Papers

Women's presence in Congress has stalled below 30%. That institutional underrepresentation is mirrored by their limited visibility on televised news, where visual presentation can shape perceived competence and authority. Yet research tells us more about whether congresswomen appear than how they are visually framed. Facial recognition analysis of 695,464 image-text segments from CNN and Fox News (2011-2021) reveals that congresswomen appear disproportionately in split-screen rather than solo shots. Two pre-registered experiments with 6,220 participants show that, in static frames, split-screen framing reduces congresswomen's perceived political competence, but not congressmen's. In dynamic videos, the competence penalty disappears; instead, outraged language reduces a congresswoman's perceived warmth roughly three times as much as a congressman's. Suggestive evidence (p = .057) indicates that women viewers report greater external political efficacy after watching a congresswoman appear alone. We conclude that visual framing shapes both congresswomen's mediated visibility and their perceived capabilities.

Knowledge distillation (KD) enables model transfer across heterogeneous platforms and deployment environments, yet it exposes proprietary models to distillation-based theft, where an adversary extracts intellectual property (IP) by training a student model on teacher outputs. Current defenses, such as software watermarking or hardware-based access control, either fail to survive the distillation process or lack the granularity to identify the specific device responsible for a leak. Aiming to provide post-theft accountability and traceability, we propose a novel fingerprinting framework that superimposes device-specific Physical Unclonable Function (PUF) signatures onto teacher logits during distillation. By utilizing signatures derived from Ring Oscillator (RO) PUFs measured on a Xilinx Zynq-7020 FPGA, we ensure that any student model trained via KD inherits a unique, hardware-linked identity. Our framework is architecture-agnostic, enabling reliable identity inheritance across heterogeneous structures, including Convolutional Neural Networks, Vision Transformers, and encoders. To ensure robust attribution, we implement a two-stage recovery pipeline consisting of a neural decoder and Hamming-distance refinement, maintaining high detection accuracy even under noisy conditions. Furthermore, we introduce a multi-level logit encoding scheme to support large-scale device deployment. Experimental results demonstrate that the embedded fingerprints are resilient against common post-distillation modifications. These results establish a practical system-level approach for enabling hardware-linked model traceability in distributed AI deployment environments.

Full-duplex voice agents must handle pauses, take turns, backchannel, and respond to user interruptions in real time. Full-Duplex-Bench evaluates these behaviors, but its English-only corpus and reliance on word-timestamped ASR and an English-prompted LLM judge make it difficult to extend to Indian languages. We introduce IndicFDB, which extends it to ten languages spoken in India with 12,350 samples, nearly 17 times as many as the original. We address three challenges: finding conversational events in multilingual speech, evaluating their timing without reliable word-level alignment, and judging responses across languages. We mine pause handling, turn taking, and backchanneling samples from roughly 50,000 hours of channel-separated conversations using voice activity detection (VAD), and construct human-validated synthetic user interruption samples. Language-independent VAD heuristics evaluate timing, while an open-weight transcription and translation pipeline converts responses to English for LLM ratings of relevance and quality. Across seven voice agents, commercial APIs show unexpectedly consistent behavior across languages but are either fast or robust to pauses, never both, while monolingual open full-duplex models expose further tradeoffs among backchanneling, response quality, and latency.

Mathematical expressions and the numerical behavior they produce are two views of the same underlying function, and connecting them is central to scientific discovery. Symbolic Regression (SR) relies on this connection directly: it searches for an expression that reproduces a given behavior. Recent multi-modal models learn this connection by embedding symbolic expressions and their numerical behavior in a shared representation space. We show that this embedding space is only globally aligned: complete expressions correspond to complete behaviors, but the contribution of individual parts of an expression is not represented. This granularity gap leaves the model unable to tell how a local edit to an expression changes its behavior, the central operation in SR. We introduce a compositional alignment method that closes this gap: a structural positional encoding exposes the substructure of an expression to the encoder, and a multi-granularity contrastive objective grounds each subexpression in the behavior it produces before propagating this grounding to the full expression. The resulting representations close much of the modality gap between symbolic and numerical embeddings, reliably distinguish the effects of local edits that the original alignment cannot, and transfer to external SR corpora.

Verifying a numerical algorithm in a large scientific simulation framework is challenging: the framework is too big to model-check, and the unit tests exercise only sampled inputs. We report a case study in which we developed a new cloud-in-cell (CIC) deposition algorithm for Flash-X, a large-scale multiphysics simulation framework, keeping the CIVL model checker in the development loop. Rather than verify the algorithm within Flash-X's hefty infrastructure, we extract only the interfaces that the algorithm needs into a small, self-contained C model, which abstracts away implementation details of the Flash-X infrastructure that are unrelated to the new algorithm. The new algorithm is then built and checked within this C model. The CIVL model checker enables verification of the required physical properties of the CIC deposition algorithm using symbolic values for the particle positions. It proves two physical properties—mass conservation and the deposition location—for the continuum of admissible positions in the simulation domain. CIVL also verifies the algorithm's memory safety and freedom from MPI deadlocks and data race conditions over all rank distributions within specified bounds. Writing the verifying properties first and continuously checking them at each stage of the bottom-up prototyping workflow turned CIVL into a design guardrail that greatly increased confidence in the extended algorithm. During our case study, CIVL surfaced a concurrency defect in the algorithm that our random-seed-based tests failed to exercise. This paper shows our workflow, with the goal of helping readers understand its benefits, cost, and tradeoffs compared with testing.

Large language models (LLMs) are increasingly deployed as autonomous agents in multi-agent systems, yet their ability to reliably execute distributed coordination protocols remains poorly understood. While AgentsNet, a benchmark framework for distributed coordination among LLM agents, enables such coordination, granting full reasoning autonomy often leads to inconsistent or degraded performance in complex domains. We hypothesize that coordination can be improved by regulating agent autonomy through symbolic guidance derived from established algorithms. To investigate this, we introduce the Symbolic Guidance Taxonomy (SGT), which characterizes a spectrum of autonomy ranging from open-ended natural language reasoning to fully prescribed algorithmic execution, with intermediate levels providing partial pseudocode guidance. Our results show that intermediate autonomy levels consistently outperform both unguided agents and fully prescriptive specifications. These findings identify autonomy regulation as a key design principle for LLM-based distributed coordination.

In the Bipartite One-sided Vertex Explosion problem (BOVE), the input is a bipartite graph $G = (T, B, E)$ and a nonnegative integer $k$. The goal is to decide whether there is a set $S \subseteq B$ of size at most $k$ such that exploding every vertex in $S$ results in a graph with pathwidth at most one. The restricted Pathwidth One Vertex Explosion problem (restricted POVE) is a generalization of BOVE. The input to this problem is a graph $G$, a nonnegative integer $k$, and a set of vertices $X \subseteq V($ The goal is to decide whether there is a set $S \subseteq X$ of size at most $k$ such that exploding every vertex in $S$ results in a graph with pathwidth at most one. In this paper, we show parameter-preserving reductions in both directions between BOVE and Co-Path Set, and between restricted POVE and restricted Co-Path Packing. These reductions yield improved parameterized algorithms for BOVE and restricted POVE and an improved kernel for BOVE.

Audiovisual Speech Recognition (AVSR) is a multimodal approach to speech recognition that incorporates visual information from lip movements to enhance model performance. Despite its advantages, its development remains constrained by the limited availability of labeled audiovisual (AV) datasets. This work explores the use of synthetic visual data as a solution, using an audio-driven talking-head pipeline to generate lip-synchronized visual content from existing audio data. We evaluate the effectiveness of synthetic visual data both as an augmentation strategy and as a standalone training resource, applying our approach to Spanish and Catalan. Our results show that augmenting real AV data with synthetic samples yields relative Word Error Rate (WER) reductions of up to 16.2%, demonstrating the potential of this approach. Moreover, we demonstrate that synthetic data alone can serve as a baseline for AVSR training in languages lacking AV datasets. These findings provide evidence that synthetic visual data can serve as a scalable solution to AVSR data scarcity, enabling broader language coverage.

Time series out-of-distribution generalization requires forecasters to remain reliable when deployment dynamics differ from training conditions due to covariate shift, concept shift, and temporal dependence. Probably Approximately Correct Bayesian domain adaptation provides computable certificates by decomposing target risk into a source risk term, a source-to-target mismatch term, and a complexity term, but standard analyses rely on independent sampling and distributional stability, assumptions that are violated in time series by serial dependence and nonstationary shift. We propose a model-agnostic online martingale Probably Approximately Correct Bayesian framework that yields finite-sample certificates under temporal dependence and distribution shift. The certificate replaces independent-sample concentration with martingale concentration that adapts to loss scale and predictable variation. We use the certificate as a surrogate regularizer for online calibration by training a gated residual Bayesian head on top of a fixed forecasting backbone, producing a corrective update that reverts to the backbone prediction when the gate is closed. Online calibration combines a source risk anchor, a posterior-shift penalty, and a time-adaptive mismatch term computed from target windows observed before forecasting. It follows a predict-then-update protocol in which outcomes become available only after forecasting and are used to update subsequent predictions. Experiments across convolutional, attention-based, and large language model-based forecasters show improved stability and accuracy under covariate and concept shift.

Interactive CAPTCHAs remain challenging for computer-use agents, while existing datasets face trade-offs among type coverage, interaction fidelity, and trajectory supervision. To address these gaps, we present CaptchaArena, the first large-scale, fine-grained training dataset for interactive CAPTCHA solving. It contains 50K puzzles across 20 CAPTCHA types and 5 interaction modes, with every solution verified through execution. CaptchaArena provides 50K screenshot-action trajectories, including 46K with step-by-step reasoning annotations. It also includes fine-grained pixel-mask annotations for irregular targets. Using CaptchaArena, we train CaptchaAgent, a single 9B policy for all 20 CAPTCHA types, with supervised fine-tuning followed by reinforcement learning. The environment verifier directly provides the RL reward. Supervised fine-tuning reaches 70.5 Pass@1, and reinforcement learning further improves it to 71.7, while also improving performance on two external benchmarks. These results demonstrate the value of large-scale, fine-grained computer-use supervision for training interactive CAPTCHA agents. We release CaptchaArena and CaptchaAgent at https://github.com/X0X0X00/CaptchaArena.

The corpus-mean direction of a transformer's residual stream is a component shared across all inputs, and is commonly removed by mean-centering before representational analysis. We present evidence that it is a functional component: the reference against which the MLP gate population sets its operating point. In Phi-2, an exact decomposition of resting gate pre-activations shows that at mid-stack layers the resting inhibition of >99.9% of gates is carried by the coupling $w \cdot b_L$ to the carried mean direction, at 48-56$\times$ the explicit bias parameter, and the coupling is direction-specific: a random direction at matched norm orders the population's firing rates at Spearman $\rho \leq 0.09$ where the reference reaches 0.95. (That 0.95 is near-tautological on its own; the paper derives its null.) Causally, removing the stream's projection on the reference multiplies above-threshold firing by about 9$\times$, dose-monotonically, at 23-59$\times$ a norm-matched control; a random-initialised twin is flat, and replacement tests show that the direction carries the function and the magnitude does not. A direction-matched control makes the same point: noise injected along the reference costs 8-42$\times$ the same energy along a random direction. The decomposition replicates on four further families spanning both gate types (GELU with an explicit gate bias, bias-free SwiGLU), and the dose-response on two of them. Across an eight-model scan the mechanism is present in every GELU and SiLU family and absent only in OPT, where an opposing LayerNorm bias cancels the carried reference. Gate thresholds are implemented as couplings to a constant the network builds for the distribution it is reading, with the bias parameters contributing little; how much of that constant is carried in the stream and how much in parameters depends on the architecture.

In this paper, we provide a construction of an acyclic discrete vector field that is compatible with a total order associated with a lower star filtration on a simplicial complex, called the colex vector field. We show that the colex vector field induces a filtered acyclic vector field, whose resulting Morse complex computes the persistent homology of the lower star filtration on the underlying simplicial complex. We show that the colex vector field can be recomputed quickly when the vertex function that induces the lower star filtration is modified via order-adjacent vertex swaps. We provide a framework for storing and computing the number of paths between cells in the simplicial complex, as well as a method to update these values quickly when the colex vector field changes. Finally, we provide publicly available proof-of-concept code for the ideas shown. When applying it to the Persistent Homology Transform, we show that its runtime is comparable to a more standard matrix reduction approach.

We study density of states (DOS) estimation for large sparse real symmetric matrices by fitting the cumulative density of states (CDOS) and differentiating the fit. We use a stochastic Lanczos method to supply Ritz values and weights, which we average across Lanczos runs to construct CDOS midpoint data. Monotone piecewise-cubic interpolation of these data yields a smooth CDOS approximation that can be easily differentiated to yield a nonnegative, normalized, piecewise-quadratic DOS without requiring a Gaussian smoothing with a fixed bandwidth in its construction. We also consider approximating CDOS by using Gaussian-process regression (GPR) with single- and double-Gaussian covariance kernels, yielding an approximation with uncertainty information. DOS approximation is then obtained by analytic derivative of the GPR-based CDOS. Experiments on matrices from diverse scientific applications are performed to compare these estimators with Gaussian-broadened stochastic Lanczos and Jackson-damped kernel polynomial approximations. At a common Gaussian validation resolution, we use error measures that assess local discrepancies, integrated errors, and agreement in the overall spectral shape. The results demonstrate that the midpoint spline can produce accurate approximations to the DOS with relatively few matrix–vector products, supporting the use of cumulative interpolation as a practical DOS estimation.

Real-time full-duplex speech models can listen while speaking, enabling natural interaction without rigid turn boundaries. Existing benchmarks evaluate turn-taking, interruption handling and multi-round dialogue, but largely centre on a designated user rather than an assistant participating in a shared conversation among several people. We introduce Duplex-MPE to evaluate when such an assistant should answer, remain silent or stop speaking. The benchmark contains 2,000 scenarios with three or four human speakers and one assistant, each paired across explicit and implicit addressing of the same request. Models receive continuous conversation audio without transcripts or supplied turn boundaries. Four scores measure fresh response initiation, answer accuracy, silence preservation and stopping when a human resolves a request. We evaluate eight open-weight speech systems: MiniCPM-o 4.5, Moshi, FLM-Audio, Voila, Freeze-Omni, Realtime-Venus-Audio, Moshika-RL-Seamless and PersonaPlex. MiniCPM-o 4.5 leads on three scored capabilities, while frequent speech from other systems can coexist with inaccurate answers or failures to remain silent. A transcript-based Gemini 3.1 Pro reference responds 64.3 percentage points more often to explicit than implicit requests; paired tests detect no significant response-presence difference for the speech systems.

Hybrid transformer architectures that replace most softmax attention layers with linear attention offer transformer-level quality at a fraction of the memory cost. Rather than pretraining such models, a growing body of work distills them from already trained full-attention transformers. However, these distilled models often collapse on long-context retrieval and reasoning tasks, particularly when operating in thinking mode, where the efficiency gains of hybrid architectures matter most. Since linear attention layers must compress context into a fixed-size state, their errors compound over long sequences. As off-policy distillation never teaches the student model to recover from this drift, tasks that necessitate longer sequence lengths become especially challenging. We introduce On-Policy Attention Linearization (OPAL) in which the hybrid attention student samples its own long-context trajectories and receives dense supervision from the frozen full-attention teacher. Applying OPAL to Qwen3-4B and MiMo-7B-RL-0530, we recover $87$–$94\%$ of full-attention performance on commonsense reasoning, $100\%$ on needle-in-a-haystack (NIAH) retrieval, and $83$–$93\%$ on mathematical reasoning with only 3B training tokens. We achieve these results without supervised fine-tuning (SFT) or reinforcement learning with verifiable rewards (RLVR). Compared with the strongest prior linearization method, which recovers $68\%$ of its teacher's retrieval performance and $21.6\%$ absolute average mathematical reasoning accuracy, OPAL fully recovers retrieval and achieves $67.6$–$72.2\%$ on math reasoning.

We present a neural method for adaptive triangle mesh refinement, in which an autoregressive model adds geometric detail to selected regions of an input mesh while leaving the rest unchanged, a key capability for efficiently allocating mesh budget. Existing upsampling methods struggle to achieve this. Classical subdivision schemes refine triangulation without semantic awareness of the underlying shape or the ability to recover geometric details missing from a coarse input. Recent neural mesh models generate shapes globally, sacrificing region-specific control. We propose a novel tokenizer that yields combinatorially many valid upsampling trajectories from a single mesh. Trained on such data, our locally-conditioned autoregressive architecture allows for direct manipulation of topology and geometry within target regions of an input mesh. We validate our method against state-of-the-art approaches and demonstrate its ability to perform adaptive upsampling with region-selective control, a capability absent from existing approaches. This unlocks inference-time view-dependent refinement, physics-aware region refinement, and coarse-shape conditioned novel mesh synthesis. We provide code at https://github.com/seanxzhan/learned-localized-mesh-refinement/.

This engineering study assesses gaze-assisted data acquisition during visual screening with a Gaze Quest implementation via webcam and GC308 near infrared camera with an Orlosky eye tracking pipeline. Ten subjects performed under both acquisition conditions. Accuracy of Tumbling E orientation, reported application logMAR value,and response latency were determined from keyboard responses and hence are behavioral outputs as opposed toeye tracker screening results. Frame-to-frame change in theangle between successive normalized gaze vectors (28.2degrees) served as the GC308 eye tracker derived diagnostic with an effective sampling rate of roughly 8 FPS. No screen target calibration or gaze to screen translation was done on the GC308 eye tracker output data for the current analysis and hence, these data represent acquisition stability and not gaze accuracy in relation to the target. The webcam pipeline relied on 25-point screen calibration. Because the display resolution and pixel pitch could not be retained in the records of the study, the reported application logMAR values cannot be viewed as measures of visual acuity in any way.

Multi-objective Bayesian optimization (MOBO) is commonly approached through specialized acquisition functions or scalarization schemes designed to explicitly account for trade-offs among non-preferential objectives. In this work, we show that such complexity might be unnecessary. We propose a framework that extends standard single-objective acquisition functions directly to the multi-objective setting through a hypervolume-based transformation. We further extend hedge strategies for acquisition functions, which are typically used only in single-objective optimization, to the multi-objective regime. Our approach requires minimal modification to existing Bayesian optimization pipelines and avoids the need for bespoke multi-objective formulations. We demonstrate how a broad class of commonly used single-objective acquisition functions and hedge strategies can be adapted in a principled manner to handle multiple objectives, while preserving their intuitive interpretation and computational efficiency. Empirically, we evaluate the proposed methods across a range of synthetic and real-world multi-objective benchmarks. Despite their simplicity, our extensions consistently match or outperform more complex state-of-the-art MOBO methods in terms of optimization performance and sample efficiency. These results suggest that effective multi-objective Bayesian optimization can be achieved by reusing and carefully extending well-established single-objective acquisition strategies, offering a simpler and more flexible alternative to existing approaches.

Agentic biomedical machine learning (ML) draws on complementary advances in biomedical evidence acquisition and executable program search. Existing systems connect aspects of these capabilities, but coordinating them throughout program search remains challenging. New evidence must guide candidate construction, execution outcomes must inform subsequent discovery and reuse, and validation demands must fit the search budget. We introduce BioDyad, which couples biomedical discovery and ML engineering through two hierarchies within Monte Carlo graph search. Its scientific hierarchy combines prior biomedical guidance with iterative discovery, then links biomedical plans to execution outcomes in memory for reuse across candidates. Its engineering hierarchy moves candidate programs from smoke execution, through train/validation evaluation, to full-data retraining. We evaluate BioDyad on the 76-task BioXArena benchmark under a two-hour per-task budget with three matched LLM backends. It achieves the highest penalized all-task score and task success rate among four agent methods and a one-shot baseline under each backend. These results support coordinating biomedical discovery and ML engineering to integrate external knowledge into executable programs across heterogeneous biomedical tasks.

Generative world models can provide visual rollouts for embodied planning, yet their feasibility on edge devices depends not only on the learned model but also on how the execution runtime represents its operations. We introduce a cache-aware lowering that expresses supported causal Conv3D calls as batched spatial Conv2D operations while preserving pretrained weights, temporal-cache semantics, convolution parameters, bias placement, and output layout. Across the complete Cosmos3-Edge image-to-video pipeline on a 64-GB NVIDIA Jetson AGX Orin, the proposed route accelerates VAE decoding by approximately $7\times$ and reduces complete-generation latency by more than $2\times$, while repeated decoder evaluations maintain complete fast-path coverage without fallbacks. The unchanged lowering also improves Cosmos3-Nano and transfers to LingBot-World's architecturally distinct Wan2.1 VAE. A clean-device comparison against fully specialized TensorRT shows that TensorRT provides a further $1.36\times$ steady-state improvement, but requires substantially greater per-module and per-runtime-state AOT specialization. Same-latent BF16 and FP32 evaluations characterize the finite-precision differences introduced by the alternative execution order. Together, these results position cache-aware lowering as a lightweight runtime optimization that recovers most of the available decoder acceleration without modifying the learned models themselves.

Large language model (LLM) agents built on the ReAct pattern concentrate four responsibilities in one model: selecting a strategy, choosing each action, formatting it, and judging whether the result is adequate. Nothing outside the generative loop can reject its output, so an agent that cannot progress does not report failure; it runs until an external budget terminates it. We propose VReAct, which treats verification as an architectural layer for ReAct agents by adapting the software-engineering V-model: specification levels descend from requirements to individual steps, each paired with a dedicated verifier; a deterministic controller enforces every verdict; and only verification outcomes write memory. A rejection thus localizes the level that introduced the fault, and an agent halts by declining rather than by exhaustion. Each verifier separates a zero-cost deterministic gate from an optional LLM judge, so the contribution and cost of each can be measured independently. A pilot study implements the acceptance- and unit-level verifier pairs, comparing five configurations that share one executor, tool set, and scorer and differ only in verification components, on the four-hop stratum of MuSiQue with an 8B-parameter backbone. Across 47 executions, the two unverified configurations answered none of ten questions, every run ending at a step cap or provider token limit; the verified configuration without a planner answered eight of ten and abstained on the rest. Deterministic gates produced eight of nine observed corrections at zero marginal cost, and planning degraded performance once verification was present. These results characterize termination behavior, not accuracy at scale; we outline a twelve-month plan to complete and evaluate the full architecture, including the integration-level pair the pilot omits.

We present Potential-Dominant Operator Splitting (PDO-Split), a real-time generalized Nash equilibrium solver for constrained dynamic multi-agent problems with potential-dominant structure. PDO-Split targets the computational bottleneck in game-theoretic model predictive control, where repeatedly solving the equilibrium KKT system becomes costly as the number of agents increases. We introduce a class of gamma-potential-dominant games, in which the potential (or cooperative) structure dominates the competitive interactions between the agents. We show that this structure allows PDO-Split to use the potential component as a preconditioner while incorporating the competitive component through iterative refinement. We establish convergence guarantees and exploit the symmetry of the potential component through a reusable LDL^T factorization to accelerate the linear solvers. We evaluate PDO-Split across several practical multi-agent planning problems, including eight-car racing and six-vehicle ramp merging, achieving substantially improved runtime and convergence rate over existing DDP-based and Newton-based methods, especially with a larger number of agents. The algorithm is also experimentally validated on miniature autonomous race car platforms, demonstrating the approach's real-time capability.

Native-latent guidance is a recent paradigm for solving inverse problems with latent diffusion models. It replaces repeated evaluations of the image-space forward model, each requiring a decoder pass, with efficient guidance computed using a learned latent-space surrogate. However, existing methods apply guidance uniformly across latent dimensions, ignoring that measurements are informative only along certain directions and that the reliability of model predictions varies across inputs and timesteps. We propose ANaLOG, a framework for efficient uncertainty-aware guidance with pretrained latent diffusion models. ANaLOG models uncertainty by learning an anisotropic, input- and time-dependent covariance that is integrated into the guidance mechanism to emphasize reliable directions and downweight uncertain ones. We theoretically analyze this framework in a linear model setting and prove that anisotropic, uncertainty-aware weighting is necessary for correct sampling, whereas isotropic guidance induces sampling errors. Experiments across five challenging inverse problems show that ANaLOG improves perceptual reconstruction quality over existing methods while preserving efficiency.

Low-Earth-orbit (LEO) satellites are increasingly expected to perform onboard learning for applications such as disaster response and environmental monitoring. However, conventional federated learning (FL) is ill-suited to onboard satellite learning, as it assumes computational, memory, and communication resources beyond the capabilities of resource-constrained LEO platforms, often necessitating the transmission of raw imagery to ground stations. We present COSMIC-FL, a resource-aware FL framework for efficient onboard learning in LEO satellite constellations. COSMIC-FL introduces two complementary Mixture-of-Experts (MoE) architectures: a Sliced design that shares backbone representations while activating task-specific channel subsets, and a Modular design that employs lightweight gating to route inputs to physically separated expert networks. A semantic class-to-expert mapping enables each satellite to train, update, and communicate only the expert paths relevant to its local data. To further improve efficiency, COSMIC-FL integrates staged optimization with three structured pruning strategies: server-side pruning, client-side fixed-ratio pruning with mean-vote aggregation, and adaptive client-side per-layer pruning based on aggregated importance and a MAD-based gap criterion. Combined with semantic expert routing, these techniques jointly adapt computation and model sparsity to both data semantics and layer importance, yielding a favourable accuracy–efficiency trade-off for heterogeneous space platforms. Experiments on six image classification benchmarks under highly non-i.i.d. settings show that COSMIC-FL maintains competitive accuracy while reducing communication, computation, and energy consumption by up to 80% over SOTA FL methods. We further validate COSMIC-FL on an NVIDIA Jetson AGX Orin, confirming its efficiency gains under realistic embedded deployment constraints.

The Tangent Galvanometer (TG) is a standard undergraduate laboratory experiment for estimating the horizontal component of Earth's magnetic field (BH) by measuring the angle of deflection of a magnetic needle corresponding to the current flowing through a circular coil. In this study, an artificial neural network (ANN) is used as a complementary data-driven model to predict the value of BH. A dataset comprising 225 observations obtained using 50-turn and 500-turn coils was used for developing the ANN model. After quality control, 223 observations were retained and divided into training (70%), validation (15%), and testing (15%) subsets. The model was optimized using a feed-forward neural network with Tanh activation. Three different models (Models A, B, and C) with different input variables were compared for optimum performance. Model C used five input variables: current, deflection angle, tan(theta), magnetic field produced by the coil, and number of turns. The addition of tan(theta) produced a substantial improvement in prediction performance, which was further improved by including the magnetic field produced by the coil. Model C gave the best test performance, with R2 = 0.99053, RMSE = 0.54076 microT, and MAE = 0.32940 microT. The experimental and ANN-predicted values of BH were also compared with an adopted local geomagnetic reference value of 39.0 microT. The mean experimental and ANN-predicted values were 37.38898 microT and 37.32161 microT, respectively. The results demonstrate the usefulness of ANN as a complementary tool for analyzing experimental variability and nonlinear relationships in an undergraduate physics laboratory experiment.

Newton methods efficiently find Generalized Nash Equilibria (GNE) in dynamic games by solving for the KKT necessary conditions. These methods are fast and can support multi-agent Model Predictive Control (MPC) for highly dynamic robots. However, a small KKT residual alone does not certify that the returned solution satisfies the second-order sufficient conditions for a local GNE. In this paper, we propose an efficient numerical method to verify the second-order sufficient conditions (SOSC) for a local GNE. We connect the inertia of the agent KKT matrix with the positive definiteness of the reduced Hessian of the cost function, projected onto the null space of the constraints. Furthermore, we introduce an inertia-corrected update step that improves convergence to local GNEs by destabilizing strict saddle points with weak cross-agent coupling. Our main contribution is a fast Newton solver for Constrained Dynamic Games that provides efficient optimality checking. Through numerical benchmarks, we demonstrate the proposed solver's runtime and convergence performance in practical multi-agent planning problems. We also validate the solver's real-time capabilities in physical experiments using a platform of miniature autonomous race cars.

MathNet-Retrieve asks a retriever to find, for a math problem, a document stating the same problem. An LLM under one fixed prompt writes each gold document and its near-miss distractors; LLM judges filter them. We call this procedure the "recipe", training on pairs built the same way "recipe-matching", and ask how much score it buys beyond the ability the benchmark claims to test. Two models from one base, matched in rows and settings, differ only in the training file: pairs written under the benchmark's published prompt by another vendor's LLM and judge, or computer-algebra-verified pairs with no LLM anywhere. The first leads by 45 R@1 points on the easy tier. By a non-LLM paraphrase control, half to two thirds of that gap comes from the pairs being LLM-written at all: LLM rewrites under two unrelated prompts, with the verified model's negatives, recover 30 and 22 of the 45 points; back-translations with the same negatives recover almost none. The remaining 15 to 25 points appear only under the benchmark's own prompt and vanish on real duplicates no generator wrote, the same problem in two languages. The hard tier rewards the recipe's pair structure, a deep rewrite against a minimal-edit near-miss: LLM rewrites alone score zero on it, attaching negatives unlocks it, and every negative that does so costs cross-language points; the sets scoring highest on it separate near-misses no LLM wrote worse than LLM rewrites with verified negatives. MELD also moves when a model trains on pairs built its way, without losing retention; on SABER-Math the registered attack fails, and the one gain, from its LLM-written summaries, is small but holds at a matched budget. Only on MathNet-Retrieve could we pin an inversion, benchmark score up and real retention down, to one edit of a training file. We release the generator-free duplicate evaluations, the near-miss test and three trained models.

Contact-rich manipulation depends on force sensing that is hard to infer from visual signals alone, both for collecting demonstrations and for training policies. Force-annotated data, however, remains hard to obtain at scale: real-robot collection ties every demonstration to physical hardware, physics simulators report contact forces that deviate systematically from real measurements, and learned world simulators, though scalable and realistic, are vision-only, so operators feel nothing during data collection and the data carries no force/torque (F/T) labels. We present HapticWorld, an interactive world simulator that predicts joint torque together with observations and renders it back to the operator in real time, closing the haptic loop between a human and a learned world model. Across three contact-rich tasks, torque feedback raises data collection throughput by 1.6 times on average. Policies trained on HapticWorld-generated demonstrations succeed in 54/60 real-world trials, approaching the 56/60 upper bound of real-world data, and far exceeding the 19/60 success rate of the vision-only baseline. Moreover, the success rates measured inside HapticWorld closely match real-world evaluation, demonstrating that HapticWorld can serve as a stand-alone F/T-conditioned policy evaluation platform.

Large language models (LLMs) are enticing in their promise to support data visualization (Vis) through faster and simpler workflows for data prep, analysis, and visualization creation. Yet LLMs are notoriously error-prone and not built for data visualization tasks. Few studies have explored LLM adoption among Vis practitioners. To fill this gap, we conducted semi-structured interviews with members of the Data Visualization Society, a global community of data visualization designers. Our findings show that Vis designers actively use LLMs for both creative and technical aspects of the visualization process. A new visualization workflow is emerging, a process we call vibe analysis, analogous to vibe coding. Some key challenges raised by participants parallel those of vibe coding, while others are Vis-specific, like gaps in Vis knowledge and chart verification. This work opens up opportunities for research combining LLM-mediated work with Vis tools that incorporate data visualization guidance, constraints, and best practices.

Agentic AI envisions ecosystems of intelligent agents collaboratively solving complex tasks with minimal human intervention. In such ecosystems, each agent possesses specialized expertise, making effective expert selection central to overall system performance. While most current approaches assume a small number of well-documented models, real-world expertise is far more diverse and cannot be adequately captured through static metadata or hand-written descriptions. We anticipate a future with millions of specialized language models (LLMs), each excelling in different domains or problem types. Rather than relying on predefined capability statements, we propose a retrieval-based paradigm in which an assistant agent infers expertise dynamically by examining models' observable behavior. Upon receiving a user query, the assistant ranks candidate LLMs based on demonstrated competence, enabling efficient and adaptive expert selection. The TREC Million LLM Track operationalizes this paradigm by shifting the retrieval target from documents to expert LLMs. Participants are given a discovery set consisting of queries, answers, and log-probabilities from more than one thousand LLMs and are challenged to infer meaningful expertise representations for each model. Given an unseen test query, systems must then rank the LLMs according to their expected performance, providing the first large-scale benchmark for expertise retrieval in agentic AI.