arXiv:2607.16297v1 Announce Type: new
Abstract: Edge intelligence systems, the intersection of edge computing and artificial intelligence (AI), are pushing the frontier of AI applications. However, the complexity of deep learning models and heterogeneity of edge devices make the design of edge intelligence systems a challenging task. Hardware-agnostic methods face some limitations when implementing edge systems. Thus, hardware-aware methods are attracting more attention recently. In this paper, we present our recent endeavors in hardware-aware design and optimization for edge intelligence. We delve into techniques such as model compression and neural architecture search to achieve efficient and effective system designs. We also discuss some challenges in hardware-aware paradigm.
Science Journals
arXiv:2607.16408v1 Announce Type: new
Abstract: Idle network service cores are treated as wasted compute. This assumption motivates increasingly sophisticated mechanisms that reclaim idle cores at microsecond timescales. We argue that this view no longer matches modern server hardware. On contemporary multicore processors, active cores compete for a shared package level power and thermal budget. Once that budget becomes the limiting resource, an idle core that waits efficiently returns compute capacity that hardware can redistribute to productive work. Measurements on a recent AMD EPYC processor show how waiting strategy, processor topology, and idle duration determine this tradeoff. Our results suggest that reclaiming idle cores often yields less benefit than commonly assumed while introducing substantial scheduling complexity. We propose a budget centric view of service core systems in which power, rather than core occupancy, becomes the fundamental resource and waiting policy becomes a first class systems design choice.
arXiv:2607.16309v1 Announce Type: new
Abstract: We propose Scene-specific Ambiguity-aware 3D Language Fields (SaaF), a novel Gaussian Splatting-based 3D language field designed for interactive object retrieval in a given real-world scene. Interactive object retrieval using natural language is a crucial capability for service robots operating in complex real-world environments. While recent 3D language field methods for object retrieval establish associations between rendered pixels and autoencoder-compressed CLIP features, they suffer from two limitations: (1) reduced discriminability among similar objects due to feature compression, and (2) poor handling of ambiguous queries, often resulting in unstable or incorrect retrieval. To address these limitations, SaaF introduces a metric learning strategy to construct a unified feature space that is both instance-discriminative and ambiguity-aware. (i) To enhance instance-level visual discrimination, SaaF employs metric learning that pulls image features from multiple viewpoints of the same object closer together in the feature space. (ii) To establish ambiguity awareness, the model jointly trains on multiple text labels generated by the proposed method from each tracked object image sequence, including ambiguous descriptions, to learn the semantic relationships between ambiguous and specific features in a target scene. This feature space enables fine-grained visual understanding while allowing the system to estimate query ambiguity and interactively request clarification when needed. Experimental results demonstrate that SaaF not only improves retrieval accuracy over previous methods but also robustly detects and handles ambiguity in the user text queries under open-vocabulary settings.
arXiv:2607.16409v1 Announce Type: new
Abstract: Unified Multimodal Large Language Models (MLLMs) offer a promising paradigm for unifying visual understanding and generation, yet they still struggle to follow complex spatial instructions and logical constraints in controllable image generation. To address this gap, we present ATLAS, a unified framework that equips MLLMs with a human-like "Think, Plan, and Paint" paradigm. We adopt layout as the shared representation that connects the three stages, enabling the model to reason about spatial requirements, plan explicit object arrangements, and render the final image. We further improve plan-to-image fidelity with reinforcement-learning-based layout alignment. We instantiate ATLAS at 7B and 80B scales, achieving state-of-the-art performance among MLLMs on image generation benchmarks and an average 65.31% improvement over existing layout-based unified MLLMs. On spatially related tasks, ATLAS obtains an average 23.06% gain over the base models. Through the same layout interface, ATLAS also supports instruction-guided editing and multimodal grounding. We further introduce ATLAS-Reasoning, a benchmark for evaluating generation under complex spatial instructions.
arXiv:2607.16316v1 Announce Type: new
Abstract: In this report, we introduce Eddy-VL 1.9B, a compressed multimodal embedding model built on Qwen3-VL-Embedding-2B for offline, edge-deployable vision-language retrieval. Eddy-VL targets air-gapped forensic and investigative settings where cloud APIs are unavailable and low latency is essential. Compression combines (i) probe-driven structural pruning that removes four redundant text-decoder layers (28 to 24) ranked by adjacent-layer linear CKA, and (ii) layered knowledge distillation with hole-covering teacher-student mappings, mid-layer attention-map 1-CKA, and final-layer MSE and cosine losses with Matryoshka dimensions {128, 256, 512, 1024, 2048}. The released model contains 1,926,188,032 parameters (3.85 GB bf16), representing approximately 9.5% fewer parameters than the 2.13B teacher model. Empirical evaluations on MMEB-V2 (78 tasks, VLM2Vec protocol) show that Eddy-VL achieves an overall score of 63.2 compared with 68.9 for the teacher, retaining 91.7% of the teacher's performance while recovering 6.4 of the 12.1 points lost through pruning alone (56.8). Compositional reasoning performance remains close to the teacher on SugarCrepe (86.1 vs. 86.4), MR2-Bench (24.5 vs. 24.7), and ARO (59.5 vs. 60.4), while Winoground group performance (6.8 vs. 8.5) remains the primary limitation. Depth pruning also reduces forward latency by approximately 10% (150.0 to 136.4 ms per image on NVIDIA DGX Spark using FlashAttention-2). We present the architecture, compression methodology, training procedures, and evaluation results, demonstrating the effectiveness of Eddy-VL for multimodal retrieval under constrained edge deployment. Model weights and inference code are publicly available on Hugging Face.
arXiv:2607.16438v1 Announce Type: new
Abstract: Stochastic Mckean-Vlasov models have a substantial importance in different fields such as finance, biology and control. This paper puts the light on stochastic proportional delay Mckean-Vlasov model with L\'evy jump where the non-jump coefficients are granted the permission to grow beyond linearity. The truncated Euler-Maruyama algorithm is then applied to our addressed model where the convergence rate and almost sure exponential stability of the aforementioned numerical algorithm are being investigated. Finally, numerical examples are presented to foster the theoretical analysis done throughout the paper
arXiv:2607.16354v1 Announce Type: new
Abstract: Retail demand forecasting remains difficult when demand shifts faster than static forecasting models can be retrained, especially in early demand cycles where newly observed labels are sparse. To address this, this study aims to improve adaptive retail forecasting by proposing a predict-then-correct (PtC) framework that retains a first-stage machine learning (ML) forecast and applies a few-shot continuous contextual bandit correction policy with similar-SKUs augmentation and top-p masked updating. Across Walmart retail data and an exclusive beverage dataset, PtC delivers statistically significant reductions in MAPE, MAE, and RMSE across stable & high volume, stable & low volume, and erratic & intermittent demand patterns, improves average RMSE by 9.52% over the ML-only baseline in the ablation study, and yields lower inventory costs than base-stock, proximal policy optimization, and soft actor-critic policies under the tested lead-time settings. These findings show that online forecast correction can bridge offline demand learning and real-time retail decision-making by adapting to sparse feedback without fully retraining the base forecasting model.
arXiv:2607.16355v1 Announce Type: new
Abstract: Recent advances in physics-grounded video generation leverage physics simulation as a physical prior to guide video synthesis toward physically plausible outcomes. The simulation process is controlled by physical specifications, which are typically generated by a vision-language model in a single pass. Such one-shot prediction often fails to accurately translate user intent into executable simulations, particularly for fine-grained object dynamics, complex motion trajectories, and temporally structured interactions. In this paper, we propose PhysAgent, a reflective agentic framework that closes the loop among physical program generation, physics simulation, stage-specific verification, and targeted program repair. Beyond improving the control of coupled physical parameters, our framework enables the agent to progressively realize complex trajectories, multi-stage interactions, and precise event outcomes by treating each physical program as an executable hypothesis. In addition, we design a set of physics-control APIs to support more stable and complex motion behaviors. Extensive experiments demonstrate that PhysAgent produces more physically plausible videos, achieves better prompt alignment, and generalizes more effectively across diverse physical scenarios.
arXiv:2607.16251v1 Announce Type: new
Abstract: Spatio-Temporal Foundation Models (STFMs) aim to learn generalizable representations of complex dynamical systems across space and time. However, existing approaches suffer from distributional bias in real-world pre-training data, structural bottlenecks of autoregressive or diffusion-based paradigms, and objectives that overemphasize point-wise reconstruction in noisy observation space.We propose \textbf{NeoST}, the first spatio-temporal foundation model pre-trained solely on procedurally generated synthetic systems. NeoST introduces a scalable synthetic pre-training corpus to mitigate real-world bias, a latent-space reasoning architecture that generates and iteratively refines multiple future trajectories without sequential error accumulation, and latent-space objectives that emphasize structural dynamics and enable inference-time correction under distribution shifts.Extensive experiments across diverse real-world benchmarks show that NeoST consistently outperforms existing STFMs in diverse real-world spatio-temporal systems, achieves superior long-horizon stability and inference efficiency.
arXiv:2607.16369v1 Announce Type: new
Abstract: This paper describes our submission to the ICME 2026 ESDD2 challenge on environment-aware speech and sound deepfake detection. The task requires five-class classification of audio clips in which speech, environmental sound, both components, or neither component may be spoofed. We propose a component-level ensemble system based on four publicly available pre-trained anti-spoofing models: XLSR-Mamba, DF-Arena, SLS, and TCM-ADD. Each model is fine-tuned on the official CompSpoofV2 development data using three binary heads for original, speech, and environmental sound detection. We further train RawBoost-augmented variants and combine selected checkpoints using margin-space score fusion. A component-wise fusion strategy with lightweight head- and class-bias calibration yields our best configuration, reaching 0.7715 macro-F1 on the evaluation set and 0.7828 macro-F1 on the test set, ranking 5th out of 31 teams in the final ranking phase and substantially outperforming the official baseline.
arXiv:2607.16266v1 Announce Type: new
Abstract: Existing approaches for reasoning about action and change provide expressive semantics for modeling dynamic systems, in most cases built on top of logic programming systems. We introduce a modular framework for transition and trajectory verification based on Tiles and implemented in Soda, which is an efficient functional programming language. The framework operationalizes action language semantics through executable verification pipelines that process states, actions, transitions, and rules as compositional functional components. Verification procedures are represented as typed functional pipelines, enabling modular specifications, reusable reasoning components, and transparent execution workflows with guaranteed pipeline termination. The framework includes an executable specification layer that allows users to define domain descriptions in YAML, which are operationalized into the underlying verification model and executable pipeline structure. We provide an open-source implementation and illustrate the framework through examples that involve misinformation and emotional reasoning.
arXiv:2607.16286v1 Announce Type: new
Abstract: The 3D geometry of real-world scene data is often incomplete. Mainstream methods use depth estimators to inpaint missing structure. However, their prediction results can be inconsistent with observed geometry, or unreliable on out-of-distribution data. To solve these problems, we propose Neural Depth Field (NDF). Our key insight is that a depth estimator can also be a scene-level implicit field. As an estimator, it adapts to the target domain by learning observed depth data. As an implicit field, it fits the existing geometry to maintain consistency. Under this view, NDF addresses both problems through a single test-time optimization. Experiments show that NDF produces high-fidelity and globally consistent geometry across diverse scene data, ranging from indoor scans to satellite imagery. It reduces cross-view inconsistency by 63.3\% and improves inpainting accuracy by 23.1\%, achieving state-of-the-art performance in 3D scene geometry inpainting. The code is available at: https://github.com/Shadow-Dream/Neural-Depth-Field.
arXiv:2607.16520v1 Announce Type: new
Abstract: Recent work has demonstrated non-diffractive topological spin textures (Skyrmion- and meron-like) that persist in the core of diffracting relativistic twisted fermion beams [1]. Here we present numerical simulations of an analogous photonic system: Laguerre-Gaussian (LG) twisted photon packets coupled to a gauged Hopf lattice with discrete flux flywheels. Our results reveal emergent behavior of the same qualitative class, including persistent core features under propagation, mean survival approx 0.150 at critical lambdat = 2 clustering tightly with the mystery scale e^{-2} approx 0.1353 and residual R approx 0.1375, golden-angle correlations in the OAM mode ladder, and topological residuals with long-lived structure. Multi-l simulations further exhibit z-resolved flux transfer and twist dynamics that play a role analogous to probability-current continuity in the fermionic setting. These findings suggest photonic platforms as accessible analogs for exploring topological textures in structured waves, and they formalize a concrete computational bridge between relativistic twisted matter waves and topological photonics.
arXiv:2607.16443v1 Announce Type: new
Abstract: Recursive rule evaluation can make explanation harder than in nonrecursive query answering. For fixed unions of conjunctive queries, each explanation is bounded by the query body. For recursive rules, the same answer may depend on large supports, and the number of minimal supports may be exponential in the input. We study this gap through deletion-based explanation, using inclusion-minimal endogenous input facts that entail the atom together with fixed background facts. We organize these supports as a hypergraph and prove that it determines actual causes, counterfactual causes, responsibility, and deletion robustness. The resulting view separates nonrecursive queries from recursive Datalog at the level of minimal input explanations. For positive-length reachability, minimal supports are exactly simple directed paths, and deletion robustness is the minimum directed edge cut. We also prove invariance under fixed-goal equivalent positive Datalog programs and an NP-hardness calibration for the robustness threshold problem.
arXiv:2607.16811v1 Announce Type: new
Abstract: We revisit Gaussian Mixture Models (GMMs) as a lightweight, interpretable tool for anomaly detection and, in particular, for detecting distributional drift in data streams. We make three practical choices explicit and evaluate them on seven public benchmarks. First, the number of mixture components is selected automatically by the Bayesian Information Criterion, initialised by k-means, removing the need to fix it in advance. Second, individual observations are scored by their negative log-likelihood under a GMM fitted to normal data, with thresholds set at a target false-alarm rate using Extreme Value Theory. Third, the same interpretable model extends to distributional drift: each Gaussian component is a named "regime," and the fraction of a stream window that matches no regime -- its unexplained mass -- is a drift signal that is itself the explanation. We benchmark this against a model-free kernel two-sample test (Maximum Mean Discrepancy, MMD) and against two GMM-to-GMM divergences (a closed-form Cauchy-Schwarz divergence and a matching-based KL surrogate). Across seven benchmarks ranging from 3 to 64 dimensions and five random splits, the GMM point detector is competitive with -- though rarely more accurate than -- Isolation Forest, Local Outlier Factor, one-class SVM, ECOD, COPOD and an autoencoder, while uniquely yielding an interpretable model. For drift, MMD is the strongest pure detector, but the interpretable unexplained-mass statistic matches it when anomalies form novel regimes (and honestly fails, as MMD does not, when drift is a pure re-weighting of existing regimes). Every alarm is explainable: anomalies lie a median of 3-10 sigma outside their nearest regime vs. about 1 sigma for normal points, and a drift alarm reports the fraction of the window matching no known regime. All code and experiments are released.
arXiv:2607.16537v1 Announce Type: new
Abstract: While Mars rover operators plan drives across hazardous Martian terrain and diagnose unexpected faults, the necessary information is distributed across separate systems and often reconstructed through manual correlation and memory. To address this challenge, we partnered with Mars rover operators at the NASA Jet Propulsion Laboratory to introduce Hindsight, a visual analytics system that unifies previously disparate rover drive data into a single workspace for search, comparison, and investigation. This paper presents a design study of the Hindsight application. The partnership revealed that operators reason about drives as holistic spatiotemporal episodes rather than discrete parameters. By externalizing operator intuition into an explicit visual query process, we argue that Hindsight transforms analysis into a structured, shareable workflow. Preliminary feedback from operators suggests Hindsight supports their ability to correlate terrain, telemetry, and fault events within a singleworkspace.
arXiv:2607.16813v1 Announce Type: new
Abstract: Sparse-support uncertainty is usually quantified by treating the dictionary as known, an assumption that can produce overconfident, label-dependent conclusions when the dictionary is learned from latent sparse mixtures. Near collisions of coherent atoms, a test signal may identify the active physical group even though the training data cannot distinguish the physical rays within it.
We develop inference for active physical rays, unit atoms modulo sign, after latent dictionary learning. In a fixed-dimensional Gaussian train-test experiment, we retain all dictionaries compatible with a robust training-moment region, profile the test representation over them, and project surviving configurations onto a permutation-invariant support space. The resulting confidence correspondence can report cross-sheet inconclusiveness, group resolution with child ambiguity, or fine-support resolution.
We characterize both its statistical cost and decision-theoretic benefit. Residual block orientation first affects the latent training density at cubic order, yielding information of order $s^6$, where $s$ is the within-block collision scale. The correspondence provides high-probability-over-training conditional test coverage, with resolution governed separately by parent detectability, test-time support separation, and learned-dictionary orientation. In the resolved fixed-shell regime, its projective Hausdorff diameter contracts at the minimax-optimal rate $s \wedge (\sqrt{N}s^2)^{-1}$, up to constants. A restricted-task theorem further determines when coefficient asymmetry allows test replication to supplement training information and when calibration uncertainty remains irreducible. The framework thus yields honest, resolution-adaptive support statements and guides the allocation of training versus test measurements.
arXiv:2607.16322v1 Announce Type: new
Abstract: Micro-gesture recognition demands the detection of fleeting, spatially localized movements that are frequently overwhelmed by dominant static appearances and background noise. While Multimodal Large Language Models (MLLMs) excel at general video understanding, they inherently struggle with subtle kinematics and often rely on static posture priors. To this end, we propose GMoT, a Gated Motion-Aware Tokenization module that explicitly distills sparse kinematic evidence into a compact sequence prior to temporal modeling. GMoT dynamically spotlights action-relevant regions via spatially weighted pooling, extracts adjacent-frame temporal differencing to capture precise motion energy, and adaptively fuses these cues into the visual stream using a conservatively initialized semantic gate. To transition from simple classification to evidence-grounded reasoning, we further introduce a progressive reward-guided policy refinement paradigm, supported by a semi-supervised annotation pipeline that generates anatomically focused captions. Beyond achieving the best Top-1 accuracy among the compared methods on iMiGUE (67.32\%) and SMG (73.11\%), improving the Qwen3-VL-8B baseline by +6.80 and +3.11 points, our framework introduces Body-Region Grounding (BRG) Recall as an anatomical-grounding proxy conditioned on correct predictions, together with an overlapping-label cross-domain transfer protocol between iMiGUE and SMG. Extensive evaluations demonstrate that our GMoT-augmented model improves in-domain accuracy, retains clear gains under label-preserving corruptions, and improves accuracy-oriented cross-domain transfer under explicit small-split caveats while maintaining high anatomical grounding in its generated rationales.
arXiv:2607.16584v1 Announce Type: new
Abstract: As a fundamental arena for the development of his dynamics, Newton postulated the existence of absolute space, in which bodies innately possess absolute velocity. Despite this, Newton argued that, although real, absolute properties cannot be detected. Since then, the claim that absolute velocity would be undetectable in such a Newtonian universe has been generally accepted. Here, we show that standard arguments for such a claim, beginning with the one offered by Newton himself, beg the question. We conclude that there are no formal reasons to believe that absolute velocity would be undetectable in a Newtonian universe.
arXiv:2607.16346v1 Announce Type: new
Abstract: We introduce the notion of fuzzy directed simulation between fuzzy Kripke models over any linear and complete residuated lattice and investigate its fundamental properties. In particular, we prove that all positive formulas of the fuzzy modal logic $\mathit{fPDL}$ are preserved under fuzzy directed simulations and establish a Hennessy-Milner theorem for this notion. Furthermore, we present a method for computing the greatest fuzzy directed simulation between two finite fuzzy Kripke models and implement it for the case where the underlying residuated lattice is the G\"odel, product, or Lukasiewicz structure. Finally, we experimentally evaluate the performance of the implementation and present the obtained results.
arXiv:2607.16562v1 Announce Type: new
Abstract: Mixture of Experts (MoE) are increasingly deployed over wireless cloud-edge networks, as a single edge device lacks sufficient resources to host large-scale models locally. In this distributed architecture, a cloud-hosted pretrained Large Model (LM) acts as a shared backbone for latent feature extraction, while heterogeneous experts deployed across distributed, wirelessly-connected clients collaboratively form the task head. However, deploying MoE over wireless links exposes two coupled bottlenecks. On the one hand, routing which clients to activate generally overloads bandwidth-limited uplinks due to required raw feature transmission. On the other hand, aggregating the activated experts' outputs over wireless links is hindered by channel noise and poor scalability. To break these bottlenecks, we propose a statistic-augmented over-the-air MoE (AirMoE) paradigm. Specifically, on the routing side, each client queries its local Feature Retrieval Library (FRL) with a cloud-broadcast compact query, retrieves a prototype-induced statistic, and reports it digitally to the cloud, drastically reducing uplink traffic; the cloud then selects the most relevant clients by aligning these statistics with the LM-extracted features via Jensen--Shannon (JS) divergence. On the aggregating side, selected experts simultaneously transmit their outputs over the multiple-access channel, which physically computes the reweighted sum via waveform superposition, with reweighting coefficients realized through channel-aware power control. The two mechanisms are thus decoupled both algorithmically and physically. We further provide theoretical analyses on convergence and iteration complexity. Taking semantic segmentation task as an example, extensive experiments demonstrate that AirMoE outperforms MoE baselines and single-model competitors. Ablations further confirm the effectiveness of each incorporated component.
arXiv:2607.16499v1 Announce Type: new
Abstract: We present a case study on proof-driven software understanding of mature, security-critical infrastructure. While formal methods are traditionally applied during the design phase, we present our experience applying formal reasoning onto a mature industrial C++ codebase. We focus on a formal analysis of the core algorithm that implements the Stellar blockchain's SDEX order book. By combining large language models (LLMs), Prototype Verification System (PVS), and SeaHorn, we are able to prove core properties of the production codebase. Our approach also identified an inconsistency in documentation related to the reachability of an exception location. Most importantly, however, we produce artifacts that make it easy for code changes to be checked against established invariants. This work demonstrates how the strategic combination of theorem proving and model checking provides a path for delivering robust assurance to legacy systems.
arXiv:2607.16508v1 Announce Type: new
Abstract: Fish-like swimming has inspired the design of several dozens if not hundreds of bioinspired robots in the last few decades. But the control and motion planning of such robots has been challenging due to the poorly modeled fluid-structure interaction and the nonlinear underactuated dynamics of such robots. While reinforcement learning has allowed significant advances in the context of ground and aerial robots, the lack of a suitable simulation environment with appropriate computational speed and accuracy have prevented similar progress for fish-like robots. We address this two-fold problem by developing a simulation platform that approximates the motion of our fish-like robot with computational efficiency. Then the motion control and path tracking by the robot is performed using PID control where the (variable) gains are learned using back propagation through time and training on a curriculum. The policy learned in the simulation is then applied on the physical platform, demonstrating an excellent match.
arXiv:2607.16586v1 Announce Type: new
Abstract: Although standard auction mechanisms help truthfully reveal preferences of bidders, they can inadvertently result in unbounded harms when they fail to account for externalities caused by bid allocations affecting non-bidders. Ad markets, that buy and sell user attention represent such auctions. This research explores a welfare improving auctioneer's audit-and-penalty mechanism that helps screen the worst externalities. We prove this mechanism can internalize externalities formally, then explore social welfare gains empirically.
arXiv:2607.16548v1 Announce Type: new
Abstract: Cross-chain DAOs face unique security challenges that go beyond traditional single-chain vulnerabilities. This paper identifies and categorizes four critical attack vectors in cross-chain DAO governance: bribery attacks, token control exploits, human-computer interaction deceptions, and protocol vulnerabilities. We propose a comprehensive security framework with a multi-layered architecture that integrates cryptographic trust anchors, fraud-resistant consensus mechanisms, and decentralized validation techniques to address these threats. Our framework introduces novel components, including a Governance Kernel with on-chain rule verification, a Cross-Chain Trust Layer using threshold cryptography, and a Resilience Layer offering time-locked decision reversals and progressive dispute resolution. By establishing a structured set of countermeasures, this work lays the foundation for secure, transparent, and attack-resistant governance across diverse blockchain environments.