arXiv:2602.16726v2 Announce Type: replace
Abstract: Geospatial applications such as urban planning, epidemic forecasting, and transportation demand modeling depend on individual mobility data, but such data are costly to collect, uneven in coverage, and privacy-sensitive. Human mobility simulation offers a scalable alternative. A recent line of work treats large language models (LLMs) as human agents, modeling individual cognitive processes to generate realistic trajectories. Yet because each agent is simulated in isolation, these methods provide no population-level coordination mechanism, and the collective regularities of real mobility - how trip distances, visited locations, and flows distribute across a population - fail to emerge. We close this gap with COMPASS, which turns empirical mobility scaling laws into a feedback signal that guides prompt construction. COMPASS starts from coarse, population-level adjustments driven by these scaling laws and progressively refines them into individual prompts, jointly satisfying multiple aggregate objectives while keeping individual trajectories realistic. Across two public datasets, COMPASS outperforms state-of-the-art LLM-based simulators.
Science Journals
arXiv:2602.16727v2 Announce Type: replace
Abstract: Simulating large-scale human mobility is fundamental to understanding population movement patterns and supporting real-world geospatial applications such as urban planning, epidemic response, and transportation analysis. Recent works treat large language models (LLMs) as human agents to simulate realistic mobility behaviors using structured reasoning, but their high computational cost limits scalability. To address this, we design a mobility-aware cache framework named MobCache that leverages reconstructible caches to enable efficient large-scale human mobility simulations. It consists of: (1) a reasoning component that encodes each reasoning step as a latent-space embedding and uses a latent-space evaluator to enable the reuse and recombination of reasoning steps; and (2) a decoding component that employs a lightweight decoder trained with mobility law-constrained distillation to translate latent-space reasoning chains into natural language, thereby improving simulation efficiency while maintaining fidelity. Experiments show that MobCache significantly improves efficiency across multiple dimensions while maintaining performance comparable to state-of-the-art LLM-based methods.
arXiv:2607.08072v2 Announce Type: replace
Abstract: End-to-end models that map multimodal inputs directly to future trajectories/maneuvers have emerged as an increasingly prominent research paradigm in autonomous driving. This class of models includes both Vision-Language-Action models and trajectory-generative planners. Unlike classic machine learning applications, autonomous vehicles operate in safety-critical and interaction-intensive environments where traditional open-loop imitation of expert demonstrations is not sufficient to ensure reliability. In particular, small execution errors can accumulate over time, while recovery behaviors are scarce in training data. In addition, long-horizon objectives such as safety and driving comfort are not captured by pointwise labels either. These limitations have motivated a shift toward post-training techniques, which further refine driving policies beyond pure imitation. This survey presents a unified view of post-training for autonomous driving by defining its scope and organizing the existing literature into four major families based on the form of supervision they use. For each family, we discuss its capabilities, limitations, and open challenges. We aim to facilitate a systematic understanding of this emerging area and stimulate future research on reliable and efficient post-training for autonomous driving.A collection of related papers is available at https://github.com/RYNing/Awesome-Post-Training-In-Autonomous-Driving-Papers.
arXiv:2607.12931v1 Announce Type: new
Abstract: Reinforcement Learning (RL) has demonstrated significant potential for improving Vision-Language-Action (VLA) models on complex manipulation tasks. However, its practical scalability remains severely limited by the substantial cost of environmental interactions. In this work, we first investigate the exploration stagnation bottleneck in current VLA-RL frameworks and reveal that trajectory diversity is fundamentally more important to sample efficiency than the sheer quantity of collected rollouts. Motivated by these insights, we introduce RL Exploration Token (ExToken), a simple yet general framework that condition VLA policies on discrete behavioral priors derived from offline demonstrations for structured exploration. By conditioning the policy on different tokens during rollout collection, ExToken encourages the agent to explore diverse behavioral modes, substantially improving state-action coverage and exploration efficiency. To bridge exploration during training with deterministic inference at deployment, ExToken further incorporates a state-conditioned token selector that adaptively predicts effective behavioral modes for unseen scenarios. Extensive experiments across simulated and real-world robotic manipulation tasks demonstrate that ExToken consistently accelerates convergence, improves task performance, and exhibits strong robustness under highly constrained interaction budgets.
arXiv:2607.12932v1 Announce Type: new
Abstract: Accurate models of high temperature methane spectra are needed in astrophysics. Previous measurements of methane hot-band transitions in the $\it{P}$6 $\leftarrow$ $\it{P}$2 polyad range have been limited to final rotational numbers of $\it{J}$ $\le$ 9, with theoretical predictions at higher $\it{J}$s remaining unvalidated. Here, we use optical-optical double resonance spectroscopy (OODR) with a 3.3 ${\mu}$m narrow linewidth pump to excite the ${\nu}$${_3}$ P(12, A${_1}$$^{(2)}$) methane transition ($\it{P}$2 $\leftarrow$ $\it{P}$0) and a cavity-enhanced frequency comb centered around 1.68 ${\mu}$m to probe the sub-Doppler ladder-type ($\it{P}$6 $\leftarrow$ $\it{P}$2) and V-type ($\it{P}$4 $\leftarrow$ $\it{P}$0) transitions, as well as Doppler-broadened collision-induced four-level transitions ($\it{P}$6 $\leftarrow$ $\it{P}$2). 49 ladder-type transitions with final rotational states $\it{J}$ = 10-12 in the range of 9510 to 9810 cm$^{-1}$ (i.e., the $\it{P}$6 polyad) were assigned to effective Hamiltonian predictions and the ExoMol database, of which 6 reached vibrational states that had not been observed experimentally before. 19 sub-Doppler V-type transitions with final states $\it{J}$ = 11-13 in the range of 6590 to 6900 cm$^{-1}$ (i.e., the $\it{P}$4 polyad) were observed and assigned to the Hamiltonian and ExoMol, while only 2 of these V-type transitions could be unambiguously assigned to WKLMC and HITRAN line lists. 170 Doppler-broadened four-level double-resonance (4LDR) lines were observed, 7 of which were newly observed compared with our previous work when pumping transitions starting from the $\it{J}$ = 7 level in the ground state [Lehmann et al., J. Chem. Phys. 163, 144304 (2025)]. We could not assign these lines as they did not form combination differences with other observed 4LDR transitions.
arXiv:2607.12756v1 Announce Type: new
Abstract: Vision-language models (VLMs) process large numbers of visual tokens, resulting in substantial inference latency and memory overhead. This has motivated extensive research on visual token compression. While training-free strategies rely on heuristic metrics and suffer significant performance degradation under high compression ratios, many training-based methods introduce external compression modules that force the VLM backbone to adapt, incurring substantial retraining cost and compromising VLMs' priors. Effective visual token compression hinges on strong information encoding, a capability already present in pretrained VLMs but underutilized by existing approaches. Motivated by this, we propose VisCo, a training-efficient self-compression framework that reuses the pretrained VLM itself as an intrinsic compressor. VisCo is a parameter-sharing autoencoder that compresses visual information using a small set of memory tokens and transfers hierarchical information from encoding to decoding. Experiments show that VisCo surpasses prior methods across all evaluated compression ratios, with larger gains under more aggressive compression, and remains stable even in the extreme single-token setting. Moreover, when combined with the original visual tokens, the learned memory tokens can even improve the base model, suggesting that VisCo captures complementary representations beyond compression.
arXiv:2607.12640v1 Announce Type: new
Abstract: Reinforcement learning with verifiable rewards, and Group Relative Policy Optimization (GRPO) in particular, is now run routinely on a supervised checkpoint in the hope of producing a stronger agent. We ask whether it adds skill to a small language and vision-language model web agent at the 4B to 8B scale, or whether it mostly reshapes behavior the supervised model already has. Across a control grid of 18 runs that varies learning rate, KL weight, seed, initialization, and clipping, no configuration credibly improves the success rate of a strong supervised baseline on tasks the agent has largely mastered. On the text track, moderate to high learning rates make it credibly worse. The null holds under paired testing, 25 evaluation seeds, 6 training seeds, changes to the recipe, both text and Set-of-Marks screenshot observations, and scaling the backbone to 8B; the credible harm is a text-track finding and is only nominal under Set-of-Marks. To show that the null reflects the setting and not a broken pipeline, we run the identical harness, reward, and recipe on tasks whose reward is reachable by sampling, and there the success rate rises by 22 points with a paired interval that excludes zero. GRPO therefore helps only when there is headroom to climb, meaning the sampled policy already succeeds more often than the greedy one. We then explain the failure. A middle learning rate degrades the agent and a high one collapses it, and the two regimes form a double dissociation: grafting localizes the degrade regime to the attention and MLP blocks, while the collapse regime cannot be traced to any single group, and the embedding change that dominates the weight movement is causally inert. At 4B, effective rank in the late layers tracks capability in both directions; at 8B the two come apart. This coupling is specific to the smaller model, so we report it as scale-dependent.
arXiv:2607.12801v1 Announce Type: new
Abstract: This study introduces a unified control framework for fixed-wing unmanned aerial vehicles (UAVs) fitted with a pan-tilt (PT) camera, intended to perform an end-to-end mission spanning from initial target detection to accurate terminal engagement. The proposed system employs a three-phase strategy: a vision-based target acquisition phase, an NMPC-based tracking phase, and a terminal guidance phase. During tracking, the framework uses an Unscented Kalman Filter (UKF) to fuse YOLO-based visual detections with inertial measurements, enabling robust target state estimation under unknown dynamics. To ensure reliable visual contact, we introduce a constraint-aware Nonlinear Model Predictive Control (NMPC) strategy that incorporates Control Barrier Functions (CBFs) to explicitly prevent UAV self-occlusion -- a common limitation in fixed-wing tracking. Upon satisfying terminal engagement conditions, the system seamlessly transitions control to a quaternion-based Biased Proportional Navigation Guidance (BPNG) law, enforcing precise impact angle constraints. High-fidelity simulations demonstrate that the framework achieves stable, robust tracking and accurate terminal interception while strictly respecting the vehicle's dynamic limits and camera field-of-view constraints.
arXiv:2607.12602v1 Announce Type: new
Abstract: Automatic voxel-level grounding of free-text findings in 3D chest Computed Tomography (CT) is critical for clinical interpretability. However, this task remains highly challenging due to the intricate spatial complexity of large 3D volumes and the heterogeneity of free-text findings. Existing end-to-end approaches often struggle to simultaneously learn the localized feature representations required for accurate 3D segmentation and the complex semantic understanding needed for text alignment, leading to suboptimal grounding performance. To overcome this fundamental limitation, we propose a novel decoupled framework that disentangles the problem into two specialized stages: (1) class-agnostic lesion segmentation and (2) text-volume reasoning. This structural separation allows the model to first extract candidate sub-volumes by localizing potential abnormalities. Subsequently, intensive cross-modal reasoning is performed to align these localized sub-volumes with free-text medical findings. To resolve the spatial ambiguities inherent in local regions, the reasoning module is augmented with explicit anatomical guidance, utilizing relative spatial coordinates and lung lobe priors. Evaluated on the ReXGroundingCT benchmark, our method achieves state-of-the-art performance in overall grounding quality on the official leaderboard. These results demonstrate that decoupling detection from reasoning is a highly effective paradigm for handling the complexity of 3D medical visual grounding. Our code is publicly available at https://github.com/khuhm/DAGG.
arXiv:2607.12934v1 Announce Type: new
Abstract: Remote sensing change detection (RSCD) models are prone to catastrophic forgetting when incrementally adapted to new domains. Existing domain-incremental learning (DIL) methods mainly preserve image-level representations but often overlook bitemporal discrepancy cues, which are critical for robust change detection under domain shifts. To address this limitation, we propose DG-FDD, a domain-incremental change detection framework that integrates Difference-Guided Adaptation and Frequency-Decoupled Distillation. Specifically, the Difference-Guided Dynamic Adapter (DGDA) models bitemporal feature discrepancies to promote change-aware feature adaptation and reduce domain-specific interference. Meanwhile, the Frequency-Decoupled Knowledge Distillation strategy with Cross-domain Synthesis (FDKD-CS) separates structural information from domain style in the frequency domain, enabling stable knowledge transfer without historical data. Extensive experiments on three public high-resolution RSCD datasets under two- and three-domain incremental protocols demonstrate that DG-FDD effectively mitigates catastrophic forgetting. Compared with independently trained single-task models, DG-FDD records mean relative changes in F1 and IoU of only -0.23% and -0.45%, respectively, across six two-domain sequences, and -0.69% and -1.31%, respectively, across the three evaluated three-domain sequences. These results indicate a favorable stability-plasticity balance between historical knowledge retention and new-domain adaptation in continual cross-domain change detection.
arXiv:2606.27741v2 Announce Type: replace
Abstract: Recent advances in video diffusion models have greatly improved visual fidelity, yet their generated motions often violate physical plausibility. We observe a common kinematic failure, "motion entanglement", the unintended coupling of independent motion sources, such as camera movement and object motion. We identify that this issue stems from data bias and the reconstruction-based training design of diffusion models. Training on noisy videos that still retain coarse motion cues inadvertently encourages the model to replicate existing motion without an incentive to learn how to model kinematically-grounded motions. To address this, we propose a Self-Imagination Fine-Tuning (SIFT) paradigm, which enables the model to learn from its own generated videos rather than directly reconstructing real ones, breaking the reconstruction shortcut. We further employ motion-aware discriminative supervision and a progressive hard-case replay strategy to stabilize and accelerate learning. By leveraging freely-generated text prompts, our method can densely cover a broad motion space, including rare or finely-disentangled scenarios that would be costly to collect as video data. Extensive experiments demonstrate that our approach substantially improves the physical realism, motion disentanglement, and controllability of generated videos.
arXiv:2606.29537v2 Announce Type: replace
Abstract: Existing computer-use benchmarks fail to capture the realism, complexity, and long-horizon demands of real-world computer use, limiting their ability to reveal the limitations of frontier agents. We introduce OSWorld 2.0, a benchmark of 108 long-horizon computer-use workflows across everyday and professional tasks, designed to capture complex and challenging real-world phenomena. Each task represents a realistic end-to-end workflow that takes human users a median of about 1.6 hours to complete and requires an average of 318 tool calls with Claude Opus 4.7 using maximum thinking, compared with about 30 in OSWorld 1.0. OSWorld 2.0 targets challenge phenomena that are common in real workflows yet underrepresented in prior benchmarks, spanning interaction-design challenges such as streaming interaction and dynamic environments, as well as agent-pattern challenges such as cross-source reasoning, implicit-state inference, and visual-spatial precision. Tasks are grounded in authentic input artifacts and cross-referenced against realistic stateful user profile data, and include separate safety reports auditing safety-sensitive execution. Under our primary binary-completion metric at 500 steps, Claude Opus 4.8 with maximum thinking and batched tool calls scores best but still completes only 20.6% of tasks at a 54.8% partial score; GPT-5.5 is far more token-efficient yet plateaus near 13%. These results show that current agents are still far from professional-level computer use: rather than stumbling on basic GUI control or coding, they lose track of constraints, miss information that arrives mid-task, guess rather than ask the user, and skip verification, struggling most when a task hinges on hidden state they must recover.
arXiv:2607.12557v1 Announce Type: new
Abstract: Large Vision-Language Models (LVLMs) face significant challenges in long video understanding due to the excessive computational cost and information loss associated with uniform sampling. Existing keyframe selection methods often treat video frames as atomic entities and allocate visual budgets equally, thereby overlooking high-level semantic structures and introducing substantial redundancy. To address these limitations, we propose GMM-EVA (Gaussian Mixture Modeling for Event-Aware Visual Allocation), which leverages Gaussian Mixture Models to model event-level structure from discrete frame-wise observations. A differentiated allocation strategy is then applied to preserve one primary high-resolution keyframe per event for high-fidelity detail, while utilizing lower-resolution secondary keyframes to maintain temporal context and optimize token budgets. GMM-EVA is a training-free, plug-and-play framework that generalizes robustly across various relevance measures and downstream LVLMs. Extensive experiments on multiple long video benchmarks demonstrate that our method significantly outperforms uniform sampling. Notably, GMM-EVA achieves comparable performance to baseline selection methods while utilizing only approximately half of the visual token budget, highlighting its superior efficiency and effectiveness.
arXiv:2607.12763v1 Announce Type: new
Abstract: Federated Reinforcement Learning (FedRL) enables coordination of distributed energy resources without sharing raw local data, but standard aggregation methods such as FedAvg do not account for system-level constraints, often leading to unsafe global behavior. In this work, we study constraint-aware aggregation for federated reinforcement learning in distributed energy coordination. We propose aggregation rules that incorporate both local performance and estimated constraint violation into the server-side update. Among these, a simple penalty-based rule, $w_i \propto R_i - \alpha V_i$, consistently provides the most reliable trade-off between reward and safety, without requiring dual optimization or modifications to local training. \textcolor{black}{We evaluate our approach on DairyGridEnv, a benchmark modeling multiple farms coordinating battery storage under stochastic demand and a shared grid capacity constraint, and further assess robustness using real load-driven demand profiles from Finland and the German FIELD dataset. Across multiple seeds, penalty-based aggregation substantially reduces violations while improving reward relative to FedAvg in both synthetic and real load-driven settings.} A combined reward-violation scheme exposes a tunable trade-off via $\lambda$, but is less stable. These results demonstrate that lightweight aggregation strategies can substantially improve empirical safety in federated reinforcement learning while preserving standard communication protocols.
arXiv:2606.20652v2 Announce Type: replace
Abstract: Simulating epidemic spread across an entire country requires balancing fine-grained realism with computational feasibility. We address this trade-off with a multiscale, hybrid modeling framework for simulating the spread of COVID-19 across Germany. The spatial domain is split into regions, each represented either by a high-resolution agent-based model (ABM) incorporating mobility data from mobile phones or by a faster, less detailed model based on partial (PDEs) or ordinary differential equations (ODEs). Data-driven jump processes model mobility between regions, enabling individuals to be transferred between model domains. Building on earlier studies on pairwise coupling strategies, we develop a unified framework that combines all three model classes within a single simulation environment. To demonstrate the framework's utility, we systematically compare ABM, PDE, and ODE representations of Berlin embedded in a nationwide simulation of Germany, investigate regional travel restrictions, and evaluate the Zero-COVID and No-COVID strategies. The results indicate that model resolution can be reduced in sufficiently homogeneous regions without substantially altering epidemic dynamics. Further, they reveal that mobility restrictions can lead to non-intuitive outcomes, including cases in which regional border closures increase infection numbers both locally and nationally. These effects are observed even between non-adjacent regions, illustrating how emergent, system-wide dynamics arise from local mobility restrictions. We quantify computational performance in terms of runtime savings and validate the framework against real-world infection data. The results show that the hybrid framework substantially reduces computational cost without sacrificing predictive accuracy, offering a practical tool for evaluating regional mobility restrictions and public health interventions at national scale.
arXiv:2607.09074v2 Announce Type: replace
Abstract: We show that every weighted hypergraph on $n$ vertices admits a spectral $\varepsilon$-sparsifier with $O(n\log n/\varepsilon^2)$ hyperedges, strengthening the independent STOC 2023 works of Lee and Jambulapati--Liu--Sidford by removing their rank dependence and answering Lee's open question on whether this loss is inherent. The key idea is global-dictionary chaining: after choosing clique edge weights with balanced effective resistances, every hyperedge seminorm is Lipschitz with respect to the same global-dictionary norm generated by normalized vertex-pair directions; the local rank complexity is thereby replaced by the Gaussian width of this common dictionary. Since these STOC 2023 works have become standard analytic primitives across a broad subsequent literature on spectral hypergraph sparsification and its variants, our rank-independent theorem sharpens many later guarantees that inherit their sampling bounds.
arXiv:2607.12946v1 Announce Type: new
Abstract: Recommender-system research for Vietnamese remains limited by the absence of a public, well-documented hotel interaction resource. Building such a resource is challenging for three reasons: cross-platform hotel names must be reconciled before interactions are comparable; quality must be audited with reproducible metrics rather than ad hoc cleaning; and public release must preserve privacy while remaining benchmarkable under realistic cold-start conditions. We introduce ViHoRec, a quality-controlled Vietnamese hotel recommendation dataset of 18{,}267 interactions between 6{,}832 users and 560 hotels, crawled from Booking.com, Traveloka, and Ivivu. Our contributions are: (i) a reproducible construction pipeline with cross-platform entity resolution and quantitative quality control; (ii) a privacy-preserving release with HMAC pseudonyms; and (iii) a public cold-start benchmark with temporal leave-last-one-out split, data-centric ablations, and dependency-free baselines. On the public split, learned models degrade sharply for users with short histories (BPR-MF Recall@10: 0.065 vs. 0.120), while UserKNN remains strongest overall, establishing ViHoRec as a sparse, cold-start-dominated testbed for low-resource recommendation. All data are publicly available at https://github.com/MinhNguyenDS/ViHoRec.
arXiv:2607.12949v1 Announce Type: new
Abstract: We develop a thermodynamically consistent framework for weakly nonlocal continua with tensor-valued internal variables. Let $\boldsymbol{L}=\operatorname{grad}\boldsymbol{v}$, with stretching tensor $\boldsymbol{D}=\operatorname{sym}\boldsymbol{L}$ and spin tensor $\boldsymbol{W}=\operatorname{skw}\boldsymbol{L}$. We introduce the generators $\boldsymbol{\Gamma}_{\alpha}=\boldsymbol{W}+\alpha\boldsymbol{D}$, $\alpha\in\{0,1\}$, which unify corotational and upper-convected transport. The resulting kinematic structure induces canonical frame-indifferent evolutions of both the internal variable and its spatial gradient, thereby providing a closure for gradient-dependent theories.
Starting from the balances of linear momentum and microforces, together with an internal power expenditure depending on the internal variable and its gradient, we derive a local free-energy imbalance for incompressible isothermal processes. Under isotropy and inherited symmetry assumptions, this imbalance admits a canonical decomposition into contributions associated with $\boldsymbol{D}$, $\operatorname{grad}\boldsymbol{L}$, the generator-induced rate $\mathfrak{D}_{\alpha}\boldsymbol{J}$, and its gradient $\mathfrak{D}^{\nabla}_{\alpha}(\operatorname{grad}\boldsymbol{J})$. This decomposition yields explicit constitutive restrictions ensuring thermodynamic consistency and identifies the induced higher-order stress contributions arising from gradient dependence.
Finally, we construct a coupled gradient theory combining viscoelasticity and constrained orientational order, in which distinct internal variables evolve under different transport mechanisms. The framework extends classical theories with tensorial internal variables, including Oldroyd-B and Landau-de Gennes-type models.
arXiv:2607.13025v1 Announce Type: new
Abstract: We show that every planar graph with $n \geq 3$ vertices admits a 4-coloring in which each color is used on fewer than $n/2$ vertices. This bound is the best possible. Moreover, such a coloring can be found in $O(n \log n)$ time. We also extend these results to five or more colors and to graphs on general surfaces.
arXiv:2604.12594v3 Announce Type: replace
Abstract: Lithium Iron Phosphate (LFP) Battery Energy Storage Systems (BESSs) are a key enabler of the energy transition. However, they are known to exhibit significant inaccuracies in the estimation of their State of Charge (SOC). Such estimation errors can directly impact the participation of BESSs in electricity markets. In this work, we demonstrate that neglecting SOC uncertainty in battery bidding can lead to significant delivery failures, including the inability to meet promised frequency reserves. To address this risk, we investigate bidding strategies that account for SOC uncertainty. We propose three constraint-tightening optimization approaches of increasing complexity: (i) a fixed-margin formulation, (ii) an adaptive-margin optimizer, and (iii) an uncertainty-aware optimization model. The latter explicitly accounts for the decision-dependent nature of the uncertainty. Numerical results demonstrate that while all three approaches robustify against SOC uncertainty, the uncertainty-aware formulation outperforms the others in maximizing revenue while ensuring reliable frequency reserve provision. This highlights the significance of treating SOC uncertainty as an endogenous process within the operational strategy.
arXiv:2604.13428v2 Announce Type: replace
Abstract: In a seminal work, Dooly, Goldman, and Scott (STOC 1998; JACM 2001) introduced the classic Online TCP Acknowledgment} problem: a sequence of $n$ packets arrives over time, and the objective is to minimize both the number of acknowledgments sent and the total delay experienced by the packets. They showed that a natural greedy algorithm, which acknowledges when the delay of pending packets equals the acknowledgment cost, is $2$-competitive.
Online TCP Acknowledgment is the canonical online problem with delay, capturing the fundamental tradeoff between reducing service cost through batching and the delay incurred by pending requests. Prior work has largely focused on richer service-cost models, e.g., Multi-Level Aggregation. However, besides the work of Albers and Bals (SODA 2003), which studies maximum delay and similar objectives, not much is known beyond the sum of delay costs of requests.
In this work, we study Online TCP Acknowledgment under two generalized delay-cost models. In the batch-aware model, each batch incurs a delay cost that depends on the packet delays within that batch. For the max-over-batches objective, we show that greedy remains $2$-competitive. For the sum-over-batches objective, the picture changes sharply: greedy is $\Omega(n)$-competitive, and the optimal deterministic competitive ratio is $\Theta(\log n)$. Our upper bounds only require the batch delay function to be monotone.
In the batch-oblivious model, the delay cost is a function of the global packet-delay vector. We show that greedy is $2$-competitive for continuous submodular delay costs, and more generally under a weaker zero-coordinate diminishing-marginals condition. This yields $2$-competitive algorithms for ordered norms. Using the submodular-norm approximation of Patton, Russo, and Singla, we also obtain an $O(\log n)$-competitive algorithm for arbitrary symmetric norms.
arXiv:2607.12571v1 Announce Type: new
Abstract: Vision-Language-Action (VLA) models are deployed through pipelines that end users cannot audit, and a poisoned VLA can behave normally on clean observations while a small visual trigger redirects a long-horizon robot policy before any failure becomes observable. Existing vision or language defenses rarely explain what a triggered VLA representation looks like or how to recover behavior without retraining. We study this gap through two independently proposed VLA attacks from groups with distinct injection strategies, BadVLA and INFUSE; the latter persists after downstream clean adaptation. Across the evaluated poisoned models, we identify a recurring internal mechanism: a \emph{compact causal footprint}, namely a small visual support that is attention-seeded, spatially compact, and \emph{causal} in a precise sense -- masking it returns a clean-calibrated evidence-evolution score to the normal operating region. This footprint motivates TrustVLA, a mechanism-guided inference-time defense that adapts the Dirichlet evidence framework from trusted classification to monitor per-token, per-layer epistemic uncertainty in VLA policies. With only a small clean calibration set, TrustVLA (i)~detects abnormal evidence evolution, (ii)~localizes the compact support by counterfactual mechanism-score drop, and (iii)~recovers the observation by localized inpainting. Across OpenVLA/LIBERO and $\pi_{0.5}$ transfer evaluations, TrustVLA reduces attack success while preserving clean-task performance, providing a retraining-free, mechanism-guided defense for visual-triggered VLA backdoors.
arXiv:2607.12872v1 Announce Type: new
Abstract: Music recordings and live streams are often affected by noise, reverberation, spectral imbalances, or artifacts that degrade listening quality. While speech enhancement has matured into a well-defined research area, music enhancement is less established because musical signals combine overlapping sources, wide bandwidths, strong dynamics, and intentional production effects. We study real-time music enhancement under strict causal and low-latency constraints. We formulate the task around recovery of the intended produced mix from acoustic and production-oriented degradations, adapt compact causal networks to music, and compare speech-derived real-time baselines, an external music-denoising model, an offline restoration reference, and a music-specific MusicFilterNet-MS variant. On the tested hardware, all causal models run faster than real time, but improvements depend strongly on the dataset, degradation type, and metric family; under several objective criteria, indiscriminate enhancement can worsen the degraded input. The main contribution is therefore a benchmark and an analysis rather than a universal best model: real-time music enhancement is feasible, but robust improvement requires degradation-aware modeling, stereo-aware processing, identity-preserving correction, and evaluation beyond a single objective score.
arXiv:2607.12563v1 Announce Type: new
Abstract: This paper examines fairness and accountability in global software development by focusing on how competence is assessed and valued across unequal regional contexts. We compare software engineers from East Africa (Rwanda and Uganda) and Northwestern Europe (Sweden and the Netherlands), regions that are increasingly connected but embedded in asymmetric technological, economic, and institutional structures. Despite the rapid growth of African technology ecosystems, empirical evidence on everyday engineering practice and evaluation in these contexts remains limited. We present findings from an on-site mixed-methods study with 48 software engineers across four countries. The study combines programming, system design, and code review tasks with semi-structured interviews. Our results reveal consistent gaps between measured performance and perceived competence. Senior engineers in Rwanda often performed at a level comparable to that of their European peers, yet European participants systematically underestimated the competence of East African engineers. We also observed differences in communication styles and organizational practices across regions, reflecting distinct but complementary ways of working.
arXiv:2607.12575v1 Announce Type: new
Abstract: AI agents are said to be forming an economy in which they pay, on their own, for the data, APIs, and compute they consume. x402, which settles a stablecoin payment on-chain for each purchase, is the most widely deployed protocol for this, and its hundreds of millions of settlements are read as proof that the economy has arrived. We show the count cannot be read as adoption: it is the one metric an interested party can manufacture almost for free, since the facilitator sponsors the gas and nothing on-chain marks who controls a payment. We give the first population-scale measurement of x402 on Base, supplemented with a coarser Solana census. Identifying settlements from their on-chain event and resolving the true payer through the meta-transaction layer, we sort each by what its trace can prove via a payment graph. Over a 280-day window Base carries 136{,}708{,}672 settlements worth \$44{,}121{,}383.81, concentrated on every axis we measure (payer, recipient, and value Gini all above 0.98), yet 21.20\% are fictitious and 63.78\% internal settlement within a linked cluster. What is genuinely independent is bounded: it lies between the \$187{,}861.35 that demonstrably reaches a nameable service and the \$20{,}258{,}746.09 (45.92\% of value) not provably manufactured. Finally, we resolve the count's manufacturable component, a coherent operator-driven economy, star-shaped, machine-timed, and gas-subsidized. Settlement count measures manufacturability, not adoption.