Papers

Layer-skipping methods for efficient LLM inference decide, at some granularity, which transformer layers to execute for a given input. We present a rigor-matched, three-seed audit of two periodic-step, search-based methods that make this decision online at inference time and re-evaluate it every few generation steps: a confidence-gated early-exit baseline (ConfLayers) and genuine self-speculative decoding (SWIFT, Xia et al. 2024), together with vanilla autoregressive decoding, across Qwen2.5-0.5B and Qwen2.5-1.5B (Yang et al. 2024) on GSM8K (Cobbe et al. 2021) and CNN/DailyMail (Nallapati et al. 2016; See et al. 2017). SWIFT is strongest on accuracy in three of four cells, while ConfLayers is dominated everywhere, with particularly large deficits on GSM8K at 1.5B. Separating online-search overhead from pure inference cost, we find that SWIFT's true inference speed is faster than ConfLayers's in all four cells (5-21%), reversing the naive wall-clock ranking in three; ConfLayers's search overhead is small and stable (1-2% of cost), whereas SWIFT's is larger and more variable across seeds (up to 28.7%). We additionally examine two trained routing methods, LayerRoute (Sikdar, 2026), a per-sequence, input-conditioned hard gate, and LayerDrop (Fan et al. 2020), a fixed, input-independent pruning pattern, as a supplemental analysis rather than a head-to-head comparison because both operate at a coarser decision granularity. Under a verified protocol with genuine per-input gating, a genuine full-model baseline, and genuine inference-time compute skipping, both show modest real speedups (1.08-1.33x) but accuracy well below the periodic-step methods, including near-total LayerRoute collapse on GSM8K at 1.5B (0.003 mean exact-match across three seeds). We release the full audit protocol as a template for rigor-matched efficiency comparisons.

Ensuring a safe virtual reality (VR) experience requires systems that can predict and respond when users lose their balance. Although prior work has examined fall prediction and motion sickness, many approaches are regression-based and postural state classification remains less explored. This study compares machine learning (ML) and deep learning (DL) models for classifying postural states in VR under visual perturbations. We used a multimodal dataset containing kinematic, electromyographic (EMG), and electrodermal activity (EDA) signals. The data were prepared for a binary task to distinguish balanced from imbalanced postural states, and participant-wise downsampling addressed class imbalance. All models were evaluated with Leave-One-Participant-Out (LOPO) cross-validation to test generalization to unseen participants. Among the models, the Mamba-inspired CNN (MI-CNN) achieved the highest accuracy of 96.76%. SHapley Additive exPlanations (SHAP) analysis improved interpretability and identified the most influential classification factors. The SHAP results showed that kinematic features were dominant, indicating that body-motion patterns are informative for detecting imbalance in VR. We also evaluated MI-CNN using only the top two-thirds of features ranked by SHAP importance. Despite a 33% reduction in input dimensionality, the model maintained performance, achieving 0.957 accuracy and 0.957 F1-score, with about a 1% decrease compared with the full-feature model. These findings suggest that multimodal sensing, temporal deep learning, and explainable AI can support reliable classification of balance-related instability in VR. Accurate recognition of imbalanced postural states may raise awareness of fall risk and guide safer, adaptive VR systems that respond to instability while improving user safety and experience. Code is available at: https://github.com/NipaAnjum/MI-CNN.

We show that smooth two-layer feed-forward networks (FFNs) expose an additional structural model extraction channel under a chosen-input raw-output oracle at the FFN branch; consider transformer FFN branches with GELU or SiLU activations under chosen-input raw-output access, without access to parameters, gradients, or internal activations; exploit a second-order leakage channel in which projected input Hessians form different mixtures of the same hidden symmetric rank-one factors induced by the FFN input weights. We formalize resulting Hessian collection as a partially symmetric decomposition to establish conditions for local identifiability and stability to exploit vector-output stencil reuse to reduce the structural query cost by a factor of 16. On independently trained CIFAR-10 vision transformers, only 16 projected Hessians, corresponding to 8193 black-box queries, recover the hidden FFN directions with average absolute cosine alignment above 0.91, with 86.7.1 % of GELU and 91.1 % of SiLU directions exceeding 0.90 alignment. Recovery remains high across independently trained models, repeated extraction runs, and all transformer blocks. The recovered structure supports functional extraction too. Keeping the recovered directions fixed and fitting only the remaining FFN parameters yields high-fidelity substitutes with more than 92 % top-1 agreement, while test accuracy remains within 1.24% and 0.57% of the GELU and SiLU targets. Output rounding and Gaussian noise substantially reduce recovery under a fixed attack configuration, but adapting the finite-difference step restores average alignment to 0.9188 and 0.9081. This is an end-to-end path from black-box second-order observations to hidden FFN-structure recovery and functional replacement. Under the stated oracle model, smooth FFN curvature exposes internal parameter geometry that behavioral fidelity alone cannot reveal.

Independently trained neural networks tend to encode the same data with similar latent geometries. These latent geometries are not directly compatible, yet they can be nearly the same up to some class of transformations. While there exists many methods for alignment between different latent spaces, it is typically done using a set of shared sample correspondences, known as anchors. This leaves a fundamental question: are the geometric signatures of different latent spaces representing similar data sufficient to recover an alignment between them? To that end, we introduce HGA (Hyperspherical Gaussian Alignment), a method that directly optimizes a transformation between two latent spaces by maximizing a geometric measure of "fit" between them. Since it is driven by the geometry of the latent spaces rather than paired data, HGA can operate in both an unsupervised and weakly supervised regime. On tasks such as model stitching or multilingual word embedding correspondence recovery, HGA manages to match supervised results with minimal or no supervision.

Cryo-electron microscopy (cryo-EM) determines the structures of proteins and macromolecular assemblies at near-atomic resolution, and the final 3D reconstruction depends on extracting a clean particle stack from noisy micrographs. This extraction decomposes into three sub-tasks, namely particle picking, contamination removal, and 2D class selection. Each of them, however, is trained and evaluated in isolation, and none is optimized for the reconstruction. We instead integrate the three sub-tasks into a single pipeline posed against downstream reconstruction quality. We instantiate the pipeline with a state-of-the-art component for each sub-task, CryoTransformer picking permissively, MicrographCleaner masking contamination, and CryoSift selecting 2D classes by a continuous quality score, and close the loop with a fine-tuning step that returns the surviving particles to the picker. The pipeline achieves a better 3D resolution than every picker we compare. We also show that the best 2D F1 is not the best resolution, so particle selection is better treated as one reconstruction-aware pipeline judged by the map it delivers.

We conducted an interview study with twelve students on their use of generative AI in academic communication. Students delegated professional messages to AI most where the pressure to sound professional is highest: email to instructors and administrators. AI involvement ranged from correcting the writer's own text to working out and writing the message outright, and students checked AI-written text against two criteria: whether it looks like AI and whether it sounds like them. Building on these findings, we model the AI-mediated process of writing a student–instructor email at the highest level of involvement we observed, and compare it with an unaided model of writing the same messages, built from participants' accounts and a classic model of the writing process. Three differences emerge: the learning loop that builds writing skill is removed, the message is no longer written for its specific recipient, and the confidence a successful exchange returns goes to using the system rather than to the writer's own ability. From these differences we derive two risks, that individual capacities never form and that authenticity and trust in communication become work. Design can respond to both but is unlikely to be enough, so the risks also need research and policy attention.

Biological knowledgebases traditionally rely on expert, professional curation of the research literature to maintain up-to-date collections of data organized in machine-readable form. However, despite the increasing amount of curatable biomedical knowledge, support for knowledgebases is declining, leaving these resources no alternative but to explore additional ways of updating and maintaining content. One way in which knowledgebases have addressed this problem is by engaging researchers to help curate their published papers, a process generally known as 'community curation'. As helpful as community curation can be, though, it is not universally adopted and, for groups that do have it, there is a wide range of approaches. To learn about existing community curation pipelines and explore possibilities for working towards a common approach, we organized a workshop, Maximizing Community Curation for the Benefit of All, at the 18th International Biocuration Conference, hosted by the Stowers Institute for Medical Research. Our aim was to examine the different strategies that groups use, share successes, failures, and ongoing challenges, and produce suggested deliverables for broader adoption of common best practices and tools for effective community curation. Representatives from 18 different resources, ranging from model organism and specialty knowledgebases to journals and literature resources, presented their work. The result was a comprehensive assessment of the state-of-the-art for community curation and an in-depth discussion on how community curation can become standard practice for maintaining timely, highquality biological resources that will continue to provide scientists with the essential information they need for their research.

While Large language models (LLMs) incorporate user personalization signals to improve usability and helpfulness, they increasingly shift from providing balanced, informative responses toward optimizing for user satisfaction when conditioned on personal context such as conversation history, inferred preferences, and user profiles. Specifically, we identify three emerging risks: (1) irrelevant personalization, where models reference personal information in unnecessary contexts; (2) preference narrowing, where models reinforce informational echo chambers; and (3) sycophantic bias, where models agree excessively with user opinions. As a result, models may reference personal information in contexts where it is unnecessary, inadvertently collapse response diversity, or agree excessively with user opinions. Despite the growing use of personalization in AI assistants, there has been limited systematic evaluation of its potential side effects. To bridge this gap, we propose PRISK, a dynamic evaluation framework with automated data generation and tailored metrics that uncovers systematic limitations in current LLM personalization and how personalized information shapes its responses. Our empirical analysis across 13 LLMs demonstrates the presence of user profiles and retrieved memories consistently exacerbates biases, resulting in an average drop of 45.9% in irrelevant personalization, 41.7% in preference narrowing and 61.7% in sycophantic bias.

We propose BlobBoards, a fiducial marker system comprising a dense, multi-scale field of Gaussian blobs and a feature-based pipeline for joint detection, identification, and pose estimation. Each board is registered from hundreds of blob features whose dense spatial coverage constrains pose, while multiple scales preserve detectability across large changes in focal length, distance, and obliquity. Learned local descriptors are matched to the reference pattern and spatially verified, so the correspondences determine pose and certify identity. Against motion-capture ground truth, BlobBoards achieve median translation errors of 3.6-5.0 mm, reducing AprilTag's median translation error by 89% on small boards and 70% on large ones. They also produce far fewer large-rotation failures than state-of-the-art tag systems. BlobBoards achieve the highest detection rate, 80% versus 74% for AprilTag and 58% for ArUco, with the largest margin on the smallest markers. Under 50% occlusion, they still detect 69% of boards with essentially unchanged median translation error, while AprilTag and ArUco detect none. In experiments BlobBoards give state-of-the-art detection rate, pose accuracy and occlusion robustness.

Representation learning begins when training changes the features that define similarity between data. A frozen-kernel model only reweights a fixed geometry. We establish quantum signal processing (QSP) as a solvable quantum model of the representation-learning regime. At arbitrary depth, we compute the exact mean and variance of its quantum neural tangent kernel, revealing an input-dependent angular geometry whose diagonal remains non-self-averaging even when the underlying unitary approaches Haar randomness. We also prove a sparse-data guarantee for the full nonlinear gradient flow without freezing or ensemble-averaging the kernel: the realized dynamics converges to an integrable scalar flow with a time-dependent kernel closure and explicit convergence times. A finite-depth speed limit holds for every data set and trajectory. At higher data density, numerical results show coupled evolution beyond both the scalar and frozen-kernel descriptions. These results give a controlled theory of learned quantum data geometry with provable training dynamics beyond the frozen limit.

We establish quantitative convergence to the target and uniform-in-time propagation of chaos for Langevin-regularized Stein variational gradient descent. The Stein interaction need not be small relative to the confining Langevin drift and does not generally yield a contractive particle coupling. At the mean-field level, the Stein and Langevin components dissipate the same relative entropy in the kernel-induced Stein and $2$-Wasserstein geometries, producing the squared kernel Stein discrepancy and relative Fisher information. Under a log-Sobolev inequality for the target, this yields exponential last-iterate convergence. We also derive a finite-particle entropy identity relative to the product target, giving exponential-in-time convergence of the empirical measure up to polynomial sampling errors. For propagation of chaos, we develop two complementary finite-time approaches. A synchronous coupling, combined with exponential moment estimates for the nonlinear mean-field diffusion, yields explicit single-exponential bounds in Wasserstein distance and kernel Stein discrepancy (KSD). Moving-product entropy gives joint-law relative entropy control relative to the evolving mean-field product law and, through entropy superadditivity and concentration, fixed-marginal relative entropy and total variation bounds and empirical KSD estimates. Under an additional $T_2$ inequality for the initial law, it also yields Wasserstein bounds. Combining these finite-time estimates with target convergence at a logarithmic cutoff time gives polynomial uniform-in-time propagation of chaos rates in expectation for empirical KSD and $W_2^2$, and for fixed-marginal total variation and $W_2^2$. All bounds control the last iterate in physical time. We also compare the two finite-time mechanisms and identify regimes in which each gives the sharper polynomial exponent.

The Park-Ravani construction generates a twice continuously differentiable, frame-invariant spline on SO(3) by exponentiating cubic canonical-coordinate polynomials. We show that the construction transfers, without changing form, to the group of orthogonal dual tensors, a representation of rigid displacements. The transferred recurrence is stated compactly through the dual extension of the right Jacobian of the exponential map and its first Fréchet derivative. This yields interpolation of prescribed rigid poses and continuity of the body dual twist and its first derivative. Using the higher-order rigid-body kinematics of dual spatial twists, we then prove that the resulting curve has a continuous physical acceleration field, not merely a continuous quantity obtained by formally differentiating the dual part of a twist. We also distinguish algebraic dual transfer from temporal differential prolongation: their simultaneous first-order use takes place in a hyper-dual algebra, and interpolation of arbitrary prolonged nodal data need not be holonomic. A noncommuting three-pose example verifies the recurrence, all knot continuity statements, and dimensional covariance under a change from meters to millimeters. We define and analyze the first-order holonomy defect of a generic hyper-dual interpolant, exhibit an exact counterexample, and remove the defect by cubic or quintic Hermite interpolation in dual logarithmic coordinates.

Currently, in biological systems Neural Correlates of Consciousness (NCCs) are characterized in terms of EEG and FMRI signals. Unfortunately, this characterization prevents the transferability of the NCCs concept to machines. Such transferability would be useful in order to investigate AI consciousness. In this paper we provide an alternate characterization that is transferable, and enables the analogous definition of Machine Correlates of Consciousness (MCCs). Specifically, we propose that NCCs (MCCs) are substrate-level signals that are not under human (AI agent) control, and that are reliably modulated by emotions. This paper presents the first empirical investigation of MCCs. Specifically, we present the results of experiments conducted with two LLMs, Llama-2 7B and Llama-3.1 70B parameters. In these LLMs we collect hardware anomaly traces that are substrate-level indicator-sequences. And we show that after controlling for confounding factors, these are modulated differently by emotional and neutral computations. And this difference is statistically significant for the larger Llama-3.1 70B, but not for the smaller Llama-2 7B. The results constitute initial empirical evidence that MCCs are present in the Llama-3.1 70B configuration. And they are consistent with the hypothesis that consciousness probability and degree increase with the LLM sophistication. Independently of consciousness, MCCs can also be used for detection of emotions in AI agents.

Artists coordinate human pose, illumination, and camera placement to convey narrative and emotion, but existing generative methods typically model these elements independently. We introduce text-to-editable 3D staging, a task that jointly generates human poses, a dominant light, and a camera configuration from an affective description. We construct 11,911 text–staging pairs from 2,328 figurative paintings by reconstructing SMPL bodies, estimating low-frequency illumination, recovering camera parameters, and pairing each scene with ArtEmis descriptions. We train a flow-matching transformer that supports variable numbers of figures and produces multiple staging alternatives for each prompt. On held-out descriptions, the model achieves 32.2% retrieval R@1, compared with 16.6% for CLIP-based nearest-neighbor retrieval, while approximately preserving corpus-level diversity. These results demonstrate the feasibility of generating editable, emotionally conditioned 3D staging references from text.

Most scientific discoveries justify their significance by filling holes between existing ideas and arguments. Representing knowledge as high-dimensional concept embeddings, we use persistent homology to detect scientific holes of increasing order, from lower-order gaps between disconnected ideas to higher-order cavities within unevenly connected ones; then we identify the research that fills them. Researchers who close holes draw outsized collective attention, staging novelty that the citing literature rewards, most strongly in discovery-oriented fields and least in design-oriented fields. Closing a hole is followed by persistent work on the same combinations of concepts at many times the rate of comparable holes left open. Yet as knowledge grows, higher-order holes explode while the fraction of research that fills them collapses, leaving most higher-order combinations unexplored. These results call for a richer science of holes and mark a frontier where contemporary AI might help fill the gaps human science opens.

Computational pathology (CompPath) is transforming medicine by leveraging artificial intelligence (AI) algorithms to support diagnosis, prognosis, and treatment prediction from gigapixel whole-slide images. Clinical adoption is progressing, but is constrained by concerns about safety, accountability, and regulatory oversight in high-stakes clinical environments. Explainable AI (XAI) systems hold promise for building trust and enabling verification, yet the literature remains fragmented due to inconsistent terminology, overlapping methodological families, ad hoc validation, and current reviews. This review aims to formalize XAI methods in CompPath through the: i) introduction of a pathology-centric vocabulary comprising seven core terms; ii) development of a taxonomy across methodological families and three orthogonal axes (stage, type, scope); and iii) establishment of a task-driven framework that maps five clinical questions to recommended methods, method evaluation, and deployment context. Five key gaps between current XAI capabilities and clinical deployment are identified, and actionable steps are proposed to advance XAI for CompPath.

Open Large Language Model (LLM) research increasingly produces compact and derived artifacts, such as adapters, quantized checkpoints, merged models, and distilled variants, that are distributed across papers, model hubs, model cards, code repositories, and release statements. Although these artifacts are publicly visible, digital libraries often lack sufficient evidence to identify, preserve, and cite them as coherent scholarly objects. We introduce a framework that conceptualizes curatability as a record-level property of distributed scholarly records and operationalizes it through four evidence dimensions: artifact identity, scholarly linkage, upstream evidence, and release assets. Guided by this framework, we conduct the first collection-scale characterization of open LLM curatability using a May 2026 snapshot of 191,375 public Hugging Face repositories and a core corpus of 2,214 scholarly papers. Our results reveal a pronounced visibility-to-curatability funnel. While 90.7% of paper records contain at least one useful curation signal, only 18.1% combine usable upstream evidence with concrete release evidence, and only 6.1% provide sufficiently coordinated evidence to support high-curatability records. Based on these findings, we derive a minimal seven-field curatable record and complementary responsibilities for model hubs, scholarly indexes, and digital libraries, providing practical guidance for improving the preservation and bibliographic control of open LLM artifacts.

We describe our submission to Task A of the 1st DAFx parameter estimation challenge. The task is to recover the six physical parameters of a simulated metal-plate reverberator – its dimensions and material properties – from a single impulse response (IR). We treat this as a black-box optimization: candidate parameter sets are fed to the simulator and scored by a loss against the target IR. The method has two stages. The first uses CMA-ES, an evolutionary optimizer, to recover five of the six parameters, comparing IRs under an amplitude-normalized loss. Amplitude normalization makes the search robust but discards the cue to the sixth parameter, the plate's surface density; a second stage therefore estimates it alone, with a ternary search on the un-normalized loss. As the choice of loss strongly affects the search, we select it beforehand, and analyze why compression in the common multi-scale spectral loss degrades recovery. Finally, we test our method on a validation set of 50 IRs, discuss a pathological failure mode, and ablate to justify having two different stages instead of a unified CMA-ES search.

Converting scientific figures into executable code has gained increasing attention, yet existing methods primarily focus on reproducing the reference figure itself. A more practical setting is to plot new data while preserving the visual style of a reference figure (e.g., color scheme and typography). Prior approaches mimic the reference through pixel-level optimization and struggle to carry its style to new data. We show that the key to this task lies in the coordinate grounding and coding capabilities present in modern computer-use models. We propose FigMirror, an agentic framework that unlocks these capabilities through Grounded Measurement, which locates visual elements by coordinates and measures their properties through executable code. We further introduce PlotTwin-Bench, an expert-curated benchmark with fine-grained code and image-level style metrics. Experiments show that FigMirror consistently outperforms existing methods on reference-conditioned style transfer. All plots in this paper are generated by FigMirror, except those produced by other methods for comparison. Our code and data are available at: https://github.com/VILA-Lab/FigMirror.

We show that a certified formalization of the hitting-set-existence axiom of Atserias and Tzameret, instantiated on the parity-based Nisan-Wigderson compression class of Khaniki, is independent of the two-sorted theory $V^0_1$ of $\mathrm{AC}^0$-reasoning, unconditionally: $V^0_1$ proves neither it nor its negation. The same holds for the corresponding certified dual weak pigeonhole principle, whose refutation is witnessed by a single seed that certified-computes every string of the model simultaneously. The mechanism is a bounded-arithmetic transfer of Atserias-Tzameret's reduction from hitting sets to the dual weak pigeonhole principle: the amplification half of that reduction, the sole source of its NP-oracle, is unnecessary at the native stretch of the Nisan-Wigderson map, and the compression half becomes a $V^0_1$-provable implication once circuit evaluation is replaced by its certified $\Sigma^B_0$ unfolding. This is, to our knowledge, the first independence result for a derandomization-flavoured existence principle at the $\mathrm{AC}^0$-reasoning level, and it makes explicit the bridge between the Khaniki Nisan-Wigderson line and the Atserias-Tzameret reverse mathematics of hitting sets.

Variational quantum algorithms (VQAs) suffer from unstable optimization due to temporal noise drift and static qubit mappings that distort gradient signals across iterations. We present BAHAMAS, an online control framework that stabilizes noise exposure by adaptively selecting physical mappings via consensus-based fidelity estimation, without requiring simulators, offline training, or prior executions. Across real quantum devices, BAHAMAS improves optimization reliability and supports inference-time retargeting under drift through robust, per-iteration control.

Extreme low-bit inference offers a route toward smaller models and constrained deployment. Ternary language models restrict weights to $\{-1,0,+1\}$, approaching the limit of $\log_2 3 \approx 1.585$ bits/weight. The practical question for a pretrained model is not simply whether weights can be quantised but which capabilities survive and whether it remains useful for adaptation. We explore this by converting Qwen3.5-0.8B (752M parameters) to ternary weights using 72.4M tokens of quantisation-aware training (QAT). The resulting model, Cloe, is evaluated across 29 benchmarks, representation diagnostics, and downstream fine-tuning. The evidence shows non-uniform degradation. A linear probe recovers 43.76% of MMLU answers from the full-precision teacher's representations but only 26.19% from Cloe (near chance), indicating specialist factual information is lost. However, Cloe retains measurable performance on ten tasks, averaging 77.1% of teacher performance. Crucially, fine-tuning raises Cloe to 89.8% on SST-2 (95.6% of the matched teacher) and reaches 79.4% teacher retention on XSum. We attribute degradation to a combination of quantisation-induced information loss and incomplete recovery due to the limited QAT budget. We also highlight an evaluation pitfall: standard answer-letter scoring failed (Cloe emitted "A" on 98.6% of MMLU questions), necessitating continuation scoring. Ultimately, ternary conversion is unsuitable as a drop-in general replacement yet remains valuable as a compact substrate for task-specific models.

Sparse autoencoders (SAEs) disentangle model activations into interpretable features and are widely used for steering large language models. Most existing SAE-based steering methods select features by applying a top- filter based on statistical scores, assuming that higher-scoring features yield stronger steering effects. In this paper, we show that this assumption is often invalid, leading to suboptimal feature selection. Our analysis reveals that effective steering features may be distributed among representationally adjacent, semantically similar groups induced by feature splitting in SAEs. Within such groups, features may exhibit disparate statistical scores despite having comparable steering influence, causing score-based selection to overlook important features. Based on these observations, we propose Neighbor Integrated Feature Selection (NIFS), a plug-and-play strategy that leverages representation similarity to improve feature selection for steering. We evaluate NIFS across multiple SAE-based steering methods and tasks, and demonstrate consistent performance gains over conventional top-$k$ selection.

The efficient market hypothesis, that prices reflect all available information, imputes a meaning to market moving information, a view of information foreign to standard information theory. Here, after reviewing properties that make a proposed formula for “pragmatic information" a plausible measure of meaning, we consider the role that the receiver's position in the machine hierarchy corresponding to the Chomsky hierarchy play in extracting this meaning. We show that a receiver at a given level in the hierarchy may be unable to extract pragmatic information from a message because it appears random, yet a receiver at a higher level in the hierarchy finds the message perfectly intelligible. Also, the maximum processing rates for messages of different levels of hierarchy serve as a kind of channel capacity, leading to a tradeoff between the amount of pragmatic information extracted and the extraction time. All of the above suggests a recasting of market efficiency in terms of “computational efficiency”, i.e. the question of whether a market appears efficient to a participant with a given computational endowment. Successful trading strategies implementable as finite state machines, the lowest level in the hierarchy, imply departures from “finite state efficiency”. We show, via a stylized example, how pragmatic information can characterize the ensuing approach to finite state efficiency. We also show that actual market dynamics can be more computationally intractable than any finite state machine can process by proving the PSPACE-completeness of the processing of the smart order routing systems of major brokerage firms. We conclude that computational efficiency is the norm and pragmatic information can characterize any departure from it.

Facial appearance editing powers popular applications like FaceApp and Photoshop. Generative Adversarial Networks (GANs) and 3D Morphable Models (3DMMs) have been widely used for facial editing. GANs can perform varied facial edits (e.g., changing hair color, hairstyle), but often produce unstable edits. 3DMMs produce stable edits, but can only alter pose and facial expression. Recently, text-guided diffusion models like Nano Banana have become popular for image editing. Text-guided models are a compelling alternative to GANs and 3DMMs since they can produce both stable and varied image edits. While text-guided models have been widely tested for whole-scene edits (e.g., “make the woman play a guitar”), they have not been comprehensively tested for facial editing. We conducted the first large-scale evaluation ($\sim1$M images evaluated) of six popular text-guided models on a sequential facial editing task. We present Face-Edit-Attributes, the largest collection of $169$ facial editing attributes focused on hair, accessories, and pose edits. We compared model performance using two popular celebrity face datasets: CelebA and CelebSET. Our results show that most models performed hair and accessory edits well, but struggled with editing pose. All models over-edit (e.g., changing hair color when asked only to change the hairstyle). We also evaluated demographic biases in each model. Our results show surprising biases in overediting: almost all models created more overedits for dark-skinned male faces and old faces. The code and data for our results (including our repository of $\sim 1$M images) can be accessed \href{https://github.com/rahul1801/Face-Edit-Bench}{\textcolor{blue}{here}}.

UML class diagrams are a crucial tool for defining the structure of software systems, but designing accurate and comprehensive class diagrams is a challenging task. Traditionally, creating UML models relies on the expertise and experience of professionals. However, with the development of AI technologies, particularly LLMs, new opportunities for software modeling have emerged. Despite this, there has been limited research on the application of LLMs in software modeling, especially in UML class diagram modeling. This study conducts experiments on several typical software system cases. Combining SDMetrics with expert manual review, this paper comprehensively evaluates the practical performance of mainstream LLMs in UML class diagram modeling from multiple dimensions, including size and completeness, relationship correctness, inheritance hierarchy, and design rule compliance. Focusing on typical defects in LLM-generated UML class diagrams, this study reveals that LLMs exhibit uncertainties analogous to human memory. Accordingly, three targeted repair strategies are proposed, including memory reinforcement, external knowledge injection, and detection-guided automated targeted repair. Experimental results obtained from the case studies indicate that (1) compared to expert-crafted class diagrams, LLM-generated UML class diagrams exhibit several issues, such as incomplete identification of key classes, confusion or omissions in relationships, insufficient or absent inheritance relationships, unused classes, and circular dependencies, and (2) after applying the repair methods, all the LLMs show varying degrees of improvement in addressing these issues. The average repair rate for key class identification reaches 85%, the coupling relationship repair rate is 46%, the inheritance relationship repair rate is 69%, while repair rates for unused classes and circular dependencies both reach 100%.

Separable nonnegative matrix factorization (SNMF) has been widely used for low-rank representation and clustering of nonnegative data, owing to its ability to produce part-based and interpretable decompositions. In particular, SNMF is closely related to graph clustering and community detection. To enhance sparsity and identifiability of the learned factors, we propose an $\ell_1^p/\ell_2$-regularized SNMF model based on a powered ratio-of-norms regularizer. The resulting formulation is nonconvex and nonsmooth, which poses significant challenges for optimization. To address this, we develop efficient algorithms based on the difference-of-convex function algorithm (DCA) and the alternating direction method of multipliers (ADMM). The proposed methods decompose the original problem into tractable subproblems, leveraging closed-form proximal operators associated with the powered norm terms. We establish descent and limiting criticality properties for the DCA scheme and convergence under standard assumptions for the ADMM scheme. Extensive numerical experiments on synthetic datasets and hand gesture classification tasks demonstrate that the proposed approach achieves competitive or improved performance in anchor identification and classification accuracy compared with existing SNMF methods, while maintaining competitive computational efficiency.

Stereoscopic omnidirectional images (SOIs) have provided users with newly immersive quality of experience in virtual reality environments. However, developing efficient and accurate perceptual quality assessment metrics for SOIs remains challenging due to many factors such as freely changeable field of views and binocular vision. In this paper, based on the characteristics of the human visual system (HVS), we propose a Predictive Coding Hierarchy-inspired metric (PCH) for blind/no-reference stereoscopic omnidirectional image quality assessment. Motivated by the viewing process of SOIs, the proposed PCH includes a local cyclopean perception module, a global predictive perception module, and a visual quality regressor. First, observers browse different spherical sceneries from viewports, and aggregate the local visual information to infer the perceptual quality of SOIs. Therefore, we extract various viewports, followed by cyclopean conversion and saliency detection to approach the perception and attention of the human brain. After the local aggregation, viewers then infer the global scene in their minds. Based on the binocular mechanism, we fuse left and right views to perform predictive coding hierarchy modelling. Finally, the visual quality regressor is exploited to obtain the ultimate quality score related to both local and global perceptual cues. Extensive experiments demonstrate that the proposed PCH achieves competitive and consistently improved performance compared with state-of-the-art quality assessment methods.

Modern artificial-intelligence coding agents can be equipped with tools for checking their own work e.g. a linter, a boot probe, a shell, a screenshot tool. We call this set the agent's verification surface. This study asks whether increasing only that surface, with everything else held fixed, produces a matching growth in the quality of the software the agent ships. We built a minimal coding agent whose tool list is the single controlled variable and used it to implement 1,116 web applications across six models and eight tool configurations. A condition-blind human graded every application against a frozen rubric, and automatic probes stress-tested the API-observable behaviors. Verification's cheapest benefit arrives first, which is to make sure that the application comes up. Without any tools, about one build in seven fails to launch at all and a single boot probe removes nearly all of these failures at roughly 35 percent of a full shell's token cost, while the full shell multiplies the no-tools cost by 2.35. Screenshots help most where mistakes are visible (e.g. element placement, interaction), though even there the gain over a shell is modest and does not survive correction for multiple statistical comparisons. In cases where failures can only be measured rather than seen, such as keeping scrolling smooth over a 100,000-row list, screenshots add nothing. A verification tool improves the output artifact only where its reach covers the way the application actually fails.

Our work evaluates the effectiveness of automated methods for solving CAPTCHA challenges commonly encountered in darknet environments. These CAPTCHAs are typically designed to operate without JavaScript, resulting in distinct characteristics compared to mainstream CAPTCHA systems. Our study considers three representative challenge types: open-circle localization, rotation-based alignment, and object-selection CAPTCHAs. The experiments reveal a systematic limitation of contemporary MLLMs: while they are generally capable of identifying relevant visual structures, they frequently struggle with precise spatial localization and geometric transformations. These deficiencies can be mitigated either through task reformulation or by augmenting the models with specialized image processing tools. These deficiencies can be mitigated by task reformulation or by equipping the model with specialized image-processing tools. We therefore propose a hybrid framework in which an MLLM serves as a high-level reasoning and orchestration layer while delegating geometric computations to deterministic algorithms via the Model Context Protocol (MCP). The resulting system achieves success rates above 90% across all evaluated CAPTCHA types and demonstrates that combining the complementary strengths of MLLMs and classical computer vision yields a more accurate and efficient solver than either approach alone.