arXiv:2605.16097v1 Announce Type: new Abstract: Multi-robot systems are integral to modern logistics, but their capabilities are often limited to tasks executable by individual agents. This paper addresses a critical gap in existing frameworks like Multi-Agent Path Finding (MAPF) and Task Allocation and Path Finding (TAPF), which lack true cooperation for transporting large items that require multiple agents. To this end, we formalise the Cooperative Transportation Task Allocation and Path Finding (CT-TAPF) problem, which integrates team formation, task assignment, and collision-free pathfinding. We present an optimal solver, Cooperative Transportation Task Conflict-Based Search (CT-TCBS), which features a novel Incremental Expansion strategy to tackle the combinatorial explosion inherent in team formation. Recognising the computational cost of optimality, we also develop a family of sub-optimal solvers that employ a global, task-centric perspective, selecting the next task to assign based on a global difficulty metric (Best Task or Worst Task). Our comprehensive empirical evaluation demonstrates three key findings: (1) the incremental expansion strategy significantly outperforms the naive combinatorial approach by successfully pruning the dominant task-allocation search space; (2) we identify a task-conflict expansion dilemma, where sophisticated conflict resolvers effective for large-agent pathfinding subproblems can be detrimental in the integrated CT-TAPF setting; and (3) our proposed sub-optimal solvers establish a new, more efficient frontier on the solution quality-runtime spectrum compared to "nn-" agent-centric baselines. This work provides a foundational framework and a set of effective algorithms for a new, practical class of cooperative multi-agent problems.
Science Journals
arXiv:2605.15927v1 Announce Type: new Abstract: Quantum chemistry calculations are often performed using atom-centered basis sets which are chosen to balance accuracy and cost. While they are systematically improvable, the total energy converges slowly with basis set size towards the complete basis set (CBS) limit. Common extrapolation methods require several intermediate-quality calculations to afford an estimate of the CBS energy. We propose combining a pairwise interaction model with a minimal complementary auxiliary basis set (CABS) baseline to estimate the CBS energy from a single quantum chemistry calculation in a minimal basis set via Kernel-Ridge-Regression (KRR), which is more efficient than both direct and $\Delta$-machine learning. We show that KRR on standard molecular representations can be improved by approximating atom-wise local kernels using Chebyshev polynomials which allows us to train KRR models efficiently on moderate compute resources, further enabling a data-driven approach towards CBS combining physical baselines capturing leading order effects with data-efficient machine learning models.
arXiv:2605.16153v1 Announce Type: new Abstract: This paper provides an algebraic exposition of the theory of dyadic morality (TDM), a psychological model of moral judgment grounded in a simple two-node template: an intentional agent causing harm to a vulnerable patient. We formalize TDM using structural causal modeling (SCM) notation and identify three psychological operators (typecasting operator, completion operator, and valence-dependent inference mechanism) that extend standard SCM to capture how people compute moral judgments under constraints. We address scalability challenges arising from TDM's dyadic limitation, showing how moral cognition compresses multi-node scenarios through node collapse and sequential processing. Drawing on this algebraic framework, we demonstrate concrete applications to AI policy design: detecting conflicting obligations, structuring helpfulness policies to preserve user agency, and designing post-failure communication as causal interventions. Finally, we recommend scoped, contextual measurement of mind perception over universal averaging to operationalize the theory empirically. This algebraic formalization enables neurosymbolic AI systems to compute morality in a way that is both mathematically rigorous and faithful to human moral cognition.
arXiv:2605.09421v3 Announce Type: replace Abstract: Code authorship attribution (CAA) supports software forensics, plagiarism detection, and intellectual property protection. However, existing supervised CAA approaches suffer from scarce training data and closed-world assumptions: they require sufficient labeled code from fixed candidate-author sets, making training difficult in low-data cases and predictions unreliable for open-world test pairs with unseen samples, or heterogeneous code pairs. Large language models remove task-specific training, but direct prompting depends on costly expert-designed prompts, can hallucinate over complex heterogeneous code pairs, and rarely yields auditable evidence traces. We propose MACAA, a belief-revision-based multi-agent framework for training-free code authorship verification. MACAA comprises a Coordinator and four Expert Agents analyzing layout, lexical, syntactic, and programming-pattern evidence. The Coordinator gathers expert signals for expansion, discounts unreliable evidence through contraction, and resolves conflicts through revision to preserve belief consistency, replacing direct LLM judgment with auditable hypothesis refinement. MACAA achieves 89.15\% F1 on same-language benchmarks and 80.00\% on mixed cross-language pairs, outperforming the baselines overall in both same-language and cross-language evaluations.
arXiv:2512.15693v2 Announce Type: replace Abstract: The misuse of AI-driven video generation technologies has raised serious social concerns, highlighting the urgent need for reliable AI-generated video detectors. However, most existing methods are limited to binary classification and lack the necessary explanations for human interpretation. In this paper, we present Skyra, a specialized multimodal large language model (MLLM) that identifies human-perceivable visual artifacts in AI-generated videos and leverages them as grounded evidence for both detection and explanation. To support this objective, we construct ViF-CoT-4K for Supervised Fine-Tuning (SFT), which represents the first large-scale AI-generated video artifact dataset with fine-grained human annotations. We then develop a two-stage training strategy that systematically enhances our model's spatio-temporal artifact perception, explanation capability, and detection accuracy. To comprehensively evaluate Skyra, we introduce ViF-Bench, a benchmark comprising 3K high-quality samples generated by over ten state-of-the-art video generators. Extensive experiments demonstrate that Skyra surpasses existing methods across multiple benchmarks, while our evaluation yields valuable insights for advancing explainable AI-generated video detection.
arXiv:2407.08094v3 Announce Type: replace-cross Abstract: We introduce the Binless Multidimensional Thermodynamic Integration (BMTI) method for nonparametric, robust, and data-efficient density estimation. BMTI estimates the logarithm of the density by initially computing log-density differences between neighbouring data points. Subsequently, such differences are integrated, weighted by their associated uncertainties, using a maximum-likelihood formulation. This procedure can be seen as an extension to a multidimensional setting of the thermodynamic integration, a technique developed in statistical physics. The method leverages the manifold hypothesis, estimating quantities within the intrinsic data manifold without defining an explicit coordinate map. It does not rely on any binning or space partitioning, but rather on the construction of a neighbourhood graph based on an adaptive bandwidth selection procedure. BMTI mitigates the limitations commonly associated with traditional nonparametric density estimators, effectively reconstructing smooth profiles even in high-dimensional embedding spaces. The method is tested on a variety of complex synthetic high-dimensional datasets, where it is shown to outperform traditional estimators, and is benchmarked on realistic datasets from the chemical physics literature.
arXiv:2605.15320v1 Announce Type: new Abstract: Avatar reconstruction has traditionally relied on per-subject optimization that requires hours of computation or on expensive preprocessing that limits scalability. We introduce FFAvatar, a generalizable feed-forward framework that reconstructs high-quality, animatable 3D Gaussian head avatars from few-shot unposed portrait images in seconds. FFAvatar fuses information from multiple source images into a unified canonical Gaussian representation through Multi-View Query-Former, which is animated via FLAME parameters predicted end-to-end directly from pixels, eliminating the overhead of offline FLAME extraction. We further propose a three-stage training curriculum that achieves both broad generalization and high-fidelity reconstruction: (i) scalable pretraining on extensive monocular video data with over 1M identities to learn strong generalizable priors; (ii) multi-view fine-tuning on a small but high-quality dataset of 360-degree captures to enhance geometric fidelity and extreme-view awareness; and (iii) optional personalization that adapts to specific identities for maximum fidelity within 500 optimization steps. Extensive experiments demonstrate that FFAvatar sets a new standard for identity preservation, geometric consistency, and animation fidelity. On the NeRSemble benchmark, it outperforms the state-of-the-art LAM by a substantial 5.5 PSNR gain. Furthermore, FFAvatar enables real-time deployment, reconstructing avatars in 2 seconds without personalization and 10 seconds with personalization, while supporting 49 FPS animation on a single NVIDIA A100 GPU.
arXiv:2605.15908v1 Announce Type: new Abstract: Natural images are continuous, yet most generative models synthesize them on discrete grids, limiting resolution-flexible generation. Continuous neural fields enable resolution-free rendering, but prior methods introduce continuity only at the decoding stage as an interpolation module, leaving the generative latent space discretized and reconstruction-oriented. We propose RaPD (Resolution-agnostic Pixel Diffusion), which performs diffusion in a continuous Neural Image Field (NIF) latent space. RaPD bridges this reconstruction-generation gap with Semantic Representation Guidance for generation-aware latent learning and a Coordinate-Queried Attention Renderer for coordinate-conditioned, scale-aware rendering. A single denoised latent can be rendered at arbitrary resolutions by changing only the query coordinates, keeping diffusion cost fixed. Experiments demonstrate superior generation quality and resolution scalability.
arXiv:2602.06932v4 Announce Type: replace Abstract: Speculative decoding can significantly accelerate LLM serving, yet most deployments today disentangle speculator training from serving, treating speculator training as a standalone offline modeling problem. We show that this decoupled formulation introduces substantial deployment and adaptation lag: (1) high time-to-serve, since a speculator must be trained offline for a considerable period before deployment; (2) delayed utility feedback, since the true end-to-end decoding speedup is only known after training and cannot be inferred reliably from acceptance rate alone due to model-architecture and system-level overheads; and (3) domain-drift degradation, as the target model is repurposed to new domains and the speculator becomes stale and less effective. To address these issues, we present Aurora, a unified training-serving system that closes the loop by continuously learning a speculator directly from live inference traces. Aurora reframes online speculator learning as an asynchronous reinforcement-learning problem: accepted tokens provide positive feedback, while rejected speculator proposals provide implicit negative feedback that we exploit to improve sample efficiency. Our design integrates an SGLang-based inference server with an asynchronous training server, enabling hot-swapped speculator updates without service interruption. Crucially, Aurora supports day-0 deployment: a speculator can be served immediately and rapidly adapted to live traffic, improving system performance while providing immediate utility feedback. Across experiments, Aurora achieves a 1.5x day-0 speedup on recently released frontier models (e.g., MiniMax M2.1 229B and Qwen3-Coder-Next 80B). Aurora also adapts effectively to distribution shifts in user traffic, delivering an additional 1.25x speedup over a well-trained but static speculator on widely used models (e.g., Qwen3 and Llama3).
arXiv:2512.19053v2 Announce Type: replace-cross Abstract: A detection method for high-frequency gravitational waves using two-dimensional ion crystals is investigated. Gravitational waves can resonantly excite the drumhead modes of the ion crystal, particularly the parity-odd modes. In the optical dipole force protocol, entanglement between the drumhead modes and the collective spins transfers the excitation of the drumhead modes to the rotation of the total spin. Furthermore, gravitational wave detection beyond the standard quantum limit becomes possible as a squeezed spin state is generated through this entanglement. The sensitivity gets better with a larger ions crystals as well as a larger number of the ions. Future realization of large ion crystals can significantly improve the sensitivity to gravitational waves in the 10 kHz to 10 MHz region.
arXiv:2602.03922v3 Announce Type: replace Abstract: Standard sequence mixing layers used in language models struggle to balance efficiency and performance. Self-attention performs well on long context tasks but has expensive quadratic compute and linear memory costs, while linear attention and SSMs use only linear compute and constant memory but struggle with long context processing. In this paper, we develop a sequence mixing layer that aims to find a better compromise between memory-compute costs and long-context processing, which we call online vector-quantized (OVQ) attention. OVQ-attention requires linear compute costs and constant memory, but, unlike linear attention and SSMs, it uses a sparse memory update that allows it to greatly increase the size of its memory state and, consequently, memory capacity. We develop a theoretical basis for OVQ-attention based on Gaussian mixture regression, and we test it on a variety of synthetic long context tasks and on long context language modeling. OVQ-attention shows significant improvements over linear attention baselines and the original VQ-attention, on which OVQ-attention was inspired. It demonstrates competitive, and sometimes identical, performance to strong self-attention baselines up 64k sequence length, despite using a small fraction of the memory of full self-attention.
arXiv:2604.04539v2 Announce Type: replace Abstract: Reinforcement learning (RL) is a core approach for robot control when expert demonstrations are unavailable. On-policy methods such as Proximal Policy Optimization (PPO) are widely used for their stability, but their reliance on narrowly distributed on-policy data limits accurate policy evaluation in high-dimensional state and action spaces. Off-policy methods can overcome this limitation by learning from a broader state-action distribution, yet suffer from slow convergence and instability, as fitting a value function over diverse data requires many gradient updates, causing critic errors to accumulate through bootstrapping. We present FlashSAC, a fast and stable off-policy RL algorithm built on Soft Actor-Critic. Motivated by scaling laws observed in supervised learning, FlashSAC sharply reduces gradient updates while compensating with larger models and higher data throughput. To maintain stability at increased scale, FlashSAC explicitly bounds weight, feature, and gradient norms, curbing critic error accumulation. Across over 60 tasks in 10 simulators, FlashSAC consistently outperforms PPO and strong off-policy baselines in both final performance and training efficiency, with the largest gains on high-dimensional tasks such as dexterous manipulation. In sim-to-real humanoid locomotion, FlashSAC reduces training time from hours to minutes, demonstrating the promise of off-policy RL for sim-to-real transfer.
arXiv:2604.09173v2 Announce Type: replace Abstract: Managing large-scale vector datasets with disk-resident graph approximate nearest neighbor search (ANNS) systems incurs substantial storage overhead due to the co-location of vector data and auxiliary index metadata, which prevents the storage layer from exploiting their distinct compressibility. We present COMPASS, a component-aware compressed storage framework for disk-resident graph vector search. Leveraging data-index decoupling as a foundation, COMPASS losslessly compresses each component according to its distinct compressibility characteristics, thereby significantly reducing storage space. It further adapts the search and update paths to preserve their performance under compressed storage layouts. Evaluation on real-world public and proprietary billion-scale datasets shows that COMPASS reduces storage space by up to 58.7%, while delivering improved or competitive search and update performance compared to state-of-the-art disk-resident graph ANNS systems.
arXiv:2605.14344v2 Announce Type: replace Abstract: Generative modeling has emerged as a promising approach for crystal structure discovery. However, existing LLM-based generative models struggle with low-level atomic precision, while diffusion-based methods fall short in integrating high-level scientific knowledge. As a result, generated structures are often invalid, unstable, or do not possess desirable properties. To address this gap, we propose CrystalReasoner (CrysReas), an end-to-end LLM framework that generates crystal structures from natural language instructions through reasoning and alignment. CrysReas introduces physical priors as thinking tokens, which include crystallographic symmetry, local coordination environments and predicted physical properties before generating atomic coordinates. This bridges the gap between natural language and 3D structures. CrysReas then employs reinforcement learning (RL) with a multi-objective, dense reward function to align generation with physical validity, chemical consistency, and thermodynamic stability. For property-conditioned tasks, we design task-specific reward functions and train specialized models for discrete constraints (e.g., space group) and continuous properties (e.g., elasticity, thermal expansion). Empirical results demonstrate that compared to prior works and baselines without thinking traces or RL, CrysReas obtains better performance on diverse metrics, triples S.U.N. ratio, and achieves better performance for property conditioned generation. CrysReas also exhibits adaptive reasoning, increasing reasoning lengths as the number of atoms increases. Our work demonstrates the potential of leveraging thinking traces and RL for generating valid, stable, and property-conditioned crystal structures.
arXiv:2604.05966v2 Announce Type: replace Abstract: Financial reporting systems increasingly leverage Large Language Models (LLMs) to extract and summarize corporate disclosures. However, most existing approaches assume a single-market setting and overlook structural differences across jurisdictions. Variations in accounting taxonomies, tagging infrastructures (e.g., XBRL vs.\ PDF), and aggregation conventions introduce substantial challenges for semantic alignment and reliable verification. Here, we aim to bridge this gap. We present FinReporting, an agentic workflow for localized cross-jurisdiction financial reporting. The system constructs a unified canonical ontology spanning the income statement, balance sheet, and cash flow statement, and decomposes reporting into auditable stages, including filing acquisition, extraction, canonical mapping, and anomaly logging. Rather than treating LLMs as free-form generators, FinReporting employs them as constrained verifiers operating under explicit decision rules with evidence grounding. Evaluated on annual filings from the USA, Japan, and China, FinReporting improves consistency and reliability under heterogeneous reporting regimes. We further release an interactive demo that enables cross-market inspection and supports structured export of localized financial statements. Our demo is available at url{https://huggingface.co/spaces/BoomQ/FinReporting-Demo. A video describing our system is available at https://www.youtube.com/watch?v=f65jdEL31Kk.
arXiv:2512.19179v3 Announce Type: replace Abstract: Efficiently harnessing GPU compute is critical to improving user experience and reducing operational costs in large language model (LLM) services. However, current inference engine schedulers overlook the attention backend's sensitivity to request-length heterogeneity within a batch. As state-of-the-art models now support context windows exceeding 128K tokens, this once-tolerable inefficiency has escalated into a primary system bottleneck, causing severe performance degradation through GPU underutilization and increased latency. We present CascadeInfer, a runtime system that dynamically reschedules requests across multiple instances serving the same LLM to mitigate per-instance length heterogeneity. CascadeInfer partitions these instances into length-specialized groups, each handling requests within a designated length range, naturally forming a pipeline as requests flow through them. CascadeInfer devises a dynamic programming algorithm to efficiently find the stage partition with the best QoE, employs runtime range refinement together with decentralized load (re)balance both across and within groups, achieving a balanced and efficient multi-instance service. Our evaluation shows that, under the same configuration, CascadeInfer reduces end-to-end latency by up to 67% and tail latency by up to 69%, while improving overall system throughput by up to 2.89 times compared to the state-of-the-art multi-instance scheduling systems.
arXiv:2603.01283v3 Announce Type: replace Abstract: Deployed reinforcement learning systems lack a principled runtime reliability theory. We close this gap by introducing Bipredictability, P, a closed form information theoretic metric that quantifies how efficiently a closed loop interaction between agent and environment converts uncertainty into shared predictability. P admits a provable classical bound P equal, smaller than 0.5, derived from Shannon entropy subadditivity, and responsive agency necessarily suppresses P below this ceiling, a structural prediction we term the informational cost of agency. Across 21 trained continuous control agents, we confirm this prediction empirically at P = 0.33 plus minus 0.02. The same suppression signature reproduces in language model dialogue, convolutional vision systems, and classical mechanical baselines, indicating that P captures a substrate independent property of agentic interaction rather than an algorithm specific artifact. The Information Digital Twin, IDT, a model agnostic architecture that computes P from the external interaction stream, detects 89.3% of coupling degradations against 44.0% for reward based monitoring, with 4.4 times lower latency. P provides the missing measurement layer for runtime reliability and closed loop self regulation in deployed autonomous systems.
arXiv:2507.00275v2 Announce Type: replace Abstract: Double Q-learning is a classical control algorithm that mitigates the maximization bias of Q-learning. To do so, it explicitly trains two independent action-value functions and uses them to decouple action-selection and action-evaluation when computing bootstrap targets. Double DQN adapts target bootstrap decoupling to deep reinforcement learning (RL), but explicitly trains only a single action-value function and does not fully decouple its estimators. Consequently, the two estimators remain correlated, and overestimation persists. In this paper, we introduce Deep Double Q-learning (DDQL), a deep RL algorithm that explicitly trains two Q-functions through Double Q-learning. DDQL stabilizes training through a combination of techniques, including lower replay ratios, longer target network update intervals, and shared layers. Across 57 Atari 2600 games, DDQL improves aggregate performance over Double DQN, outperforming it on 47 games while further reducing overestimation. In addition, we study key design choices when adapting Double Q-learning to deep RL, including the network architecture, replay ratio, and minibatch sampling strategies.
arXiv:2603.08063v3 Announce Type: replace Abstract: Cross-view UAV geolocalization is fundamentally a challenging large-scale image retrieval task, aiming to determine the geographic coordinates of Unmanned Aerial Vehicle (UAV) queries by matching them against an extensive geo-tagged satellite image database. Most existing methods learn separate feature representations for each view and determine the final prediction using naive heuristics to assess feature similarity, thereby neglecting to model the crucial cross-view relationships. In this paper, we propose SkyLink, a novel plug-and-play ranking framework that pioneers joint relational modeling of inter-view relationships to enhance cross-view UAV geolocalization. SkyLink leverages a Large Vision-Language Model (LVLM) to model the intricate visual-semantic relationships between UAV and satellite views, facilitating effective cross-view matching. To further refine the learning process, we introduce a relational-aware loss. It leverages soft labels to provide a more nuanced supervision signal, mitigating the harsh penalty on near-positive pairs. This approach enhances both training stability and the model's discriminative capacity. Extensive experiments conducted across multiple base retrieval architectures and benchmark datasets demonstrate that SkyLink significantly boosts the ranking effectiveness of existing models, consistently achieving superior performance in various challenging scenarios.
arXiv:2605.15577v1 Announce Type: new Abstract: In the High-Level Trigger (HLT) of both electron-positron and hadron collision experiments, the tracking process for large-volume gaseous detectors typically consumes a latency of hundreds of milliseconds. Upgrades of existing experiments and the development of next-generation facilities demand enhanced HLT tracking performance: handling higher detector occupancy and suppressing latency. To address high occupancy conditions, a novel HLT tracking algorithm based on track segments is proposed. This method involves constructing a pattern bank comprising 11 pre-defined patterns, optimizing edge-matrix formation using position, momentum, and timing criteria, and merging stereo superlayer segments to improve track consistency. These measures significantly reduce the number of stored segments and the size of the edge matrix, thereby lowering the complexity of global tracking. Even at 25\% occupancy, the number of elements for global tracking is reduced to approximately 400-500, while the density of the edge matrix remains below 1\%. With the depth-first search within connected components, the simulation results show that the algorithm maintains stable performance with occupancy ranging from 5\% to 25\%, achieving a data compression ratio of approximately 50\% to 70\%. Validation against the STCF offline reconstruction algorithm confirms that the HLT algorithm preserves high signal-hit retention without introducing significant adverse effects on offline tracking efficiency or on the reconstruction. These results demonstrate that the proposed algorithm can retain high-quality signal hits across a broad range of occupancy levels, indicating a strong potential for further development and adaptation to even more challenging, high-luminosity experimental conditions.
arXiv:2511.22279v3 Announce Type: replace Abstract: Radiation forces and torques enable the manipulation of objects with acoustic and electromagnetic waves. Yet, harnessing them in complex scattering media remains a formidable challenge, especially when multiple objects must be controlled under competing objectives. Here, we demonstrate that sound or light can be shaped to tailor momentum transfer to multiple objects simultaneously in a complex scattering medium. For a single object, our theory yields the maximal achievable force or torque; for multiple objects, it produces Pareto-optimal actuation and exact bounds on the simultaneous realization of incompatible objectives. This opens new applications for wave tweezers, enabling selective and precise manipulation of objects within complex media, ranging from the handling of cells, organoids, or microrobots, to targeted drug delivery in biological media.
arXiv:2605.16062v1 Announce Type: cross Abstract: Correlative nanoscale surface characterization benefits from simultaneously measuring electronic and structural properties in the same environment, a capability that is essential for modern-day materials science and semiconductor failure analysis. In-situ AFM-SEM measurements facilitated by self-sensing cantilevers offer great potential here; however, they are limited due to their inherent capacitive crosstalk. Here, we demonstrate for the first time the in-situ implementation of single-pass heterodyne Kelvin probe force microscopy inside a scanning electron microscope, using piezo-resistive cantilevers. We overcome the capacitive crosstalk prevalent in piezo-resistive cantilevers by demodulating excitation and detection to simultaneously map surface topography and contact potential difference for correlation with compositional analysis. We systematically compare different operational modes of this heterodyne technique, elucidating their spatial resolution, signal sensitivity, and signal-to-noise ratio. The integrated approach yields exceptional signal quality and reveals how electron beam scan parameters can directly influence surface potential contrast. We demonstrate this correlative analysis workflow on two-dimensional heterostructures and semiconductor circuits. This work establishes a robust and versatile correlative imaging mode for in-situ Kelvin force and topography imaging inside a scanning electron microscope for next-generation semiconductor device analysis and materials science.
arXiv:2602.09297v3 Announce Type: replace Abstract: Transformers update token representations through multi-head attention and residual connections as $X \leftarrow X + \sum_{i} P^{(i)}XW_{V_i}W_{o_i}$, where $P^{(i)}$ is the softmax attention matrix in head $i$. We propose replacing a subset of $P^{(i)}$'s with the Laplacian $I - P^{(i)}$, giving $X \leftarrow X + \sum_{i \in \mathcal{A}} P^{(i)}XW_{V_i}W_{o_i} + \sum_{i \in \mathcal{L}} (I - P^{(i)})XW_{V_i}W_{o_i}$. Our proposal has two motivations. First, it allows attention heads to update the mean of token representations, while Laplacian heads can directly control within-sequence variance. Second, if tokens are viewed as nodes in a graph with edge weights $P^{(i)}$, then $I - P^{(i)}$ is the corresponding graph Laplacian, and the update can be interpreted as one step of heat diffusion on the graph. We show that this simple modification improves performance across supervised learning, language modeling, and self-supervised learning tasks. To investigate why, we examine the token representations learned with and without Laplacian heads. In supervised learning, Laplacian heads collapse token representations within the same sequence and align the sequence means with the geometry of Neural Collapse. In language modeling, they increase the separability of token representations that share the same next-token prediction. In self-supervised learning, they produce token representations whose principal components are better suited for segmentation. Across modalities, they also lead to faster-decaying spectra, indicating stronger token smoothing. Overall, our findings challenge the prevailing view that token oversmoothing is inherently harmful, showing instead that certain forms of smoothing can be beneficial.
arXiv:2602.16274v2 Announce Type: replace Abstract: We present the first regret bound for classical online Q-learning in infinite-horizon discounted Markov decision processes (MDPs), without relying on optimism or bonus terms. We first analyze Boltzmann Q-learning with decaying temperature and show that its regret depends critically on the suboptimality gap of the MDP: for sufficiently large gaps, the regret is sublinear, while for small gaps it deteriorates and can approach linear growth. To address this limitation, we study a Smoothed $\epsilon_n$-Greedy exploration scheme that combines $\epsilon_n$-greedy and Boltzmann exploration, for which we prove a gap-robust regret bound of near-$\tilde{O}(N^{9/10})$. We also obtain sample complexity guarantees, with both regret and sample complexity bounds holding with high probability. To analyze these algorithms, we develop a high-probability concentration bound for contractive Markovian stochastic approximation with iterate- and time-dependent transition dynamics. This bound may be of independent interest as the contraction factor in our framework is allowed to converge to one asymptotically.
arXiv:2511.02342v3 Announce Type: replace Abstract: Aerial manipulation combines the maneuverability of multirotors with the dexterity of robotic arms to perform complex tasks in cluttered spaces. Yet planning safe, dynamically feasible trajectories remains difficult due to whole-body collision avoidance and the conservativeness of common geometric abstractions such as bounding boxes or ellipsoids. We present a whole-body motion planning and safety-critical control framework for aerial manipulators built on superquadrics (SQs). Using an SQ-plus-proxy representation, we model both the vehicle and obstacles with differentiable, geometry-accurate surfaces. Leveraging this representation, we introduce a maximum-clearance planner that fuses Voronoi diagrams with an equilibrium-manifold formulation to generate smooth, collision-aware trajectories. We further design a safety-critical controller that jointly enforces thrust limits and collision avoidance via high-order control barrier functions. In simulation, our approach outperforms sampling-based planners in cluttered environments, producing faster, safer, and smoother trajectories and exceeding ellipsoid-based baselines in geometric fidelity. Actual experiments on a physical aerial-manipulation platform confirm feasibility and robustness, demonstrating consistent performance across simulation and hardware settings. The video can be found at https://youtu.be/hQYKwrWf1Ak.