arXiv:2607.08010v1 Announce Type: new
Abstract: Production LLM agents often waste latency and reliability by regenerating code for the same procedural steps on every request. We replace this inference-time coding loop with an agentic tool-making pipeline that compiles repeated SOP steps into validated, versioned tools before deployment. The tool-maker grounds synthesis in the live environment as it collects execution traces, observes backend schemas and values, generates candidate tools, and repairs them against labeled cases. At runtime, the production agent calls these tools directly and falls back to code generation only when needed. We deploy the approach in a Fulfillment Center alarm-triage system, where an agent diagnoses alarms against a 44-node SOP over heterogeneous metric backends. In production, tool calls reduce p50 latency by 42%. On 1,500 historical alarms, they reduce end-to-end error rate by up to 53% by suppressing run-to-run variance in repeated steps. Because tools return compact structured verdicts, they also enable a simpler direct-call architecture, reducing p50 latency by a further 62% in a controlled ablation. Versioned tools also improve auditability and expose specification gaps and upstream data drift. Our results show that self-evolving agents can make industrial LLM systems faster, more reliable, and easier to operate.
Science Journals
arXiv:2607.08147v1 Announce Type: new
Abstract: Autonomous web agents promise to automate everyday browsing tasks, but inherit one of the web's oldest attack surfaces. Cross-Site Scripting proved that mixing trusted and untrusted content is dangerous, even on benign pages. Agents resurface this risk by interpreting natural language as instructions, allowing third-party and user-generated content to hijack the agent via prompt injection. The core challenge is that deriving a task-specific security policy requires reasoning over page structure that is entangled with the attacker's content.
We present Prismata, a defense enforcing contextual least privilege for web agents, constraining both what the agent sees and what it can do. Prismata's dynamic trust derivation produces permission labels for page content, with structural confinement guarantees, inspired by classical integrity models, that bound any labeling errors so that labels can only decrease in privilege and mislabelings are bounded. Prismata's mechanical confinement enforces these labels by redacting content and restricting agent capabilities. Importantly, these mechanisms require no developer annotations, so Prismata supports the long tail of websites. Across recent published web agent attacks, including adaptive variants, Prismata substantially reduces attack success while preserving benign task utility.
arXiv:2606.10062v2 Announce Type: replace
Abstract: Foundation-model agents are increasingly long-lived systems that remember users across interactions, making memorization an explicit deployment-time function rather than solely a property of model weights. Existing work addresses parametric memorization or audits fixed memory configurations, but does not characterize how memory-design choices jointly shape personalization utility, extraction risk, and deletion fidelity. We study this surface as deployment-time memorization, formulating agent memory as a privacy-utility frontier measured by Personalization Recall (PR) and Adversarial Extraction Rate (AER), and sweeping three memory-design knobs: summarization aggressiveness, retrieval breadth (k), and deletion mode. We further introduce the Forgetting Residue Score (FRS) to quantify whether deleted information remains recoverable from derived memory tiers. On LongMemEval, key-fact summarization reduces canary extraction by 76% on Gemma 3 12B and 64% on GPT-4o-mini while preserving nearly all personalization recall; critically, once content is compressed away, increasing k no longer restores leakage. The same compression, however, induces a deletion-fidelity failure: raw-only deletion leaves derived summary copies recoverable in approximately 20% of instances, and only full-pipeline purge or tombstone redaction drives worst-tier residue to zero. Together, these results establish that persistent agent memory must be evaluated as a first-class memorization mechanism -- assessed by what it helps agents recall, what it makes extractable, and what it can truly erase.
arXiv:2607.07906v1 Announce Type: cross
Abstract: Quorum sensing (QS) is known in biology as a form of intercellular communication mediated by signaling molecules called autoinducers. The QS protocol governs the transition from individual to collective cell behavior once a critical population density is reached. Using numerical simulations, we investigate how defects influence the QS transition and the structural organization of the resulting colonies. Our model system consists of a mixture of slow ("cold") and fast ("hot") diffusing colloidal particles that obey the QS protocol, together with defect particles characterized by a constant diffusivity. A striking reentrant solidification of QS particles, characterized by long-range order, is induced by hot defects, whereas cold defects give rise to amorphous structures with only short-range order. These findings deepen our understanding of the QS interaction and provide a mechanism to control the degree of organization in QS systems, with potential applications in robotics, social sciences, and medicine -- for instance, in overcoming antimicrobial resistance.
arXiv:2606.12886v2 Announce Type: replace
Abstract: Interleaved thinking, where a unified multimodal model alternates between textual reasoning and visual generation, has shown promise on spatial and physical tasks. However, in complex long-chain scenarios, we identify a fundamental failure mode: generated images diverge from the textual context while subsequent text ignores the visual evidence, causing the two modalities to alternate without genuinely informing each other. We term this Modal Isolation and attribute it to compounding information loss at modality boundaries. We decompose each reasoning cycle into atomic operations and define modality transition loss, quantifying cross-modal hallucination (text-to-image) and visual utilization deficit (image-to-text) at each boundary. We propose MoTiF (Modality Tiransition Fidelity), a two-stage training framework that directly optimizes these transitions: Reflective SFT trains the model to detect and recover from erroneous visual outputs; Flow-GRPO improves image generation fidelity via reinforcement learning. All training signals in MoTiF derive from transition-level fidelity rather than end-task accuracy. Across four visual puzzle benchmarks, this transition-level supervision substantially improves both cross-modal coherence and final task accuracy. The results demonstrate that effective interleaved reasoning requires explicit structural supervision at modality boundaries, not merely scaling or end-task optimization.
arXiv:2607.08221v1 Announce Type: new
Abstract: Large language model (LLM)-based lossless image compression methods typically represent pixel data through the native text interface of a pretrained model, converting pixel values into token sequences that the LLM processes through its vocabulary head. This design shows that pretrained language models can provide probability estimates for image coding, but it also couples compression to tokenizer behavior, vocabulary-specific numeric tokens, and model-family-specific adaptation. In this paper, we present LUMI (LLM-based Unified Model-agnostic lossless Image compression), a tokenizer-agnostic framework for lossless RGB image compression with frozen LLM backbones. LUMI replaces pixel-as-text tokenization with a pixel embedding module that maps raw intensity and channel information into the continuous embedding space of the LLM. It further introduces intra-patch position encoding to retain two-dimensional spatial structure after flattening, and uses a 256-way prediction head to produce probabilities over the native pixel alphabet. Only the pixel embedding, position encoding, soft-prefix parameters, and prediction head are trained, while the LLM backbone remains fixed. Experiments on natural, medical, and remote-sensing image benchmarks with LLaMA, Qwen, and Gemma backbones show that LUMI provides a unified interface across tokenizer families, achieves competitive compression rates, and improves cross-domain robustness over tokenizer-based LLM compression baselines. These results formulate LLM-based lossless image compression as pixel-space adaptation of frozen foundation models rather than tokenizer-specific language-symbol modeling.
arXiv:2607.07968v1 Announce Type: new
Abstract: Soft robotic exogloves can provide hand rehabilitation and assistance. Fitting these gloves often relies on standardized measurements not tailored to the individual, limiting their effectiveness, especially for fine articulation necessary for dexterous manipulation. We present the design, fabrication, modeling, and testing of a personalized pneumatically-actuated soft robotic exoglove. The glove was fit to a user's hand with topological scans and fabricated with silicone mold casting. Finite element analysis (FEA) was performed to evaluate actuator bending and forces from physical human-robot interaction (pHRI) between an actuator and a simplified personalized biomechanical finger model. Pneumatic pressure control experiments were conducted to flex the user's finger with static and dynamic references. Fabrication results show that topological scans enable precise tailoring to hand anatomy. Simulations showed that anatomical personalization enables analysis of pHRI contact forces, and results indicate sufficient joint mobilization with non-ideal compression on the proximal phalanx. Pneumatic testing indicates that pressure control allows accurate and targeted mobility of the metacarpophalangeal (MCP) and proximal interphalangeal (PIP) joints with intrinsic stiffness. Testing of multiple designs showed that relaxing the strain-limiting layer improves actuator-to-finger joint alignment during actuation. This work presents personalization to the human hand in structural conformability, joint topology, modeling of pHRI contact, and time-dependent actuation-deformation profiles. This lays a groundwork for informing exoglove design optimization to enable assistance in dexterous manipulation and neuromuscular rehabilitation of fine motor skills.
arXiv:2607.08056v1 Announce Type: new
Abstract: Diffusion Language Models (DLMs) have recently achieved substantial progress in natural language generation tasks. Recent research demonstrates that adaptive token generation ordering can significantly improve performance in mathematical reasoning and code synthesis applications. In this work, we investigate the optimization of generation order for both text-to-image synthesis and multimodal understanding. We first establish that, unlike structured problems in language generation such as Sudoku puzzles, model logits alone are insufficient for determining optimal generation sequences in text-to-image generation and multimodal understanding. To address this challenge, we introduce a learnable control module trained via Group Relative Policy Optimization (GRPO) to determine the generation order. Our results demonstrate that learning this control block substantially improves both text-to-image alignment and multimodal understanding in DLMs. In particular, it enhances the model's ability to capture fine-grained spatial relationships in generated images while also strengthening performance on multimodal reasoning and comprehension tasks. We evaluate our framework on GenEval, an object-focused benchmark for text-to-image alignment, where it achieves 4.08% relative improvements. In addition, experiments on VLMEvalKit confirm 4.85% relative improvements in multimodal understanding, highlighting the broad effectiveness of our approach.
arXiv:2607.08246v1 Announce Type: new
Abstract: We study 4D generation to synthesize temporally coherent sequences of 3D geometry for animation and content creation. In contrast to existing SDS-based optimization methods and video-driven animation approaches, we adopt a skeleton-driven animation framework aligned with standard industrial pipelines, which enables explicit control and editing. To this end, we propose SkelGen4D, a weakly supervised feed-forward framework for text-driven mesh animation that generates explicit skeleton motions without requiring per-frame skeleton annotations. SkelGen4D first recovers temporally consistent pseudo-skeletons from animated meshes via differentiable fitting, and then generates text-conditioned skeleton motion sequences in a feed-forward manner, further refined with Motion-GRPO to ensure temporally coherent, physically plausible, and articulated animation. We evaluate our method on two large-scale benchmarks, Truebones Zoo and Diffusion4D. Our results show that our weakly supervised skeleton modeling matches or surpasses fully supervised baselines while scaling to diverse object categories for high-quality text-driven mesh animation. Further, our method supports flexible motion editing and is aligned with standard animation production pipelines.
arXiv:2606.15137v2 Announce Type: replace
Abstract: io_uring moves I/O submission and completion into shared-memory rings. This makes it fast, and it also makes it invisible. strace sees only the ring setup, and the kernel tracepoints that expose the request flow are not stable ABI, so the few tools built on them work only on narrow kernel ranges. We present uringscope, a single-binary, language-agnostic observability tool for io_uring built on CO-RE (Compile Once, Run Everywhere) eBPF. uringscope makes four contributions. The first is a precise model of the request lifecycle and a method to reconstruct per-request flows from kernel events. The second is a technique for attaching portably to an unstable tracepoint surface, using BTF-probed program variants, CO-RE field flavors, and position-independent reads. The third is an evaluation of the tradeoff between overhead and fidelity: on device-bound NVMe workloads uringscope's aggregate mode costs 0.7 to 9.9% of throughput, which is cheaper than every full-fidelity alternative we measured. The fourth is a lightweight correctness mode that reuses the same reconstruction to detect submission-boundary hazards, together with a built-in doctor that turns the measurements into named pathologies with evidence, for operators who are debugging a tail-latency incident rather than browsing histograms.
arXiv:2607.08267v1 Announce Type: new
Abstract: Unmanned aerial vehicles (UAVs) increasingly rely on visual grounding capabilities to localize task-relevant targets from diverse instructions in complex aerial scenes. Existing referring expression comprehension (REC) benchmarks and methods, however, are largely built around text-only queries and single-object outputs, which limits their applicability to practical UAV scenarios involving reference images, multimodal instructions, absent targets, and multiple valid target instances. To address this gap, we introduce \emph{Universal Referring}, a generalized UAV referring task that jointly expands the query modality and the output cardinality. We construct \emph{UniRef-UAV}, a multimodal benchmark that supports text-only, image-only, and text+image queries with modality-dependent target cardinality, where text-only and text+image queries admit no-target, single-target, and multi-target grounding while image-only queries focus on existence-aware single-instance grounding. It also provides in-domain and cross-domain evaluation protocols for visual-query generalization. We further present \emph{UAV-URNet}, a detection-style baseline that maps heterogeneous queries into a shared query space and predicts variable-size target sets through set prediction. Extensive experiments show that UAV-URNet provides a stable and reproducible baseline with more consistent no-target discrimination and a more lightweight, reproducible implementation than large general-purpose MLLMs. Additional domain analysis, query-representation analysis, and ablation studies demonstrate that multimodal queries help reduce visual-query ambiguity and promote a more unified query--target alignment space. The annotations, visual query crops/images, train/validation/test splits, evaluation scripts, and baseline code will be made publicly available to facilitate reproducible research.
arXiv:2607.02885v2 Announce Type: replace
Abstract: Cognitive Behavioral Therapy (CBT) provides a structured framework for understanding a user's mental state by examining the interaction between cognitive and behavioral factors. However, out-of-the-box LLMs respond fluently and empathetically, yet collapse into validation & reflection, regardless of what the user actually needs. They know theoretical CBT (scoring up to 96% accuracy on licensing exam questions) but fail to apply it effectively. We explore this gap with a knowledge-guided framework that treats CBT dialogue as controlled affective reasoning: user narratives are decomposed into Beck's Cognitive Conceptualization structure, grounded in clinical SNOMED CT concepts validated via Natural Language Inference, and a Multiple Chain-of-Thought (MCoT) strategy selection between Validation & Reflection, Socratic Questioning, or Alternative Perspectives. To measure whether such guidance actually changes behavior, we introduce the Protocol Leverage Force (F), a behavior-level metric that captures how far an intervention shifts a model away from its default response. Across three open-weight LLMs and 14 RealCBT-derived case studies, evaluated with human experts, valence-arousal trajectories, and linguistic entrainment, F shows that simply introducing protocol definitions via single chain-of-thought prompting fails to change LLM behavior, while MCoT on these definitions guides strategy selection better. Still, the effect stays within 1% (approx. 1.2-1.3%), and all models remain biased toward Validation & Reflection. These results show CBT knowledge alone does not ensure effective application, giving the affective-computing community instrumentation to measure where LLMs fall short.
arXiv:2607.08440v1 Announce Type: new
Abstract: Fluid Computing aims to support distributed applications execution across heterogeneous cloud, edge, and device resources, motivating task execution mechanisms that adapt to dynamic and privacy-sensitive environments under runtime conditions. In this context, current task offloading schemes rarely address privacy risks and information leakage under adversarial execution settings; furthermore, most coded computing proposals focus on straggler mitigation without considering system-level objectives such as energy awareness. This paper proposes a coded task offloading scheme for D2D networks under stochastic task arrivals and queue-based dynamics. The proposal combines task offloading techniques with linear secret sharing schemes, where tasks are encoded into redundant shares to support threshold-based recovery, straggler mitigation, and privacy preservation while enhancing system performance. Then, we formulate a privacy-aware offloading problem that jointly optimizes delay and energy while penalizing the theoretical privacy leakage of coded tasks under noisy leakage observations. The problem is solved using a branch-and-bound solver alongside a lightweight heuristic scheduler, both of which are evaluated through a discrete-event simulator. Results show that coded offloading improves the delay--energy trade-off with respect to classical full and parallel offloading schemes, while the heuristic achieves near-optimal performance, outperforming baseline and state-of-the-art solvers. The results also show how privacy leakage penalties reshape offloading decisions, exposing an inherent delay--energy--privacy trade-off.
arXiv:2607.08436v1 Announce Type: new
Abstract: Egocentric human data offers scalable supervision for robot manipulation. However, behavior cloning entangles transferable content like objects, scenes, and task semantics, with non-transferable factors like human morphology, head motion, and behavioral style. We study whether World Action Models (WAMs) provide a better training signal by requiring policies to predict not only actions, but also how the scene evolves. The central question is what world representation best enables human-to-robot transfer. We hypothesize that an effective world target should abstract appearance, capture agent-invariant physical effects, and separate camera motion from environment change. We introduce EgoWAM, a controlled human-robot co-training framework that fixes the policy backbone, action head, and data mixture while varying only the world prediction target, comparing Pixel, DINO, and 3D motion flow. Across three real-world bimanual tasks, WAM co-training scales more effectively with in-the-wild egocentric human data than behavior cloning. Pixel-based prediction transfers weakly, while DINO and 3D flow yield substantial gains: DINO improves out-of-distribution object and scene generalization by up to 4x, and 3D flow improves in-domain performance by 20-30%. More details: https://gatech-rl2.github.io/egowam.github.io
arXiv:2607.08499v1 Announce Type: new
Abstract: We present a Procrustes-conditioned Joint End-to-end Top-K Sparse Autoencoder (SAE) for extracting cross-seed universal features from independently trained BERT models. Cross-seed feature universality is a fundamental challenge in mechanistic interpretability: because dictionary learning is non-convex, independently trained networks learn misaligned feature spaces, so apparently identical features may differ by random initialization. We address this by computing an orthogonal Procrustes rotation between seeds' activation spaces before joint SAE training, combining Top-K sparsity, end-to-end downstream optimization, and an auxiliary dead-feature revival loss based on previous SAE literature. Evaluating on five independent seed pairs (ten BERT models) across three benchmark datasets (SST-2, Stanford Politeness, TweetEval Emotion), our full pipeline produces more universal features (Pearson r $\geq$ 0.70 across seeds) than post-hoc alignment baselines on all three datasets. A minimal qualitative analysis confirms that high-universality features encode interpretable sociolinguistic patterns.
arXiv:2607.08497v1 Announce Type: new
Abstract: Recent unified multimodal models show a single architecture can jointly perform vision/language understanding and image generation/editing. However, they repeatedly feed all historical visual and textual inputs into a shared context window, limiting long-horizon multimodal dialogue due to visual token explosion and unreliable cross-turn referencing. We propose a Cognitive-structured Multimodal Agent that externalizes visual information into an Episodic Visual Memory and selectively reactivates relevant episodes during reasoning. The agent consists of a Perceptual Abstraction Engine for structured visual abstraction, a Cognitive Retrieval Engine for cross-turn memory retrieval, and a Multimodal Executive Controller for autonomous task inference and action planning. To address the lack of turn-level retrieval supervision in existing datasets, we develop a Unified Scenario Engine that programmatically generates structured multi-turn conversations with fine-grained retrieval annotations, enabling reinforcement learning to optimize abstraction and retrieval policies. We also construct a long-horizon visual-dialogue benchmark stratified by difficulty to evaluate episodic visual recall. Our 8B agent achieves 91.4% retrieval accuracy over 20-turn sessions, surpassing 32B baselines by +8.2% while nearly halving per-turn inference time (23.1s -> 12.7s). We further present the Cognitive-structured Multimodal Agent Harness (CMA-Harness), a tool-augmented deployment of the same cognitive structure integrating persistent multimodal memory, web access, image generation/editing/composition tools, and OpenAI-compatible serving. Structured memory and modular decision-making offer a more scalable, efficient paradigm for long-horizon multimodal agents than monolithic parameter scaling. Code: https://github.com/caseclose/cma-harness ; Project page: https://caseclose.github.io/cma-harness/
arXiv:2607.08184v1 Announce Type: new
Abstract: The thermal radioactivity of beta-decay photons, described by a 1D Planck distribution, can be modeled as classical radiation emitted by an accelerated electron. Here, we present the basics of the out-of-equilibrium computation to illustrate acceleration thermality. Suitable for advanced undergraduate calculations, we demonstrate that an exactly soluble non-uniformly accelerated trajectory enables spectral analysis of the emitted photons, facilitates time evolution, and reveals Planckian radiation.
arXiv:2607.08555v1 Announce Type: new
Abstract: The operational integrity of complex industrial systems relies on precise anomaly detection and diagnosis. The vast majority of existing methods narrowly focus on capturing temporal similarities of representations, often overlooking the disruption of internal causal relationships, which characterizes system failures and latent anomalies. In this paper, we propose a novel framework (CAAD) that reframes anomaly detection as the continuous verification of Granger causality consistency through exogenous variables.
Specifically, the CAAD framework models exogenous time-series variables as residuals, identifying anomalies as significant deviations caused by external interventions. The proposed framework leverages multi-scale alignment to internalize system dynamics and utilizes a gradient-based matrix to monitor internal causal relationship breakdowns. By quantifying causal deviations of both dynamic evolution and relational topology, the CAAD is able to capture subtle causal shifts to achieve precise anomaly detection. Extensive experiments on real-world industrial datasets demonstrate that the CAAD achieves high-precision anomaly detection, outperforming most state-of-the-art baselines.
arXiv:2607.08516v1 Announce Type: new
Abstract: Proximity gaps are a property of error correcting codes that arise in the study of Interactive Oracle Proofs (IOPs) and Succinct Non-interactive Arguments of Zero Knowledge (SNARKs). Recent work of Goyal and Guruswami has established near-optimal proximity gaps for many families of codes, including subspace design codes, as well as random ensembles like random linear codes, Reed-Solomon codes with random evaluation points, and Gallager's ensemble of LDPC codes (Goyal & Guruswami, 2025). However, the parameters for these latter randomized ensembles are worse than the parameters for subspace design codes, and degrade as the degree ell increases.
In this work, we obtain improved proximity gaps for random ensembles of codes, including random linear codes, Reed-Solomon codes with random evaluation points, and Gallager's ensemble. Quantitatively, our results for these random ensembles match the results that Goyal and Guruswami attained for subspace design codes. In fact, our techniques are a black-box transference from subspace design codes: any progress on subspace design codes will automatically lead to analogous progress for these random ensembles. To obtain our results, we extend the Local Coordinate-wise Linear (LCL) property framework developed by Levi, Mosheiff, and Shagrithaya and by Brakensiek, Chen, Dhar, and Zhang to a \textit{row-span constrained} version (Levi, Mosheiff & Shagrithaya, 2025; Brakensiek, Chen, Dhar & Zhang, 2025). This allows us to cast \textit{curve-decodability} -- a property that implies proximity gaps -- directly as a row-span constrained LCL property, and make use of that machinery. In contrast, because curve-decodability is not obviously a vanilla LCL property, prior work had worked with a proxy property instead, leading to the aforementioned parameter losses.
arXiv:2607.08561v1 Announce Type: new
Abstract: A series of results from the NeuroAI over the past fifteen years have raised core questions both about how to compare Deep Neural Network (DNN) models to the brain, and about how much convergent evolution to expect between artificial networks and real brain networks. Here, we show that for any two minimal DNN solutions to a sufficiently hard task: (i) "weak" alignment of network representations based on affine mappings guarantees "strong" alignment of privileged axes, and (ii) alignment "zippers" up the network hierarchy, causing the emergence of privileged axes from end-to-end task optimization. These results formalize the notion of contravariance from Cao and Yamins [2024], and illustrate important consequences for the theory of NeuroAI: with sufficiently strong tasks, choice of metric for inter-network comparison is not all that sensitive, and that convergent evolution is probably inevitable.
arXiv:2607.08159v1 Announce Type: new
Abstract: Adjoint optimization is a cornerstone of broadband nanophotonic inverse design, but conventional time-domain implementations face a severe memory bottleneck because they retain forward-field histories at every finite-difference time-domain (FDTD) time step. Here, we show that this full time-step storage is unnecessary for band-limited design objectives. By storing forward fields only at Nyquist-compliant temporal intervals and using the resulting sparse field history during the reverse-time adjoint pass, the proposed method enables on-the-fly gradient accumulation without retaining full forward- or adjoint-field histories. This Nyquist-sampled adjoint FDTD framework preserves the two-simulation scaling of time-domain adjoint optimization while substantially reducing the dominant field-storage cost. Gradient verification confirms that Nyquist-compliant sampling reproduces conventional full-storage adjoint gradients with negligible error, whereas undersampling beyond the Nyquist limit produces aliasing-induced gradient degradation. Across four two-dimensional broadband nanophotonic benchmarks and a fully three-dimensional metalens, the method maintains gradient fidelity and optimized device performance while reducing dominant field-storage memory by up to 107x. These results suggest that the principal memory barrier in broadband time-domain adjoint FDTD is not an intrinsic requirement of gradient evaluation, but a consequence of redundant temporal field storage, opening a practical route to large-scale three-dimensional nanophotonic inverse design.
arXiv:2607.08272v1 Announce Type: new
Abstract: Robots are increasingly deployed in remote or hazardous areas for mission-critical control tasks. Due to their limited individual capabilities, they have to rely on other field sensors to obtain the state information of targets, and also a dedicated edge information hub (EIH) to enable information exchange, sensing data analysis and control command generation. Such configuration follows a sensing-communication-computing-control (SC3) closed loop. To optimize the whole closed-loop performance, this paper minimizes the linear quadratic regulator (LQR) control cost by designing the sensor-to-EIH bandwidth allocation. Specifically, we first model the distortion noise caused by limited communication data rate based on the mutual information theory. Next, under the control policy based on the Kalman filter and LQR controller, we formulate the control process as a partially observable Markov decision process (POMDP), and develop a deep reinforcement learning (DRL)-based sensor-to-EIH bandwidth allocation scheme. The proximal policy optimization (PPO) algorithm is utilized to train the DRL agent. Simulation results are provided to show the superiority of the proposed DRL-based scheme.
arXiv:2607.08509v1 Announce Type: new
Abstract: This paper investigates the behaviour of a fluid characterized by a viscosity simultaneously depending on pressure and shear rate within a Hele-Shaw cell featuring a sharp corner geometry. The study extends previous analyses conducted on purely pressure-dependent (piezo-viscous) and yield-stress fluids, providing a new perspective on confined complex flows. Motivated by practical applications related to designing biomedical devices and flows of relevance to biomedicine area, thin film technologies, injection molding -- to name only a few -- the flow configuration considered here can highlight essential features of complex fluid behavior in narrow-gap geometries around a sharp edge. Starting from the governing equations for an incompressible generalized Newtonian fluid and employing an appropriate rheological model, we derive the modified flow equations adapted to the Hele-Shaw flow. A particular solution is obtained near the corner region. Numerical simulations complement the theoretical results, illustrating the influence of the rheological parameters on the flow behavior.
arXiv:2509.10757v2 Announce Type: replace
Abstract: The tracking module of a visual-inertial SLAM system processes incoming image frames and IMU data to estimate the position of the frame in relation to the map. It is important for the tracking to complete in a timely manner for each frame to avoid poor localization or tracking loss. We therefore present a new approach which leverages GPU computing power to accelerate time-consuming components of tracking in order to improve its performance. These components include stereo feature matching and local map tracking. We implement our design inside the ORB-SLAM3 tracking process using CUDA. Our evaluation demonstrates an overall improvement in tracking performance of up to 2.8x on a desktop and Jetson Xavier NX board in stereo-inertial mode, using the well-known SLAM datasets EuRoC and TUM-VI.
arXiv:2607.08368v1 Announce Type: new
Abstract: With the widespread deployment of basic models in edge intelligence, communication bandwidth has become a core bottleneck restricting the scalability of federated learning. Although one-shot federated learning alleviates this problem by minimizing communication rounds, existing iterative fine-tuning or knowledge distillation methods still face challenges such as high server-side computational costs and hyperparameter sensitivity. Analytical federated learning achieves efficient gradientfree aggregation using least-squares closed-form solutions, but in environments with non-independent and identically distributed data, its static feature assumptions fail, leading to feature manifold misalignment and severely impairing model performance. To address this contradiction, this paper proposes the FedOPAL framework. This framework adapts the visual prompts as feature rectifiers, actively correcting the feature distribution of heterogeneous data to a linearly separable space by applying local proximal constraints, thereby satisfying the theoretical assumptions of analytical federated learning. Experimental results show that FedOPAL not only significantly outperforms the original analytical methods on several benchmarks, but also achieves accuracy comparable to state-of-the-art iterative methods while maintaining zero server-side training costs, providing a new engineering paradigm for efficient collaboration of large models on the edge.