arXiv:2607.01106v2 Announce Type: replace
Abstract: Distributed trajectory estimation arises in many applications across robotics, but existing implementations typically do not consider asynchrony in agents' communications and computations. Therefore, we propose an asynchronous block coordinate descent algorithm for distributed trajectory estimation. We consider a team of agents that observes a team of robots and estimates the robots' states over a sliding window. The agents solve an approximation of the maximum a posteriori estimation problem, which we derive. We show this approximation introduces negligible errors and eliminates up to 96.9% of communications among agents. Next, we prove that agents' iterates converge exponentially fast to the optimal estimate of the robots' states. Simulations show that this approach has up to 64% less error than a comparable state-of-the-art algorithm. Experiments on mobile robots show this approach is robust to delays whose lengths span three orders of magnitude.
Science Journals
arXiv:2607.14487v1 Announce Type: new
Abstract: Dexterous manipulation is limited not only by algorithms but by a shortage of accessible hand hardware that combines human-scale morphology, ease of manufacturing or maintenance, tactile sensing, and practical cost. Existing dexterous hands tend to optimize some of these properties at the expense of others. We present MIDAS Hand, a low-cost, open-source, human-scale dexterous hand with integrated tactile sensing for manipulation research. MIDAS Hand provides 16 total degrees of freedom (DoF) with 13 active DoF, directly driven actuation with measurably low backdrive torque, and 283 three-axis tactile taxels in a compact 700 g package with a bill of materials under 3,000 USD. Built from 3D-printed components, it assembles in under three hours while providing the strength, repeatability, and maintainability needed for repeated real-world experiments. Alongside the hardware, we release a full stack: design files, build documentation, control and tactile Python APIs, simulation models, and retargeting and teleoperation pipelines. We characterize MIDAS Hand through workspace and grasp-taxonomy analysis, payload and reliability tests, backdrivability measurements, and teleoperation demonstrations with tactile sensing, showing that it offers a balanced, reproducible platform for tactile dexterous manipulation and human-to-robot data collection. Project page: https://midas-hand.com
arXiv:2607.14781v1 Announce Type: new
Abstract: The simultaneous arrival of multiple mobile robots at a target point is crucial for cooperation tasks such as cooperative encirclement, disaster relief, and environmental monitoring. Although the simultaneous arrival problem itself is already complex, the problem becomes more challenging when there are constraints on the robot trajectory curvatures and the speeds are required to be constant (possibly different for different robots), and the control law for robots needs to be distributed. These constraints are typical for a multi-robot system consisting of, e.g., fixed-wing UAVs. To address this challenge, this paper proposes a distributed switching control method based on the maximum consensus protocol. By exploiting the geometric properties of Dubins paths along with optimization principles, a virtual time variable is introduced, and a hybrid control law that combines optimal control with saturated proportional control is designed. Under the proposed control law, each robot is driven to approach the maximum virtual time among its neighbors, thereby achieving simultaneous arrival under some mild conditions. Furthermore, we prove that in certain cases the proposed method attains a theoretically optimal arrival time. The approach is scalable and real-time, with low communication overhead. Its effectiveness and robustness are validated through extensive simulations and experiments.
arXiv:2607.15246v1 Announce Type: new
Abstract: The reliability of deepfake detectors frequently degrades under black-box adversarial transfer, as these models often rely on fragile, architecture-dependent forensic cues. Existing transfer attacks often lack semantic awareness and struggle to maintain effectiveness under strict no-query constraints, particularly when perturbations are transferred from convolutional surrogates to transformer-based targets. To address these limitations, this paper introduces ARMOR++, a robust multi-agent framework designed for high-transferability deepfake evasion. The framework leverages the Qwen2.5-VL Vision-Language Model (VLM) to supply spatial semantic priors, while the Qwen3 Large Language Model (LLM) orchestrates primitive selection, adaptive hyperparameter reparameterization, and entropy-regularized perturbation mixing. By integrating five complementary primitives, spanning dense optimization, saliency-based methods, spatial transformations, frequency-domain perturbations, and block-structured modifications, ARMOR++ effectively targets heterogeneous inductive biases. Rigorous evaluation on the AADD-2025 benchmark demonstrates that ARMOR++ significantly outperforms existing agentic and non-agentic baselines across both low- and high-quality image regimes. Statistical analysis confirms a substantial gain in blind-target Attack Success Rate (ASR) over the state-of-the-art agentic baseline, with further performance advantages evidenced against non-agentic benchmarks and under robust defensive configurations. These findings highlight a significant residual reliability gap in current deepfake detector deployments and demonstrate the efficacy of agentic orchestration in identifying latent vulnerabilities.
arXiv:2607.14155v1 Announce Type: new
Abstract: Agent systems validate inputs, tool calls, and generated objects. The final package often escapes the same scrutiny. In one DRSS release, the ledger supported 60 points and a failed certificate; the report announced a 100-point Gold Path. Every local gate was green. The package contradicted itself.
We study that failure alongside Schema Docs, where similar faults became product contracts, and Brand Shuttle GEO, where evidence is turned into repair work. The result is a candidate Schema-SIP Relational Conformance profile (SIP-RC). It models a release as a graph: claims point to evidence, decisions carry bounded authority, derived artifacts retain their execution conditions and lineage, and published bytes must match the package that was checked. Hard failures cannot be averaged away, and a validator recomputes critical decisions on a separate path. The paper establishes the failure class and shows that several mechanisms are practical. Whether the full profile performs better than existing checks remains an open experiment.
arXiv:2607.14234v1 Announce Type: new
Abstract: This paper presents a comprehensive dataset of past ICA (The International Communication Association) annual conference papers from 2003 to 2018, encompassing 27,466 papers, 21,038 authors, and 4,935 sessions. We made the dataset publicly available in both CSV and JSON formats. Additionally, we developed an API to facilitate programmatic access, and an intuitive user interface to enable users to navigate and explore the data more easily. The web application, API documentation, downloadable data, and reproducible code to obtain and process the data are available at https://ica.hongtaoh.com.
arXiv:2607.14601v1 Announce Type: new
Abstract: Developers who maintain real systems must continually recognise and remediate vulnerabilities in existing code, yet this skill is rarely trained directly: secure software development is commonly taught only after programming fluency is acquired, and accessibility support is treated as a secondary concern, disadvantaging learners with ADHD and related executive-function differences. This paper presents SYNAPSE, a publicly deployed adaptive tutoring platform for Java, Python for cybersecurity, and secure software development. SYNAPSE coordinates Claude, GPT-4o, and Gemini through the Model Context Protocol, routing interactions by pedagogical intent under a three-stage Socratic hint policy. It exposes eighteen always-visible accessibility features and anchors practice in ShopSecure, a deliberately vulnerable web application mapped to six OWASP Top 10 (2021) categories, on which learners practise the detect-understand-remediate loop characteristic of software maintenance. A feasibility pilot with nineteen participants across neurodivergent and neurotypical cohorts returned a System Usability Scale score of 76.4 and engagement of 4.2/5, with comparable cognitive-load levels across cohorts. SYNAPSE is available at https://synapse-course.com; a screencast is available at https://youtu.be/9R17KC47qQI.
arXiv:2403.12261v2 Announce Type: replace-cross
Abstract: The interaction of radiation defects with grain boundaries (GBs) governs damage tolerance in refractory materials for extreme environments. Tungsten (W), a leading plasma-facing material for fusion, will be subjected to coupled ion and neutron irradiation that degrades both surface and bulk properties. In this study, molecular dynamics (MD) simulations are employed to examine defect evolution under successive 1 keV displacement cascades at a W surface in nano-bicrystals containing Sigma3 and Sigma5 symmetric tilt GBs. The free surface biases interstitial accumulation toward surface planes, reducing bulk interstitial populations, while vacancy saturation is driven by cascade overlap. When cascades indirectly interact with GBs, defect accumulation becomes strongly dependent on GB character. The higher energy Sigma5 boundary acts as a more effective defect sink for interstitials relative to the coherent Sigma3 boundary. This behavior arises from its larger interstitial segregation energy and enhanced strain field, which promote trapping via thermal migration and focused collision sequences. The deeper trap states of the Sigma5 GB suppress interstitial emission and limit recovery, whereas the shallower traps and mobile crowdion configurations in Sigma3 GBs enable dynamic defect recombination. These results highlight the critical role of GB structure and grain size in controlling radiation damage evolution in tungsten with behavior that applies broadly to refractory BCC metals.
arXiv:2607.14514v1 Announce Type: new
Abstract: Object-goal navigation requires an embodied agent to locate and reach an instance of a specified object category in an indoor environment. Recent training-free approaches leverage vision-language models (VLMs) for open-vocabulary semantic reasoning, but are typically evaluated under an episodic protocol that resets all scene-specific state after each episode. We introduce Cross-Episode Object-Goal Navigation, in which an agent repeatedly operates in the same scene, retains only self-acquired experience, and keeps its model parameters fixed. To support experience reuse, we present \method, a training-free VLM navigation framework with a persistent hierarchical Visual-Topological Memory (VTM). The VTM organizes scene knowledge at room and object levels and retrieves relevant experience through coarse-to-fine matching, providing memory as soft guidance only when it agrees with current observations. A conservative execution guard further mitigates oscillations, blocked motions, and premature stopping. Under a controlled same-scene protocol, we evaluate \method{} on three benchmarks, HM3D v0.1, HM3D v0.2, and MP3D, and compare it with a strengthened WMNav baseline augmented with cross-episode textual memory, while keeping the VLM backbone and action pipeline identical. \method{} achieves the best performance across all three benchmarks, demonstrating the effectiveness and robustness of structured visual-topological experience reuse across datasets.
arXiv:2607.14784v1 Announce Type: new
Abstract: Photovoltaics can exhibit favourable installation-level energy return on investment (EROI), yet electricity must also be delivered when solar and wind generation are insufficient. This study evaluates how the energy balance changes when the boundary is expanded to reliable electricity supply. A fleet-equivalent benchmark model includes component turnover, grids, storage, renewable overbuild, dispatchable backup, and fuel supply. It is not a simulation, optimization, or real-system prediction. Photovoltaics provide the accounting reference in an illustrative Central European mix of 80% wind and 20% photovoltaics, while the firming penalties arise more generally from weather-dependent generation.
Expanding the boundary is decisive. The unfirmed renewable fleet retains an EROI of 10.7-16.0, but does not provide continuous electricity. Battery load-balancing references decline from 7.1-12.5 for 1h to 0.7-2.3 for 24h. Seasonal hydrogen yields 3.4-7.7; adding a 1h battery reduces the combined range to 2.9-6.8. Pipeline-gas and LNG backup yield only 1.2-2.6 and 1.0-2.2.
The lifecycle-carbon advantage narrows accordingly. Under present industrial supply chains, GWP$_{100}$ intensities rise from 38-75 gCO$_2$eq/kWh without firming to 80-289 gCO$_2$eq/kWh for hydrogen and battery-hydrogen firming, and 121-327 gCO$_2$eq/kWh for gas backup. These favourable benchmarks set orientation, site, curtailment, and delivery factors to unity; real deployment lowers EROI and raises emissions. The results identify firming as a critical energetic constraint: reliable decarbonization requires firm low-carbon generation with sufficient net-energy surplus to sustain a resilient industrial society.
arXiv:2607.14371v1 Announce Type: new
Abstract: Large Language Models (LLMs) have revolutionized AI services, but a critical tension emerges: while personalization improves model performance, it consumes scarce computational resources that users must share. When should a user invest in expensive Supervised Fine-Tuning (SFT) versus lightweight In-Context Learning (ICL)? How does congestion from other users' personalization choices reshape these incentives? And what strategies should platforms adopt when offering multiple personalization algorithms?
We develop a tractable framework for LLM serving that captures the statistical-economic trade-offs users face. Our analysis yields several surprising insights. First, we show that ICL and SFT dominate in different regimes, determined by an interplay between pretraining coverage and data signal-to-noise ratios, but congestion can flip these rankings. Second, equilibrium resource consumption exhibits pronounced non-monotonicity: improving pretraining precision reduces the congestion, while broader pretraining coverage and harder tasks sometimes increase it. Third, we prove that offering both personalization methods never hurts the platform's maximal profits, despite potentially increasing computational load.
Experiments with GPT-2 on linear regression tasks validate our theoretical predictions about algorithm performance. Complementing these results, our review of documentation from 21 major AI platforms shows that the share offering both SFT and ICL increased from 9.5% in 2021 to 71.4% in 2025, consistent with our platform-design implications.
arXiv:2607.14545v1 Announce Type: new
Abstract: Machine-learned predictions can speed up offline NP-hard optimization, but asking a predictor what to do amounts to asking it to solve the problem, and committing an unchecked prediction forfeits every worst-case guarantee. CASP (Certificate-Augmented Solution Pruning) instead asks which parts of the search space may be ignored, and accepts each answer only after a sound polynomial-time verifier has checked it, so correctness never depends on prediction quality. We develop the learning theory of this design. The verifier makes the induced loss class uniformly bounded, so certificate parameters are learnable from $\tilde O(\varepsilon^{-2}\log K)$ samples ($K$ the maximum instance size), whereas the unverified commitment class admits no distribution-free rate and, under cost spread $R$, none below $\Omega(R/\varepsilon^2)$. Filtering noisy predictions by verifiable confidence dominates the standard min-combiner, with a margin we compute in closed form, and the prediction stays useful even given the LP, because it breaks ties on degenerate optimal faces, where every symmetric LP policy, meaning one whose commitments depend on the instance only through the verifiable confidence values, provably stalls. Experiments on five problems test the theory's quantitative predictions. With trained predictors, unverified pruning loses up to $26%$ of the optimum under distribution shift, while the verified deployment of the same predictions loses nothing.
arXiv:2607.14786v1 Announce Type: new
Abstract: Across hydrodynamics, ecology, neuroscience, network dynamics, non-Hermitian physics, and socio-economic systems, asymptotically stable dynamics can exhibit large transient amplifications that are invisible to eigenvalue-based analyses. The mechanism is geometric rather than spectral: perturbations entering along one direction may be expressed transiently along another, allowing asymptotic decay to coexist with strong transient or noise-driven amplification. We introduce non-normal directional response inference, a data-driven method for detecting this geometry from multivariate time series when the governing operator is unknown. A local linear operator is estimated from sliding windows and projected onto the dominant two-dimensional input-response subspace. The reduced dynamics are summarized by the eigenvalue splitting $\Delta$, eigenvector non-orthogonality $K$, and the scale-free ratio $R=K/K_c(\Delta)$, where $K_c(\Delta)$ is the two-dimensional threshold for transient amplification. Controlled benchmarks show that the reduced geometry, particularly $R$, can be recovered from finite data even when the full high-dimensional operator is poorly estimated. Tests across sample size, dimension, training horizon, spectral structure, and non-stationarity confirm that the relevant response geometry requires far fewer observations than full-matrix recovery. Applied in moving windows to electrohysterogram, seizure EEG, freezing-of-gait, and unstable push-up inertial recordings, the method reveals systematic changes around known physiological or behavioral episodes through shifts in $R$, changes in $\Delta$, or stronger projection of fluctuations onto the inferred response direction. It thus exposes interpretable changes in local response geometry without framing the problem as supervised event detection.
arXiv:2607.14580v1 Announce Type: new
Abstract: We present a novel system that integrates negative prompt optimization via a fine-tuned sequence-to-sequence LLM and latent-space classifier guidance to improve the quality of images generated by Stable Diffusion. Our approach automatically generates optimized negative prompts, and employs a CNN-RNN hybrid classifier to evaluate and guide diffusion steps, rolling back low-quality latent updates. Experimental results demonstrate that our dual-guidance framework reduces artifacts and improves semantic fidelity compared to baseline diffusion.
arXiv:2607.15119v1 Announce Type: cross
Abstract: We introduce a thermodynamic theory of voting and show that it provides a good description of distribution of party votes in EU elections. The theory traces parallels between system energies of coupled nonlinear oscillators and party vote fractions. Such a classical system evolution is characterized by the conservation of total energy and probability norm that leads to the Rayleigh-Jeans (RJ) thermalization and condensation at low energy states. A similar thermalization also describes the wealth inequality in society. This feature belongs to the phenomena of constraint driven condensation known in statistical mechanics. We show that the RJ theory well depicts the Lorenz and Pareto curves obtained from the EU vote results. The theory also recovers the dispersion of votes between candidates of first round presidential elections in France.
arXiv:2607.14934v1 Announce Type: new
Abstract: In this manuscript we release two datasets for visual sensing of tomato plants grown in commercial-like settings and acquired using a robot. The first is BUTom21 which consists of still images and manual annotations. The second is BUTom-ST21 which consists of video-based data and semi-automated annotations through AI-based methods, referred to as pseudo-labels. In both cases, we provide pixel-level labels for the ripeness of the fruit. The aim is to provide the research community a challenging set of real-world imagery to explore methods to sense and estimate the state of tomato plants and their fruit, which is an important horticultural crop. Importantly, the spatial-temporal dataset provides individual fruit count and ripeness information enabling researchers to push the boundaries of field-based phenotyping.
arXiv:2607.14398v1 Announce Type: new
Abstract: Constrained generative models aim to produce samples that satisfy complex feasibility constraints while remaining faithful to the data distribution. Existing constrained generation methods typically enforce constraints either through training-time optimization or sampling-time correction. Training-time optimization approaches optimize on states induced by the training distribution, which can differ substantially from those encountered during sampling. Sampling-time correction methods instead modify the sampling process at inference, introducing distribution shift and requiring expensive tuning, particularly for few-step sampling. We propose a fine-tuning framework that incorporates constraint guidance obtained through online rollout into the training process, which aligns training with sampling by differentiating through the fixed noise schedule used to numerically integrate the denoising process. This exposes the model to violations that arise along the denoising trajectory and aligns diffusion learning with the sampling process. Experiments across multiple tasks show that our method improves constraint satisfaction while maintaining competitive sampling quality compared to prior methods.
arXiv:2508.10266v4 Announce Type: replace
Abstract: Dynamic mode decomposition (DMD) is a data-driven modal decomposition technique that extracts coherent spatio-temporal structures from high-dimensional time-series data. By decomposing the dynamics into a set of modes, each associated with a single frequency and a growth rate, DMD enables a natural modal decomposition and dimensionality reduction of complex dynamical systems. However, when DMD is applied to transient dynamics, even if a large number of modes are used, it remains difficult to interpret how these modes contribute to the transient behavior. In this study, we propose a simple extension of DMD that facilitates extraction of oscillatory transient activity by introducing time-varying amplitudes for the DMD modes based on sparsity and smoothness regularization. This approach enables identification of dynamically significant modes and extraction of their transient activities, providing a more interpretable representation of non-steady dynamics. We illustrate the validity of the proposed method using a simple example and then apply it to fluid flow data of a laminar airfoil wake exhibiting transient behavior. We demonstrate that it can capture the temporal structure of mode activations that are not accessible with the standard DMD method.
arXiv:2607.08208v2 Announce Type: replace
Abstract: This paper describes our self-designed system for Task 1 of the MLC-SLM 2026 Challenge for multilingual two-speaker conversational speech. The system combines a modular speaker diarization front end with a challenge-adapted Qwen3-ASR-1.7B recognizer. The diarization front end performs voice activity detection, subsegment generation, CAMPPlus speaker embedding extraction, two-speaker spectral clustering, and RTTM-based audio segmentation. The resulting speaker-attributed segments are grouped by language or region and decoded by the adapted ASR model. For ASR adaptation, we first perform supervised full fine-tuning on the official training data, then apply LoRA fine-tuning with synthetic speech generated by a three-pipeline TTS-based synthetic speech augmentation framework, and finally refine the model using GRPO reinforcement learning with rewards based on WER/CER and penalties for hallucination, repetition, and length deviation. On the official development set, the full system achieves an average tcpMER of 23.70, reducing the error rate by 6.83 absolute points relative to the released Qwen-ASR-1.7B performance. On the final evaluation set, the system achieves an average tcpMER of 17.97. Ablation results show that supervised fine-tuning provides the largest gain, while synthetic-speech LoRA adaptation and reinforcement learning further improve robustness.
arXiv:2607.13276v2 Announce Type: replace
Abstract: Aurora DSQL is a serverless SQL database designed for cloud-scale transaction processing with multi-region active-active capabilities. Built on a disaggregated architecture, DSQL separates compute, storage, and transaction coordination into independent, horizontally scalable services. Query processors run in Firecracker MicroVMs executing PostgreSQL-compatible SQL without local state. The system uses multiversion concurrency control with precision timestamps for coordination-free reads and optimistic concurrency control for writes, deferring coordination to commit time through distributed adjudicators and the Journal replication system. This minimizes cross-region latency by requiring coordination only during commits, not individual statements. DSQL enables elastic scaling from zero to millions of transactions per second while providing strong consistency, ACID transactions, and continuous availability during availability zone or region failures.
arXiv:2607.14805v1 Announce Type: new
Abstract: This paper traces the evolution of Red Ambiental Ciudadana de Monitoreo (RACiMo), a citizen-science and environmental-education initiative developed by Universidad Industrial de Santander in Colombia. RACiMo has evolved through successive editions from a school-based open-hardware programme into a regional environmental monitoring network that integrates meteorological and air-quality data, open-data practices, and student-centred research. The project's central objective is to train citizens, especially secondary-school students, teachers, and university mentors, to record, curate, analyse, interpret, and communicate climate and air-quality data relevant to their local contexts. RACiMo has involved approximately 515 students from urban, metropolitan, rural, and p\'aramo communities in Santander, Colombia. It has progressed from Arduino-Raspberry Pi stations assembled through a Do-It-With-Others approach to low-maintenance commercial instruments and a multi-municipality network of professional weather and air-quality stations. Its pedagogy has shifted from learning by building sensors to learning by analysing real environmental datasets through Python, Jupyter notebooks, visualisation tools, and student-led research projects. The current RACiMo-Orqu\'ideas implementation expands the network across five municipalities, emphasises local environmental issues such as freight traffic and industrial activity, and provides public access to data through repositories and interactive tools. The paper discusses the trade-offs between openness, educational value, reliability, data quality, sustainability, and scalability. It argues that citizen environmental monitoring can strengthen climate awareness and adaptation when local communities are trained not only to collect data, but also to understand and use it critically.
arXiv:2607.14423v1 Announce Type: new
Abstract: Frozen self-supervised vision models can align parts of generic objects, but it remains unclear whether this correspondence extends to human faces, where global layout is shared while identity-specific appearance varies sharply. We test whether frozen DINOv3 features define a region-level facial coordinate system: a feature space in which eyes, brows, nose, mouth, skin, and hair remain distinguishable across people and across time without face-specific training. Using DINOv3 ViT-L/16 patch embeddings and FaRL only as a face-part labeling interface, we evaluate cross-identity nearest-neighbor matching and temporal label propagation on 200 CelebDF-v2 real videos. DINOv3 achieves 83.0% region-level semantic accuracy under unconstrained cross-identity matching, compared with a 23.0% area-weighted random baseline, and 95.5% temporal tracking accuracy without a learned temporal module. A no-FaRL control collapses to 0.9%, showing that FaRL supplies semantic initialization while DINOv3 supplies dense spatial correspondence. The strongest correspondence appears at an intermediate layer: block 18 gives a 4.93x same-region versus cross-region discrimination ratio, compared with 1.48x at the final block. Against CLIP ViT-L/14, DINOv3 shows only a small aggregate advantage but a +16.8 pp gain on anatomical regions, indicating that image-level contrastive supervision captures coarse facial layout but not fine-grained anatomical identity. These results establish frozen DINOv3 as a strong zero-shot representation for region-level facial correspondence and identify intermediate self-supervised features as the most useful layer for dense face analysis.
arXiv:2607.14808v1 Announce Type: new
Abstract: Repeated elliptic solves on domains with evolving boundaries arise in moving-interface simulation, design, and reactive navigation. Even when a fixed Cartesian grid avoids remeshing, rebuilding all boundary interactions for every configuration can limit the efficiency of repeated solves. We develop a static--dynamic boundary reduction for an unfitted lattice Green's function method on prescribed moving planar domains. Like boundary integral and boundary element methods, the formulation reduces the problem to boundary-supported unknowns through a Green representation. Its construction, however, reverses the usual order: the Cartesian operator is discretized before the Green representation is formed, rather than representing the continuous problem first and then discretizing the boundary. This discretize-then-represent viewpoint avoids boundary meshes and singular quadrature. The method also separates interactions associated with stationary geometry from those affected by motion, reuses the invariant part throughout a simulation, and updates only couplings involving the changing boundary. Boundary conditions are imposed at true interface intersections, lattice-kernel data are reused, and the interior field is reconstructed by a fast sine-transform solver. The principal contribution is an implemented and validated update strategy for translating, deforming, appearing, and topology-changing obstacles.
arXiv:2607.14596v1 Announce Type: new
Abstract: Sparse count matrices from single-cell transcriptomes to k-mer profiles and document-term frequencies are conventionally analyzed via PCA-reduced graph clustering or iterative optimization in continuous embedding spaces. We introduce MMTB, a deterministic non-learned binary representation framework that requires no label supervision, model fitting, or gradient-based optimization. Column-wise Min-Max normalization followed by fixed cutoffs maps each sample to a thermometer fingerprint whose Hamming distances show empirical correspondence with normalized L1 distances, with Pearson correlation approximately 0.92 on single-cell RNA-seq pairs. In a favorable three-cell-line mixture, the 3-threshold fingerprint achieves NMI of 0.99 at 188 bytes per cell. Under a fair Hamming nearest-neighbor graph plus Leiden readout, MMTB approaches PCA plus Leiden on this coarse task. On challenging tissue-like annotations, continuous pipelines often lead; PBMC Seurat NMI is 0.39 for MMTB versus 0.49 for Scanpy, underscoring that MMTB is suited for coarse-grained separation and resource-constrained deployments rather than fine-grained subtype discovery or as a general replacement for continuous embeddings. Relative to dense float32 representations, MMTB fingerprints reduce memory by approximately 10-fold while providing fixed-width Hamming-indexable codes. PCA30 embeddings and sparse CSR may be smaller; we do not claim universal compression. A label-free suitability score is provided as a deployment guideline, not a performance predictor.
arXiv:2607.14809v1 Announce Type: new
Abstract: RoboCup has always been a scenario to develop systems that solve real-world problems. Driven by the main goal of playing against the 2050 FIFA World Cup champions, the RoboCup Soccer leagues need to constantly measure how the research community is progressing. Computing visual statistics from match videos is a crucial way to track this evolution. To address this challenge, this paper introduces a fully autonomous, real-time sports commentator for RoboCup matches. By bridging the gap between raw kinematic tracking and natural language generation, our neuro-symbolic architecture extracts precise statistics from video streams and turns them into fluent, hallucination-free narration. The proposed system is capable of generating statistics and commentary both during live match streaming and in post-game analysis, easily adapting to the new dynamism of the league where different humanoid robots of different sizes share the field. Supplemental materials are available at https://lab-rococo-sapienza.github.io/MARIO/