Computational Engineering
Papers
Fresh from arXiv, typeset properly. Highlighted words trade on the market.
Tuesday 18 August
Gray elements and material overlaps at the interfaces limit density-based multi-material topology optimization. This article extends the level set-based negative-mapping interpolation to the multi-material proportional topology optimization of macro-scale structures in two and three dimensions. An alternating active-phase algorithm decomposes M-phase problems into two-phase sub-problems described by level set functions; an evolutionary strategy removes the need for sentitivity analysis; and the negative-mapping interpolation eliminates the overlaps of the phases in the interface elements. Cantilever and half-MBB beams in two dimensions and a cantilever beam in three dimensions, with three and four material phases, give smooth boundaries, no gray elements and overlap-free designs. The compliance lies below the SIMP value in four of the eight two-dimensional cases and 0.3%, 0.4%, 4.8% and 12.7% above it in the other four. The influence of the material properties, of the interface treatment and of the algorithmic parameters is also examined.
Robotics
PRISM: Precision and contact-rich Real-world Industrial Skill dataset with Multimodal sensing
Recent progress in robotic learning has been fueled by large-scale datasets collected in everyday environments. However, most existing datasets emphasize short-horizon, low-contact tasks such as pick-and-place, and therefore do not capture the precision control, force/torque or tactile regulation, and multimodal feedback required for industrial assembly. To address this gap, we introduce PRISM, a large-scale multimodal dataset for contact-rich industrial operations. The dataset spans more than 25 manipulation tasks (e.g., electronic components plug/unplug, conveyor-based sorting) and covers diverse mechanical constraints. PRISM includes more than 5,000 trajectories totaling 45 hours of teleoperated demonstrations, recorded using synchronized multi-view RGB-D, force/torque, tactile, and robot-state measurements. In contrast to datasets collected in household or laboratory settings, PRISM provides a realistic benchmark for multimodal perception and control under high-precision industrial constraints, and serves as a foundation for contact-rich, generalizable manipulation in real-world manufacturing environments. The dataset is open-sourced at: https://tengbo-yu.github.io/PRISM/
Read the full abstract
Cryptography and Security
COMA: A Compositional Misleading Attack Class on Security-RAG, and a Causal Counterfactual Defense
Every document a security copilot retrieves can be true, instruction-free, and non-contradictory — and the copilot can still be driven to assess a critical, exploitable vulnerability correctly and then recommend a remediation that leaves it open. We study this failure in retrieval-augmented generation (RAG) backing analyst-facing copilots in Security Operations Centers, and identify a class of attacks, \emph{\compmis{}} (COMA), in which every adversarial document is factually correct, instruction-free, non-contradictory, and distributionally benign — yet the answer is misled by their composition. We realize \compmis{} through action-corruption, which steers a correctly-diagnosed vulnerability toward an inferior remediation, and verdict-flip, which destabilizes the exploitability verdict via an undecidable reachability chain. Action-corruption bites all five tested models — including frontier reasoning models — on every run, on two synthetic domains and a real CVE (CVE-2021-33813); verdict-flip bites stochastically, decreasing with model capability but never vanishing. A single principle governs both: the attack succeeds when the disambiguating fact must be inferred rather than read. We propose \ccd{} (Causal Counterfactual Defense), an audit that measures the leave-one-out causal influence of each retrieved document and flags answers whose influence concentrates on low-trust documents. \ccd{} localizes the attack to attacker-controlled documents with no false positives on four benign multi-document controls; an adaptive influence-spreading adversary is caught by an aggregate variant. We release attack seeds and a \ccd{} reference implementation.
Read the full abstract
Artificial Intelligence
Towards Zero-Shot Task Transfer with Neurosymbolic World Models
State-of-the-art model-based reinforcement learning methods learn neural world models that allow policy improvement by planning in a latent space, without assumptions on the structure of the underlying environment. While expressive, these models are generally task-dependent: they learn uninterpretable latent representations that are tied to the training task and thus hard to generalize to new tasks. In this work, we present a novel world model formulation where the reward prediction only depends on a subset of structured, symbolic components of the whole latent state. Decoupling observation reconstruction and reward prediction allows us to learn world models that can adapt zero-shot, i.e. without further environment interactions, to new reward functions defined over the same symbolic state space. We discuss the main advantages and challenges of learning these neurosymbolic world models and demonstrate the strong generalisation properties of our approach over purely neural methods.
Read the full abstract
Information Theory · Cross-listed from math.ST
A First-Order Entropy Law for Canonical T-Complexity of Finite-Alphabet i.i.d. Sources
Let $W_N$ be an exact length-$N$ block from a strictly positive i.i.d. source $\mathbf p$ on a fixed finite alphabet. We prove that the canonical T-complexity $c_T$ satisfies \[ \frac{c_T(W_N)}{e^{-\gamma}h(\mathbf p) N/\log N}\longrightarrow1 \] in probability and in $L^r$ for every fixed $1\le r<\infty$, where $h(\mathbf p)$ is the source entropy in nats and $\gamma$ is the Euler-Mascheroni constant. The proof combines an exact length budget for canonical recovery, a critical-scale $E_1$ estimate for an ideal backward chain, and an exact finite-block boundary representation. An exact Doob-transform identity expresses the finite-boundary law relative to the ideal law conditioned at each step to avoid the current history-dependent successor codeword. A history-uniform renewal estimate then makes the telescoping endpoint density uniformly asymptotic to one, so no one-step approximation errors accumulate.
Read the full abstract
Machine Learning
Understanding the Surprising Generalization Properties of Tabular Foundation Models
Tabular Foundation Models (TFMs) increasingly rely on in-context learning, where a model receives labelled examples at inference time and predicts labels for new inputs without updating its weights. Existing TFMs are typically trained on either massive synthetic corpora or very large collections of real datasets. In contrast, we show that surprisingly strong transfer can emerge from self-supervised pre-training on just a single real table. In this setting, we also find that tables tend to be either broadly useful or broadly poor regardless of downstream prediction task, and that the strongest predictor of usefulness is the number of features rather than the number of instances. This leads to a task-centric interpretation of tabular pre-training: the number and the quality of tasks are essential for the pre-training of TFMs. We show that the same task-centric perspective can help corpus design at scale: fine-grained column-level pre-processing consistently improves downstream performance, while no improvements are observed when we filter or deduplicate at the dataset level. Finally, we offer a new perspective for how TFMs generalize: we believe that tabular in-context generalization is largely retrieval-based, and good models are those that learn to identify relevant examples in the provided context and aggregate them well. The mechanics of TFMs have been relatively understudied; our task-centric, retrieval-based perspective offers a new framework to guide future model and corpus design.
Read the full abstract
Machine Learning
An Omitted Mode Is a Rare Rule: The Sampling-Verification Danger Law in Continuous Code World Models
In the Code World Model paradigm an LLM synthesizes an executable world model that a classical planner searches, and the model is accepted when it reproduces sampled transitions. We ask what that acceptance certifies in continuous control. We define the pipeline's danger as an expected risk and isolate its exact factor: the probability that N i.i.d. gate rollouts all miss a critical event of probability r is exactly (1-r)^N; an independent acceptance sample adds its budget to the exponent. On three hybrid instruments the accepted mode-blind model is exploited: the planner is pinned at the mode boundary at a regret of nearly the whole attainable return. We prove a localization budget, valid at boundary points: models with Lipschitz constant at most L differing by eta at a point disagree above tolerance eps on a region of volume at least kappa((eta-eps)/L)^(d+m); the discontinuous reset modes studied pay no such budget. With real LLM synthesis, GPT-5.x repairs an omitted 1D clamp in 105 of 111 mode-containing draws – every attempt exact on 50 of 56 instrument-stream blocks (95% CI [0.781, 0.960]). On 2D regions no artifact recovers the rule (0/156); eight targeted interventions leave the failure in place, and positive controls locate it: a located rule is not induced, while given form and location the constants follow exactly. A version-space certificate proves identification is class-relative: at the widest dose the declared fit succeeds in 20/20 blocks and every sample-consistent circle is within tolerance in 18/20. We prove a class of entry rules exactly consistent with every sample yet harmless at play, so identifiability is a measurable property of the instrument. Re-scoring all 1034 artifacts on independent samples confirms acceptance certifies sample consistency and no more: where the gate is provably informative it covers about two percent of the exploited planner's queries.
Read the full abstract
Computation and Language
Do Large Language Models Play Six Degrees of Separation? Measuring Topological Compression in Long-Context Manifolds
Large Language Models (LLMs) demonstrate remarkable multi-hop reasoning capabilities over long contexts, yet the internal mechanisms enabling these distant cognitive leaps remain poorly understood. Traditional attention-based interpretability often fails to capture true semantic proximity due to routing artifacts like attention sinks. In this paper, we bypass attention weights to directly analyze the dynamic geometry of the hidden state manifold, proving that deep LLM latent spaces natively organize into Small-World networks. By sparsifying the continuous similarity matrices of long-context representations into unweighted graphs, we trace the connectivity between highly disjoint semantic anchors across two distinct architectures. Our findings reveal a sharp topological phase transition: while early syntactic layers remain entirely fractured, deep reasoning layers abruptly compress massive conceptual distances into highly navigable pathways strictly bounded by the "Six Degrees of Separation" limit (=< 6 semantic hops). Furthermore, we demonstrate the practical efficacy of this framework by applying it to zero-shot hallucination detection within Retrieval-Augmented Generation (RAG) using the RAGognize dataset. We show that factually grounded generations maintain structural integrity with their source context (approximately 3 hops), whereas hallucinations induce severe topological collapse. Ultimately, this work mathematically formalizes how transformers execute abstract reasoning and provides a novel, strictly geometric signature for evaluating factual reliability.
Read the full abstract
Information Theory
Tail exponents of conditional guesswork via the method of types
We study the problem of guessing a realization of an i.i.d. random sequence given element-wise correlated side-information. We use type-counting to provide estimates of the tail probabilities of the number of guesses for the case without side-information, which was shown earlier through large-deviation techniques. We then extend the same counting argument to the conditional setting, obtaining new explicit expressions for the corresponding guesswork exponents as divergences involving conditional tilted distributions. Finally, we provide an application of these exponents to brute-force password guessing with side-information.
Read the full abstract
Machine Learning
SIGMA: SHAP-Guided Implicit-Trajectory Generation for Metadata-Free LLM-Based AutoFE
Recent research has leveraged Large Language Models (LLMs) to enhance Automated Feature Engineering (AutoFE) through semantic descriptions and trajectory-based prompting. However, there exist two challenges that limit their applicability and scalability in long-horizon optimization: (1) semantic metadata is unavailable in many practical settings, and (2) trajectory accumulation increases the risk of exceeding the context window, while without it, the generation process can become unstable, leading to becoming stuck in the local optima and a high duplicate rate of generated features. To this end, we propose a SHAP-enhanced Implicit-trajectory Generation for Metadata-free AutoFE (SIGMA), a scalable constant-context optimization framework. SIGMA leverages SHAP values to provide task-aware signals for guiding group feature generation instead of semantic information. In addition, we adopt an EXposed-feature Implicit Trajectory (EXIT) approach, where the exposed features in the prompt implicitly represent the trajectory. Empirical results demonstrate that SIGMA achieves performance comparable to the state-of-the-art (SOTA) LLM baselines with a nearly constant prompt length. Notably, EXIT significantly reduces the duplicate ratio of generated features from 37.2% to 6.8%. At the same time, SIGMA matches traditional SOTA performance with only 5.4 features on average, demonstrating substantial efficiency gains in feature utilization.
Read the full abstract
Artificial Intelligence
Procedural Content Metageneration via Program Search and Continual Abstraction Discovery
Large language models can generate executable programs, which makes it possible to search directly over procedural content generators rather than individual levels. We study this approach in Sokoban, Zelda, Dangerous Dave, and Lode Runner. Each run evolves complete Python generators through language-model mutation and crossover. We introduce Continual Abstraction Discovery, or CAD, which extracts reusable primitives from high-fitness programs into a run-specific helper module. A 2x2 experiment crosses CAD with access to a fixed hand-written domain API. The completed data set contains 160 complete runs, with at least ten 50-generation runs in every cell. CAD raises mean final best fitness in all eight domain and API comparisons. Across all CAD runs, learned libraries are adopted by most later programs and repeatedly rediscover validation, reachability, and structural utilities. These results support that discovering reusable primitives improves evolutionary program search for content generators.
Read the full abstract
Computer Vision
Cross-Domain Generalization in Machine Unlearning via Label-Conditioned Energy Magnitude Regularization
Machine unlearning removes the influence of specific data from a trained model. However, most methods treat the forgotten concept as isolated. In this paper, we study what happens to the rest of the model when a class is forgotten, using a label-conditioned energy-based model (EBM) that assigns per-class energies, making the effect directly observable. We forget a class by raising the energy of its image-label pairs, training with a forget term, a retain anchor to the pretrained model, a global margin, and an energy regularizer that stops the energy magnitudes from growing without limit. A propagation term applies the same forget signal to retain samples, weighted by each sample's DINOv2 similarity to the forget class, so forgetting reaches images that resemble it and leaves the rest untouched. We evaluate on two benchmark datasets: 1) On a subset of DomainNet across four visual domains, we forget tiger, lion, and scissors one at a time. Forgetting a class in the sketch domain also erases it from real, clipart, and painting, with forgetting error reaching 98% and 99% for lion and scissors, and the effect carrying over to the most similar class. 2) On CIFAR-10, we turn off the propagation term and forget each of the ten classes on its own. Forgetting is complete (100%), while the other nine classes retain 98.5% of their pre-unlearning accuracy on average.
Read the full abstract
Machine Learning
Efficient RLVR Scheduling via Graph-Structured Online Difficulty Estimation
Reinforcement learning with verifiable rewards (RLVR) improves the reasoning capabilities of large language models but relies on costly rollout exploration. Assigning the same exploration budget to samples with different difficulty levels is inefficient: easy samples may receive redundant rollouts, whereas difficult but learnable samples may receive too little exploration. Existing adaptive schedulers address this mismatch through curriculum-based sample selection or non-uniform rollout allocation based on estimated sample difficulty. However, obtaining reliable online difficulty estimates remains challenging: dedicated probing adds substantial generation overhead, whereas history-based estimators face a cold start with no initial observations and stale feedback, and typically ignore relations among samples. To address these limitations, we propose a plug-and-play graph-based online difficulty estimator that shares rollout feedback across related samples and continuously updates their difficulty estimates, mitigating cold start and staleness without dedicated probing. Specifically, we first construct a difficulty-aware sample graph based on semantic and reasoning similarities. Based on this graph, we introduce latent difficulty states and use a Potts prior to encourage neighboring samples to share the same state. We then employ a state-level Beta-Binomial model to aggregate the rollout outcomes associated with each state. Finally, we use an online mean-field variational algorithm to continuously update the latent-state assignments and state-level difficulty as new feedback arrives. Our framework can be integrated into sample-selection and rollout-allocation schedulers, enabling difficulty-adaptive exploration without dedicated probing. Experiments across multiple base models, RL schedulers, and benchmarks demonstrate that our framework achieves better performance.
Read the full abstract
Systems and Control
Policy Iteration for Linear-Quadratic Stochastic Differential Games with State- and Control-Dependent Noise
This paper presents a novel sequential policy iteration (PI) method for stochastic differential games with state- and control-dependent noise. The updates preserve mean-square stability, so that the iteration is well posed. We further derive a closed-form expression for the Fréchet derivative of the sequential PI map at a Nash equilibrium. The resulting characterization reveals how control-dependent noise, policy-evaluation sensitivity, and update ordering govern local error propagation, and yields explicit sufficient conditions for local linear convergence. Since finding an initial stabilizing solution is a major challenge in policy iteration, we also propose a homotopy-based initialization that ensures a valid starting point. The effectiveness of the proposed PI algorithm and the analytical results are verified through a numerical example.
Read the full abstract
Systems and Control
Infinite-Horizon Inverse Linear-Quadratic Differential Games with State- and Control-Dependent Noise
This paper presents a method to solve the inverse problem for N-player infinite-horizon linear-quadratic (LQ) differential games with state- and control-dependent noise. For this stochastic setting, we derive necessary and sufficient conditions for linear feedback Nash equilibria, which take the form of coupled stochastic algebraic Riccati equations. We then derive a kernel representation of these equations to explicitly characterize the set of all cost function parameter combinations across players that are consistent with observed equilibrium trajectories, thereby solving the associated inverse problem. Numerical results illustrate the approach and confirm the theoretical findings, highlighting the inherent ambiguity of the inverse problem.
Read the full abstract
Computation and Language
Grading Needs a Rubric, Not Intelligence
Small language models can grade open-ended examination answers as reliably as substantially more expensive models when they grade against an explicit rubric. We test this claim as the design principle behind any-to-bench: a frontier model reads source documents once, at ingestion, to extract each question and its rubric; lower-cost models then perform all repeated grading work. We evaluate six cost-efficient model configurations from two model families at three reasoning-effort levels. Each configuration answers 24 open-ended examination questions, and each also grades every answer sheet three times, yielding 3,456 per-question grades. Scores depend overwhelmingly on the answer being graded: answer identity explains 95.6% of score variance, whereas judge identity explains only 0.2%. Raising a writer's reasoning effort moves earned scores by as much as 0.143 of full marks, while raising a judge's reasoning effort moves assigned scores by at most 0.006. Six frontier-tier judges, added as a check, reproduce these scores and are no more reliable as a panel. Two ablations then decompose the rubric on the same questions and answers. Removing its criteria and levels while keeping the official answer changes nothing measurable. Removing the official answer as well collapses reliability (ICC 0.888 to 0.628), inflates scores, and makes judge reasoning effort matter again. The rubric is what decouples grading from judge intelligence, and within the rubric the official answer does nearly all the work. We find no evidence of length preference or same-family preference under rubric-anchored grading.
Read the full abstract
Computer Vision
Beyond Instrument Motion: Recognizing Tissue Tension Toward Surgical Skill Assessment
Surgical performance assessment in minimally invasive surgery largely relies on manual expert review, making it time-consuming, subjective, and difficult to scale. While existing surgical video understanding methods address tasks such as instrument segmentation, surgical phase recognition, and action recognition, they do not explicitly capture fine-grained tissue handling, a key indicator of surgical quality. To address this gap, we introduce tissue tension recognition, a new clinically motivated video understanding task for laparoscopic and robot-assisted rectal cancer surgery. To support this task, we construct SurgTension, the first expert-annotated tissue tension dataset, providing a benchmark for objective tissue tension recognition. We further propose TensionTRAC, a lightweight trajectory-based framework that models tissue tension from sparse point trajectories. Using a compact trajectory encoder, TensionTRAC achieves competitive performance against strong pretrained video backbones.
Read the full abstract
Systems and Control
A Coalitional Game for Demand-Side Management in a Micro-Grid with Multiple Electricity Retailers
This paper develops a demand-side management framework for electricity networks with multiple competing retailers. The interaction among retailers is formulated as a coalitional game, yielding a family of coupled mixed-integer optimisation problems in which retail prices, consumer power demands, and the network partition are jointly optimised. To solve this problem, we propose a coalition-formation algorithm based on multi-objective optimisation principles. The algorithm seeks to identify coalition structures that balance retailer profit and consumer welfare. We prove that the proposed algorithm converges in a finite number of steps and recovers a subset of weakly Pareto-efficient solutions of the coupled optimisation problems. The framework is further extended to a risk-sharing formulation, in which the objective is defined using conditional value-at-risk. Numerical simulations on an academic example demonstrate the method's behaviour and show that the resulting equilibrium partition set contains several admissible trade-offs between the competing objectives. The results provide a tractable approach for analysing competition, coalition formation, and risk-aware pricing in multi-retailer demand-side management systems.
Read the full abstract
Artificial Intelligence
EvoTS-Agent: A Self-Evolving LLM Agent for Financial Time Series Change Point Detection
Financial time series exhibit non-stationary and heterogeneous statistical properties, making change-point detection challenging because no single unsupervised algorithm performs consistently across assets and market regimes. Conventional workflows consequently depend heavily on expert-driven model selection, feature design, and hyperparameter tuning, limiting their scalability and adaptability. We propose EvoTS-Agent, a validation-guided self-evolving LLM agent for autonomous financial time-series change-point detection. EvoTS-Agent first performs curated exploratory data analysis to characterize dataset properties and initialize candidate detection models. It then evolves executable experiment trajectories through three complementary operators: Revision exploits the current best solution, Alternative Strategy explores fundamentally different modeling directions when progress stagnates, and Recombination synthesizes complementary evidence from high-performing trajectories. Validation feedback guides trajectory evolution throughout the search, enabling the agent to adapt its detection pipeline to the statistical characteristics of each dataset while preserving reliable optimization. Experiments across four benchmark datasets demonstrate that EvoTS-Agent consistently outperforms existing LLM-based agents while maintaining a 100% execution success rate across all evaluated backbone LLMs.
Read the full abstract
Multiagent Systems
Collective Counterfactual Planning: Coordination, Consent, and Verification under Representational Constraints
Groups routinely complete projects that no single member can plan, execute, or verify alone. We propose a formal model of this phenomenon, Collective Counterfactual Planning (CCP), in which the binding limitation on each agent is neither capability, knowledge, nor observability, but representational geometry: each agent perceives the state, conceives moves, consents to actions, and certifies goal requirements only through a projection onto an agent-specific subspace of a common task space. Four gates jointly determine whether a team can reach a conjunctive goal and legitimately recognize that it has done so: the exogenous implementation coalitions required to perform each action, together with three representational gates – conception, consent, and task-relative verification qualification. We define the Collective Counterfactual Solvability (CCS) problem, separating geometric feasibility, executable attainment, and validated completion. The results expose a positive-negative duality. Iterated cross-agent relay can unlock a solution that no one-shot pooling of individual plans contains, but any goal requirement depending essentially on the subspace dark to the entire team is unverifiable and therefore not validly completable, even when the trajectory accidentally attains it. Memoryless and audited consent further constrain different objects – action directions versus cumulative trajectory states – and neither dominates the other. A four-step exhaustive horizon-bounded solvability scheme is sound and complete under exact representation of the relay closure; restricted implementations remain sound on returned plans but need not be complete. The model gives one geometry for sequential mutual enabling, competent execution of steps whose purpose is invisible to the executor, forced sub-teaming at expertise boundaries, and completion that cannot be validly declared.
Read the full abstract
Computation and Language
SpeechSense: A Paralinguistic-Focused Dataset for Fine-Grained Speech Sentiment Analysis
Recent advances in AI have revolutionized speech processing, yet effective speech understanding requires discerning not just what is said, but how it is said. Speech Sentiment Analysis plays a critical role in decoding these paralinguistic cues for diverse real-world applications such as recruitment and customer service. However, existing Speech Sentiment Analysis research faces two primary limitations. First, dominant approaches rely on text-centric pipelines that cascade Automatic Speech Recognition with text analysis. This process inevitably discards essential acoustic features like prosody and tone, failing to capture attitudinal meanings in acoustically ambiguous utterances. Second, current benchmarks suffer from a mismatch in label granularity, prioritizing basic emotions (e.g., happy, sad) over the nuanced interpersonal stances (e.g., confident, impatient) necessary for social sensitivity. To address these limitations, we propose a novel dataset, SpeechSense, for fine-grained speech sentiment analysis. Specifically, we define a specialized 8-class taxonomy of interpersonal stances detectable primarily through prosodic cues beyond lexical content alone. We then construct a curated dataset based on this taxonomy, built from high-fidelity speech synthesis and rigorous human validation. Comprehensive experiments across multi-modal LLMs, text-only LLMs, and speech encoders demonstrate that models with acoustic access consistently outperform text-only baselines. These results empirically validate the primacy of acoustic cues in detecting subtle speaker attitudes, highlighting the necessity of SpeechSense. Dataset and supplementary materials are available at https://github.com/Sher13cked/SpeechSense.
Read the full abstract
Graphics
Love Handles: Decimation for Deformation Handles with Compact Support and Low Memory Footprints
Estimating the deformation of solids via physical simulation is an important problem spanning fields such as computer animation, engineering and robotics. Such simulations are computationally expensive and scale poorly when the representation of an object is refined by increasing the level of discretization. Reduced Order Methods (ROM) offer computational savings by decreasing the number of degrees of freedom, for example by using handles that control groups of vertices. We present the first decimation-based algorithm for computing a sparse, compactly supported set of deformation handles. The crux of our method utilizes iterative algebraic simplification to optimize handle deformation to match any input deformation, such as linear vibration modes. This applies to any volumetric input mesh, including those with high genus or porous features, since we do not alter the geometry. We also devise an efficient algorithm to compute and update compact supports and their associated weights. We leverage compact support to develop an efficient, reduced-cubature computation scheme. Once optimized, our handles offer a memory-efficient solution while enabling real-time elastodynamics simulation of complex geometry. We show real-time performance on a variety of tetrahedral meshes with up to 796,623 tetrahedra.
Read the full abstract
Artificial Intelligence
Adaptive Policy Portfolios for Robust Markov Decision Processes
Robust Markov decision processes optimize one policy against a set of plausible transition functions. This can be conservative when the unknown dynamics are fixed and become partially identifiable after deployment. We study adaptive policy portfolios: finite sets of memoryless randomized policies synthesized offline and paired with a lightweight online selector. Robust regret is a natural measure of portfolio quality: for each plausible environment, it measures the loss of the best portfolio member relative to the policy that would have been optimal had that environment been known. Related regret objectives were studied by Ghavamzadeh et al. (2016) with an emphasis on approximations and relaxations for safe policy improvement. We give a complexity-theoretic account of portfolio certification and synthesis. Certifying a given portfolio is $\forall\mathbb{R}$-complete already for deterministic portfolios in acyclic (s,a)-rectangular RMDPs. Synthesizing a portfolio of unary-bounded size is $\exists\forall\mathbb{R}$-complete for general rational polytopes, even with fixed discount and acyclic dynamics. The single-policy case is already hard, both combinatorially and algebraically. Finally, we present an offline portfolio construction that is amenable to runtime specialization.
Read the full abstract
Multiagent Systems
A Theoretical Framework for Parallel Lifelong MAPF Using Group Decentralized Planning
In the Lifelong Multi-Agent Path Finding (L-MAPF) problem, agents must repeatedly move from one destination to another while avoiding obstacles and inter-agent collisions. Widely regarded as one of the highest-performing solutions to this problem is the Rolling-Horizon Collision Resolution (RHCR) framework. However, commensurate with its quality solutions, it incurs a computational cost that limits its applicability to even modest agent counts. In this paper, leveraging theoretical methods from the Locally Interdependent Multi-Agent MDP literature, we first theoretically prove the near-optimality of RHCR in a discounted MDP formulation of the L-MAPF problem. Then, we leverage these results to naturally motivate an extended framework called Group Decentralized RHCR (GD-RHCR) which incorporates a group decentralized structure that partitions agents based on a transitive communication scheme and plans for each partition of agents in parallel. We show that both RHCR and GD-RHCR achieve similar exponentially close to optimal guarantees, establishing a theoretical duality between the time based restrictions performed by vanilla RHCR and the additional space based partitioning performed by GD-RHCR. Lastly, we show that across varying maps, GD-RHCR is able to attain high throughput that scales into higher agent counts while maintaining a significantly lower per plan cost.
Read the full abstract
Computer Vision
PerFact: Perception-Derived Fact Prompting for 3D Brain MRI Report Generation
Radiology report generation has matured almost entirely on 2D chest radiographs, where the default route to better reports is a larger backbone or a pre-training one on medical data. We revisit that assumption on 3D multi-sequence brain MRI, a volumetric multi-disease regime, and find that the model is not the lever. Zero-shot medical and radiology vision-language models transfer poorly to brain MRI, with chest radiograph specialists failing most conspicuously, and five backbones fine-tuned identically across three model families and an order of magnitude in scale differ only marginally. What determines the quality of the report is the information injected into the prompt. We delegate perception to upstream 3D segmentation and classification, serialize their outputs into a structured fact sentence, and prompt a LoRA-adapted vision-language model with it; we call this PerFact. In a controlled study that fixes the backbone, data split, target reports, and adaptation while varying only the injected grounding, perception-derived facts outperform retrieved prior reports, retrieval becomes redundant once facts are present, and end-to-end predicted facts remain effective without any ground-truth annotation at inference. The residual gap between predicted and oracle facts is explained by the granularity of the facts rather than by the generator. Closed-ended visual question answering comes at no measurable cost to report quality, though the grounding source has little effect on it. On 3D brain MRI, grounding information, not model choice, is the dominant controllable factor in report quality.
Read the full abstract
Systems and Control
Steady-State Equivalent Circuit Model for Data Center Loads
Planners currently represent data centers as aggregate constant-PQ or ZIP loads in steady-state interconnection and contingency studies. These aggregate models are computationally convenient. However, they obscure the electrical relationship between computational workloads, server utilization, and grid-side demand. They ignore the internal power-electronic conversion stages of IT loads and assume homogeneous workload distributions across the compute clusters. This hides operating-point-dependent converter losses and efficiency variations. We propose a steady-state equivalent-circuit model (ECM) for data centers, which explicitly builds circuit models for IT loads, power supply units, cooling, and auxiliary systems. For power supply units, the equivalent circuit model explicitly represents internal power-electronic conversion stages. For IT loads, we develop a utilization-dependent server power model, and we combine it with loss-aware ECMs of power supply units. This approach captures the grid-side impact of heterogeneous workload distributions while preserving compatibility with conventional power-flow analysis. We evaluate this data center ECM in large-scale transmission power flows, using Monte Carlo simulations under heterogeneous and homogeneous cluster utilization. In comparison with the fixed-efficiency constant-PQ model, the ECM predicts that the most stressed line exceeds its thermal limit in about 30% of Monte Carlo samples. The results further show that homogeneous server utilization overstates line-loading variability by 17%-46% relative to heterogeneous server utilization, depending on the intra-cluster workload correlation.
Read the full abstract
Numerical Analysis
From complex-step differentiation to a general reconstruction framework
The complex-step method is traditionally derived from the Taylor expansion of an analytic function and is widely used as a numerical technique for derivative approximation. We present an alternative formulation based on the Cauchy–Riemann equations and show that the classical complex-step relation arises naturally from the harmonic structure of holomorphic functions. In particular, the complex-step method admits two complementary harmonic interpretations: as a Cauchy problem, in which the derivative is identified with the normal datum of the imaginary component on the real axis, and as a reconstruction problem in a strip, in which the finite imaginary perturbation provides the upper-boundary data. The latter formulation leads explicitly to the strip Poisson and conjugate Poisson kernels and their derivatives. A related harmonic reconstruction framework in the upper half-plane leads to the Poisson, conjugate Poisson, and Cauchy kernels as elementary reconstruction operators for harmonic and holomorphic functions. Extending this reconstruction from ordinary boundary functions to finite measures yields the classical Stieltjes transform and its inversion formula. The same measure-theoretic structure appears in spectral theory, where scalar matrix elements of the resolvent are Stieltjes transforms of the associated spectral measures. These results establish a common complex-analytic structure connecting complex-step differentiation, harmonic reconstruction, Stieltjes inversion, and spectral reconstruction, while distinguishing the boundary-value problems through which the corresponding information is recovered.
Read the full abstract
Computer Vision
AppendiGrade: An XAI-Enhanced Deep Learning Framework for Grading Appendicitis in Ultrasound with Gaussian Blur and Grad-CAM
Appendicitis is one of the most common abdominal emergencies worldwide and requires prompt diagnosis and treatment to prevent life-threatening conditions. However, accurately differentiating complicated cases, such as perforation or abscess formation, from uncomplicated appendicitis remains a significant clinical challenge. Among other methods, ultrasound is a safer and more cost-efficient diagnostic technique because of the lack of radiation exposure. In this research, an advanced system capable of automatically detecting complicated appendicitis from ultrasound images was developed. A dataset consisting of 4679 ultrasound images with 5 classes, namely perforated, abscess, acute, appendicolith, and normal, was used for the proposed model training and testing. Four pretrained deep learning models, DenseNet201, InceptionV3, ConvNextTiny, and VGG19, have been employed for detecting and classifying complicated appendicitis. In the initial configuration, InceptionV3 achieved the second highest accuracy, with a value of 69.21%. Owing to suboptimal performance with raw images, further optimization techniques, including image preprocessing, hyperparameter tuning, model fine-tuning, and image sharpening, were applied. These enhancements significantly improved the model's performance, with an accuracy of 95.58% for InceptionV3. The model performance is then explained with gradient-weighted class activation mapping (Grad-CAM), which creates a heatmap of the regions responsible for the model's prediction of the infected areas. This could make crosschecking with experts much easier.
Read the full abstract
Human-Computer Interaction
Analysis of Types of Inquiries in Student-AI Interaction: A case study of two CS2 tasks
Background and Context: Question and inquiry are integral parts of knowledge seeking and learning. Despite their importance, students tend not to ask enough questions in the classroom. However, studies have shown that students interact extensively with generative AI systems for learning and problem solving. Objective: In this paper, we seek to better understand the types of questions that students ask AI systems, and how those questions evolve during problem solving and across tasks. Method: We use the Graesser et al. taxonomy to classify students' inquiries into 18 types. We develop a few-shot learning approach to automatically classify students' interactions with AI into these categories. We use this system to analyze 830 interactions of CS2 students across two programming tasks. Findings: Our results suggest that a small subset of question types accounts for the majority of student inquiries, and that the types of questions students ask change substantially as the task progresses.
Read the full abstract
Computer Vision
Comparative Study of Out-of-the-Box Technology for Automatic Target Detection and Recognition
Automatic Target Detection and Recognition (ATD/R) is critical for military decision support and (semi-)autonomous operations. Recent advances in object detection and artificial intelligence (AI) significantly boosted the potential performance of ATD/R. However, the scarcity of publicly available military datasets limits the application of these systems. As a solution, this paper explores the use of publicly available models and civilian datasets to achieve reasonable performance in military contexts. We benchmark several state-of-the-art models, including six iterations of the YOLO series and two variations on the DETR framework, on a newly acquired military relevant dataset. This dataset features military vehicles and challenging circumstances, including various degrees of occlusions and small targets. The out-of-the-box version of each model is validated alongside a version finetuned on the VisDrone dataset. This dataset features small objects, an Air-to-Ground (A2G) perspective and relevant classes, potentially generalizing to our military ATD/R task. We compare the performance of the models using mAP@0.5 and mAP@0.5:0.95, across A2G and Ground-to-Ground (G2G) perspective, target size and model size, giving insight into the real-time capabilities of models. Our main findings are: (1) bigger models outperform smaller models, (2) DETR-based models show promising results compared to the YOLO series,(3) fine-tuning models on an out-of-domain A2G dataset, improves their A2G performance and slightly improves their performance on small objects, but (4) all models still struggle with detecting small objects in an A2G scenario. We conclude that, despite recent advances in object detection, in-domain training is still crucial for creating capable ATD/R systems.