alignment, and instruction tuning. To do so, we train the Multimodal Instruction Network for Transactions (MINT), which combines a transaction encoder pretrained on billions of real-world payments with multimodal instruction tuning on millions of transaction question-answering examples. We evaluate predictive and extractive question answering, zero-shot generalization to unseen question types, and inference efficiency. Our results reveal a consistent trade-off: compact transaction embeddings improve predictive QA accuracy while substantially reducing input tokens, latency, and memory relative to a text-serialized baseline, whereas serialized histories remain highly competitive for extractive QA. Overall, our empirical findings provide a set of actionable insights and practical guidance for building multimodal transaction-aware language systems at network scale.
Read the full abstract
Machine Learning
KV Cache Compression Through the Lens of Transform Coding
The key-value (KV) cache stores information from past tokens and is a major memory bottleneck in long-context inference. Existing quantization methods address this bottleneck by representing the KV cache uniformly with lower-precision data types and designing quantization schemes to minimize reconstruction error in the cache itself, without accounting for how that error propagates through attention mechanisms. We prove that, under a white-noise quantization model, the expected attention-aware distortion decomposes into additive key and value contributions that factor across tokens and channels. Building on transform coding and reverse water-filling, which are classical tools from signal processing and rate-distortion theory, we introduce Attention-Aware Transform Coding (AATC), which allocates bits over a calibration set to minimize attention-aware distortion. On Llama-3.1-8B-Instruct and Qwen-2.5-7B-Instruct, evaluated across LongBench, RULER, GSM8K, MMLU-Pro, and MATH-500, our method achieves near-lossless accuracy at approximately $5.8\times$ compression, whereas each baseline degrades in at least some settings.
Read the full abstract
Machine Learning
Revisiting Energy-based Tabular Anomaly Detection: Energy and Reconstruction are Complementary
Tabular anomaly detection is dominated by classical density-proxy methods (Isolation Forest, OCSVM, LOF), reconstruction-based detectors (Autoencoders, VAEs), and modern non-parametric scorers (COPOD, ECOD, Deep SVDD), all of which approximate the inlier distribution only indirectly; explicit energy-based models are largely absent. Motivated by the recent revival of EBMs in deep learning (e.g., Energy-Based Transformers, JEPA), we revisit the classical Deep Boltzmann Machine (DBM) for this task and hypothesize that its mean-field energy combines more effectively with a reconstruction-based score than same-lineage pairs do. We evaluate a two-hidden-layer DBM on two tabular benchmarks spanning distinct domains (UCI Bank Marketing and NSL-KDD) against eight classical and modern baselines across twenty random seeds. The DBM mean-field energy matches the strongest baseline (the Autoencoder) on Bank Marketing and statistically beats it on NSL-KDD, while significantly outperforming the remaining seven on both datasets. When fused with the Autoencoder via rank fusion, the DBM energy yields a statistically significant improvement on both datasets (AUROC=+0.014, p<0.01 on Bank Marketing; +0.002, p<0.001 on NSL-KDD); every non-DBM-derived base model instead fails to improve or significantly degrades the AE-paired ensemble. Our position is that classical EBMs, exemplified by the DBM, deserve a place in the tabular anomaly detection toolbox as a non-redundant complementary view to the reconstruction-based scores that dominate current practice.
Read the full abstract
Information Theory
Positioning with Flexible Reflectors: Solution and Performance Analysis
Flexible reflectors (FRs) have emerged as a low-cost and energy-efficient solution for reshaping electromagnetic propagation environments across a wide range of applications. This paper investigates FR-swarm-assisted target localization in scenarios where line-of-sight (LoS) paths are unavailable. By leveraging the virtual LoS paths created by the FRs, a simple yet accurate estimator is proposed for localization under severe blockage conditions. To characterize the performance limits of the proposed scheme, we derive the Cramer-Rao lower bound (CRLB) and use it to optimize the positions and orientations of the FRs. Furthermore, by accounting for random FR deployment, we characterize the CRLB distribution and reveal how different network configurations affect localization accuracy. Simulation results demonstrate that the developed scheme closely approaches the CRLB performance, while the derived analytical results provide useful guidelines for FR deployment and network design.
Read the full abstract
Artificial Intelligence
Can Language Models Understand mmWave Data? Benchmarking Large Language Models for mmWave Radar-Based Human Understanding
Large language models (LLMs) have shown remarkable reasoning and generative capabilities, motivating their use as universal reasoning engines for perception. While modern approaches such as vision-language models (VLMs) have attempted to incorporate reasoning capabilities into visual sensing, the integration of LLMs with the millimeter-wave (mmWave) modality-despite its unique advantages under low light and occlusion-remains largely unexplored. The principal bottlenecks stem from the scarcity of radar language pairs, severe cross-dataset heterogeneity, and the absence of a foundational mmWave encoder. We address this gap through a minimal textualization interface that serializes each mmWave point cloud into concise natural language, allowing off-the-shelf LLMs to operate in a question answering (QA) setting. Building on this, we present mmWave-QA, the first benchmark for language-conditioned mmWave human perception. mmWave-QA aggregates heterogeneous public mmWave datasets and harmonizes them via calibration-aware preprocessing and global taxonomy alignment, while providing natural language QA. Spanning six scenarios and five QA tasks, the benchmark enables standardized evaluation across diverse mmWave hardware and experimental conditions, establishing a foundation for scalable research on mmWave-LLM integration. We further evaluate and analyze LLMs on our mmWave-QA, highlighting their zero-shot reasoning potential for radar perception, as well as their robustness under visual degradation.
Read the full abstract
Computer Vision
LightTeaNet: A Weakly Supervised Lightweight CNN for Multi-Label Tea Leaf Disease Detection and Localization
Tea is known as an important crop in many parts of South and Southeast Asia, yet the production of tea is still hampered by the multiple diseases that decrease the quantity and quality. Traditional methods of inspection, which are manual, are not consistent, labor-intensive, and depend on extensive monitoring. This paper introduces a lightweight convolutional neural network (CNN) designed for weakly supervised multi-label classification and disease localization in tea leaves called LightTeaNet. LightTeaNet learns directly from image-level labels and employs Class Activation Mapping (CAM) to localize disease-affected regions automatically, unlike conventional object detection models such as YOLO, which require extensive bounding box annotations. For Parameter efficiency, the network integrates Depthwise Separable Convolutions, and for enhanced feature discrimination, it integrates Channel Attention. LightTeaNet has achieved a Precision of 0.9615, a Recall of 0.8772, and an F1-score of 0.9179, while it shows mAP@0.50=0.1810 without any manual annotations, which delivers a competitive localization performance in the experimental results. These results validate the model as an interpretable as well as a resource-efficient framework for intelligent disease monitoring in agriculture.
Read the full abstract
Machine Learning
Structure-Guided Spatiotemporal Attention Graph Neural Network for Traffic Flow Prediction
Deep spatiotemporal models integrating graph convolutions and attention mechanisms have demonstrated excellent performance in network-level traffic flow prediction, owing to their exceptional ability to capture complex spatiotemporal dependencies. Despite their predictive success, deployment of such models in safety-critical urban systems remains constrained by their inherent lack of transparency. Existing post-hoc diagnostic methods often struggle with spurious correlations and fail to unveil the intrinsic decision-making mechanisms governing traffic dynamics, resulting in suboptimal interpretability and limited operational trustworthiness. To address these challenges, this paper proposes the Structure-Guided Spatiotemporal Attention Graph Neural Network (SGSAN). Departing from traditional architectures that rely on unconstrained adaptive graphs, SGSAN explicitly learns a static Directed Dependency Graph (DDG) to identify the invariant macroscopic propagation paths of traffic states. We further introduce an InfoNCE-based soft-coupling mechanism that anchors the model's dynamic spatiotemporal attention to this structural prior, offering a mechanistic account of the model's decision-making process while ensuring robust forecasting by aligning attention-based reasoning with identified macroscopic dependencies and preventing over-reliance on ephemeral local noise. Furthermore, a decoupled two-stage optimization framework is developed to resolve the fundamental conflict between structural discovery and predictive error minimization. Extensive experiments on multiple real-world datasets demonstrate that SGSAN achieves state-of-the-art predictive accuracy while providing built-in interpretability that organically aligns with the physical logic of traffic networks.
Read the full abstract
Human-Computer Interaction
Physics-Bounded mmWave Sensing for Schedulable, Privacy-Preserving Human Pose Estimation
Millimeter-wave (mmWave) is a promising modality for human pose estimation (HPE) in mobile deployments with strong privacy requirements and limited resources, such as fall detection in bathrooms or activity monitoring in bedrooms, where cameras are inadmissible and computationally demanding processing is infeasible. Although mmWave signals naturally confine human reflections to compact, physically bounded regions, the algorithmic foundations of existing systems fail to provide deterministic execution and accuracy guarantees. They either process the full spectrum uniformly, resulting in unpredictable latency that varies across different scenes, or apply lossy compression that discards vital pose structures. To address this, we present PRISM, a framework that exploits the spatial concentration of RF reflections to achieve schedulable edge HPE. PRISM introduces three core components: 1) Physics-Bounded Integral Processing (PBIP), which restricts computation via constant-time integral queries; 2) Physics-Adaptive Instance Proposal (PAIP), which decomposes scenes involving multiple people into bounded local subproblems; and 3) Deadline-Aware Operation Profiles (DAOP), which provide offline-verified worst-case bounds for runtime quality-latency trade-offs. We evaluate PRISM on four public datasets spanning diverse radar configurations, reporting physical-bound and pose-accuracy measurements across this suite and examining deadline-aware scheduling on multi-person recordings together with an additional single-person set. Under single-threaded isolated execution, PRISM reduces 99th-percentile latency by 24%–58% relative to baselines that miss the deadline, records a 0.0% miss rate on the evaluated traces, and attains the highest pose accuracy among deadline-feasible configurations, providing a practical route toward schedulable mmWave sensing on mobile edge hardware.
Read the full abstract
Computer Vision
Concept Guidance: Precise, Training-Free Latent Control for Text-to-Image Generation
Text-to-image diffusion models have two major drawbacks that severely limit their practical utility: (1) standard models lack an intrinsic mechanism for continuous, concept-specific guidance (e.g., for precisely controlling how aesthetically pleasing an image looks), and (2) they lack reliability for tasks requiring high local coherence (e.g., generating text or human hands). To tackle these issues, we introduce a novel notion of concept-wise mutual information and find large, concept-dependent differences between individual layers, demonstrating that the generation of specific structures is localized in distinct parts of the network. We exploit this insight by reinforcing the impact of concept-relevant layers in Concept Guidance (CoG), a precise, target-specific guidance method that works for models out-of-the-box without additional training, external models, gradients, or prompt engineering. CoG first quantifies each layer's concept-specific impact and then guides denoising using a weighted combination of predictions generated with concept-relevant layers skipped. We demonstrate performance increases across various targets and popular models like PixArt-alpha, SD3, SD3.5, and FLUX.1-dev. Code is available at https://github.com/CompVis/concept_guidance
Read the full abstract
Machine Learning · Cross-listed from quant-ph
Classical Limits of Spectral Filtering in Quantum Generative Models
Spectral filtering has been proposed as a route to regularization in quantum generative models: the quantum Fourier transform exposes the amplitude spectrum of a quantum circuit Born machine, and a diagonal filter suppresses the high frequencies associated with finite-sample noise, an operation whose classical counterpart seemingly requires manipulating an exponentially long amplitude vector. We examine whether this coherent operation produces anything that classical post-processing of samples from the unfiltered model cannot match. Measuring the filter against convolution with a symmetric probability kernel at matched sampling cost, which accounts for the post-selection overhead of attenuation, we derive necessary and sufficient conditions for the gap between the two to vanish. Magnitude (attenuating) filters obey a dichotomy: at a fixed affordability threshold, the filtered output is either a constant-size Fourier object with an efficient classical sampler, or the passband must widen until no fixed frequency is attenuated and the filter no longer smooths. In neither case does the filter create a quantum-classical separation. Whatever separation survives is inherited from the spectral phase of the input state. Numerical experiments on trained circuit Born machines confirm the classification and show that the deciding phases are invisible to the Born-rule training loss and set by the initialization. Within the diagonal family, pure phase filters remain the only spectral operations exempt from these constraints.
Read the full abstract
Game Theory
Optimal Pricing and Charging Strategy Design for Non-cooperative Battery Swapping Stations
Battery swapping is a rapid way to recharge electric vehicles (EVs). As more and more entities are involved in building Battery Swapping Stations (BSSs), how non-cooperative BSSs maximize their profit in a competitive market needs further investigation. In this paper, we focus on a practical scenario where competitive BSSs are coordinated by the same aggregator. To study the optimal pricing and battery charging, we formulate a hierarchical game-theoretic model, where BSSs determine the swapping price in the day-ahead market in the first stage, and then determine the optimal battery charging strategy in the real-time market in the second stage. We rigorously prove the existence and uniqueness of the Subgame Perfect Nash Equilibrium (SPNE). In particular, the uniqueness property provides theoretical support that the strategy under equilibrium is optimal in the competitive environment. Based on the unique SPNE, we propose an optimal pricing and charging strategy for each BSS to maximize profit in the competitive market. A prediction error handling method is also proposed to deal with unexpected fluctuations in swapping demand. Our simulation with a 12-BSS system based on real-life data from Xi'an, China shows that our pricing and charging strategy increases the individual BSS profit by at least 18.1%, while the optimal charging strategy naturally achieves peak shaving for the power grid.
Read the full abstract
Information Theory
Integrated Information in the Active Inference Framework
The active inference framework provides a principled approach to modeling sentient behavior. In this framework perception and action selection are treated in a unified way. The resulting agents form an internal generative model of the relevant dynamics of the world in order to infer their future observations, their internal states and to select actions. We combine this modeling framework with the Integrated Information Theory of consciousness and are therefore able to analyze the active inference agents from the perspective of integrated information. The Integrated Information Theory aims at quantifying the level of consciousness of a system by assessing its capability to integrate information. Here, we define a measure of integrated information for the generative model by making an additional structural assumption. Experiments with simulated agents reveal a correlation between integrated information measures and the free energy of the active inference agents that increases with the size of the generative model.
Read the full abstract
Numerical Analysis
TOGEARI: Interaction-Space Preconditioning for Condensed Finite-Element Systems with IPC Contact
TOGEARI constructs a compressed contact correction for condensed finite-element equations with incremental potential contact (IPC). A core-conditioned interaction matrix ranks contact combinations by their mechanical responses; a raw-factor proxy acquires only the retained responses. For a symmetric positive-definite core, the reference analysis gives the exact spectrum, scaled inverse error and optimal worst omitted interaction. The selected responses are maintained through signed contact changes using supported operator images and a small coarse matrix. A complementary Schur spectrum and perturbation bounds connect this construction to the full current linear equation, damped local Newton steps and compatible episode reuse. On a 325,260-coordinate finger/cup problem, eight selected directions reduce Krylov work from eleven columns to five, matching full contact. Two reversed-order load studies give matching anchored displacements and accepted normal reactions, with 28.8-29.3 percent less warm time and 5.1-5.3 percent less complete time than per-step direct refactorization. A completed twelve-episode run saves 18.8 percent of total time against direct and 2.8 percent against a held factor. Full response caching has comparable time with 7.5 times the response storage. A compressed repeat terminates at an energy line search; separate diagnostics identify constitutive cancellation and terminal-backtracking sensitivity. Larger-contact, held-out-load and frictional comparisons show where compression or preparation loses its advantage. The complete Newton equation remains the residual operator throughout; the convergence guarantees retain their stated reference and local hypotheses.
Read the full abstract
Artificial Intelligence
BiasTrace: Linking Reasoning Behaviours to Biased Outputs in LLMs
LLMs exhibit social biases that can produce inaccurate and discriminatory inferences, posing risks in high-stakes applications. While prior work has made progress in measuring and mitigating bias, it largely focuses on final outputs of models, with limited understanding of the mechanisms that produce biased outcomes. Recent advances in LLM reasoning offers a new lens for investigating bias, yet the link between reasoning and bias remains poorly understood. Existing approaches focus primarily on final answer correctness or explicitly biased language, overlooking different behaviours in reasoning that can drive biased outcomes. We introduce BiasTrace, an annotation scheme for labelling reasoning behaviours in model-generated traces and linking them to biased outcomes. BiasTrace captures bias-specific behaviours (e.g., unsupported demographic assumptions) as well as general reasoning patterns that may implicitly contribute to bias (e.g. overthinking). We apply BiasTrace to reasoning traces in bias-sensitive contexts, scaled using validated LLM-as-a-judge methods, producing a large annotated dataset. Our analysis shows that biased outputs often stem from subtle reasoning behaviours rather than explicitly biased language, and that reasoning-level annotations improve bias detection. We further show that BiasTrace behaviours can be exploited for inference-time mitigation. These findings underscore the importance of examining a broader range of reasoning patterns to better understand bias in LLMs.
Read the full abstract
Robotics
OccPlanner: Goal-Aware Occupancy-Conditioned Diffusion Planner for PixelGoal Navigation
PixelGoal navigation specifies targets directly in the agent's camera view, providing a natural interface between high-level visual reasoning and low-level navigation. Depth can lift a visible target pixel into a metric PointGoal, but this estimate becomes unreliable under occlusion or sensor noise. Moreover, a PointGoal alone does not encode traversability or feasible paths around obstacles. We present OccPlanner, a goal-aware occupancy-conditioned diffusion planner that learns complementary egocentric goal and planning-oriented 3D representations through metric target and occupancy prediction, respectively. These representations condition a diffusion trajectory module to generate target-directed, obstacle-aware trajectories. For scalable geometric supervision, we introduce L3ROcc, which converts monocular RGB navigation videos into aligned 3D occupancy and trajectory annotations. We train OccPlanner on L3ROcc-processed InternData-N1 and evaluate it in closed-loop simulation across four unseen InternScenes categories and two goal-distance ranges. Across all eight settings, OccPlanner substantially outperforms existing open-source PixelGoal approaches and achieves competitive performance against PointGoal planners with direct metric-goal inputs.
Read the full abstract
Artificial Intelligence
Removing Temporal Note Redundancy Improves Multimodal Reinforcement Learning for Medicine
Mechanical ventilation is a critical life-support intervention, requiring dynamic adjustments to ventilator settings as a patient's condition evolves. While reinforcement learning (RL) offers a promising framework for optimizing these sequential decisions, standard approaches rely primarily on structured electronic health record (EHR) data, missing crucial clinical context recorded in free-text notes. Integrating longitudinal clinical notes into RL state spaces is challenging because notes are heavily inflated by temporal redundancy, such as copy-forward text, templating, and repetitive documentation, which dilutes time-local updates and degrades state representation quality. To address this, we propose a redundancy-aware multimodal state representation framework that explicitly removes duplicated note text over time before policy learning. We evaluate two computationally efficient temporal decomposition strategies for removing duplicated note text: (1) an embedding-space decomposition using singular value decomposition on local history subspaces, and (2) an interpretable sentence-level diff operation that filters out previously documented sentences before text encoding. Using real-world ICU data, we demonstrate that state representations constructed by stripping temporal note redundancy significantly outperform both structured-only and raw-note baselines across multiple off-policy evaluation methods (Model-Based Rollouts, Fitted Q-Evaluation, Weighted Importance Sampling, and Weighted Doubly Robust Evaluation). Our findings show that explicitly isolating new clinical information from repeated note text yields higher-quality state representations and directly improves RL performance for clinical decision support.
Read the full abstract
Machine Learning
Deep Reinforcement Learning solution for pickup and delivery routing problems with time window and capacity constraints
The task of constructing vehicles optimal routes for pickup and delivery of goods is one of most promising tasks in the context of global urban population growth. Although this kind of problems with small size can be solved by various classical approaches, a fast (or realtime) route optimizer under the constraints of the real world (such as capacity and time windows constraints) for medium-large size problems still remains a highly challenging task. In this work we, for the first time, successfully applied a deep Reinforcing Learning approach (modified JAMPR model) to solve Pickup and Delivery problem with Capacity and Time Window constraints (CPDPTW). We obtained a robust model that gives a fast optimal solution for problems of small and medium size, and gives fast suboptimal solution for problems of larger (> 200) size.
Read the full abstract
Artificial Intelligence
Towards Efficient Multimodal and Multilingual Opinion Extraction for STI: A QLoRA-Based Fine-Tuning Approach
Recent advances in large language models (LLMs) have reshaped semantic analysis. Opinion Extraction (OE) for Science and Technology Intelligence (STI) requires concise core opinions from large information streams. Off-the-shelf models struggle to filter noise from these streams and show limited structured-output reliability in zero-shot multilingual and multi-modal settings. To address information overload and extraction defocus, this study proposes a multimodal core-opinion extraction framework in which visual evidence serves as a contextual anchor for textual judgment. Using VideoLLaMA2 (VL2) and VideoLLaMA2.1 (VL2.1) as the base models, we apply Quantized Low-Rank Adaptation (QLoRA) fine-tuning on a curated dataset of 2,194 multilingual and multimodal samples. Under the selected Image-Augmented setting, fine-tuned VL2.1 generates structured JSON core-opinion outputs, achieving 64.98% Precision, 42.15% Recall, 51.14% F1-score, and 74.00% sample-level accuracy. Relative to the zero-shot VL2.1 setting, it raises the F1-scores of Spanish and Russian from 4.83% and 0.45% to 46.05% and 51.93%, respectively. The framework further incorporates a Fuzzy Cumulative Prospect Theory-based post-extraction triage module for case-level value assessment, providing a case-level value signal for downstream STI screening.
Read the full abstract
Computation and Language
Leading-Silence Augmentation and Multi-Stage Synthetic Supervision for the Second MLC-SLM Challenge
The second Multilingual Conversational Speech Language Model (MLC-SLM) Challenge evaluates two tasks over complete, unsegmented multilingual conversations: speaker diarization and recognition (Task 1) and conversational speech understanding (Task 2). Neither task provides oracle utterance boundaries or speaker labels at evaluation, and Task 2 provides no question-answer training set. For Task 1, we fine-tune VibeVoice-ASR-7B with random leading-silence cropping, consistent timestamp correction, and an exponential moving average (EMA) training strategy. For Task 2, we construct synthetic question-answer pairs through multimodal candidate generation, silent-audio filtering, and distribution-matched augmentation, and fine-tune Qwen3-Omni-30B-A3B-Instruct for tagged direct answering. On the Task 1 evaluation set, cropping reduces tcpMER from 18.30% to 17.27%, and EMA further reduces it to 16.73%. On the Task 2 evaluation set, jointly applying distribution-matched augmentation and tagged direct answering raises accuracy from 83.0% to 86.0%.