arXiv:2605.07501v2 Announce Type: replace
Abstract: Large reasoning models (LRMs) achieve strong performance via extended chain-of-thought (CoT) reasoning, yet suffer from excessive token consumption and high inference latency. Existing reinforcement learning (RL) approaches for CoT compression rely on uniform, static length penalties that neglect model capability dynamics and problem-level difficulty variation. We propose \textbf{ExpThink}\xspace, an RL framework that addresses both dimensions through two complementary mechanisms. First, \emph{experience-guided reward shaping} tracks the shortest correct solution found so far for each problem and applies a three-tier reward: full credit for concise correct responses, discounted credit for verbose correct ones, and zero for incorrect ones. The threshold tightens automatically with model improvement, forming a self-evolving curriculum that requires no manual scheduling. Second, \emph{difficulty-adaptive advantage} replaces standard deviation normalization with correct-count normalization, yielding monotonically difficulty-scaled gradients that amplify learning on hard problems to preserve accuracy while suppressing gradients on easy ones to encourage brevity. Together, these mechanisms enforce an accuracy-first, compression-second training objective. Experiments on multiple mathematical reasoning benchmarks demonstrate that \textbf{ExpThink}\xspace reduces average response length by up to 77\% while simultaneously improving accuracy, achieving up to $3\times$ higher accuracy-efficiency ratio (accuracy divided by average token count) than the vanilla baseline and outperforming existing RL-based compression methods on both metrics.
Science Journals
arXiv:2605.18327v1 Announce Type: new
Abstract: AI agents deployed into SRE workflows currently derive their understanding of environment state from raw observability telemetry at query time, paying a semantic-interpretation tax in tokens, latency, and inferential reliability. We propose Causely, a causal intelligence layer that maintains a structured representation of environment topology, attribute dependencies, and causal relationships that are anchroed to a ontological representation of the managed environment. Causely transforms raw telemetry into a live, queryable model providing the semantic and causal foundation AI agents require to diagnose, evaluate impact, and act safely in production. We evaluate this value proposition through a benchmark study conducted in a controlled setting with injected faults in a 24-microservice OpenTelemetry demo application. Our experiments compare four agent configurations (Claude Code, OpenAI Codex, HolmesGPT with Sonnet and Gemini backends). Experiments are run with and without access to Causely under two scenarios: an active incident and a healthy baseline. On the active-fault scenario, causal grounding reduces mean time-to-diagnosis by 63\%, mean token consumption by 60\%, and mean tool-call count by 78\%, compressing the investigation footprint by 4.8$\times$ and lowering direct API cost per run by 57\%; root-cause-diagnosis accuracy rises from 75\% to 100\%.
arXiv:2605.18328v1 Announce Type: new
Abstract: LED Virtual Production (VP) uses large LED volumes to render backgrounds in real time, enabling in-camera visual effects but making post-shot changes labor-intensive. We address this with CineMatte, a robust background matting framework for VP and beyond. CineMatte employs a cross-attention-conditioned design. Instead of concatenating the background with the input, CineMatte employs a Siamese, frozen DINOv3 Vision Transformer with shared weights to encode the input frame and the captured background separately. A cross-attention module compares the two streams to predict the foreground, preserving pretrained semantics and improving robustness to background shifts. Previous ViT-based matting models use a parallel convolutional "detail branch" to recover fine details, which can cause boundary artifacts in real-world samples due to semantic misalignment with the backbone. We instead replace it with a pretrained, image-guided feature upsampler, which largely mitigates the problem. We also introduce CineMatte-4K, a 4K HDR image-video dataset captured on a professional LED VP stage. To the best of our knowledge, the image subset is the first dataset for VP matting and is non-synthetic, obtained via green-screen insertion; the video subset includes camera motion with tracked trajectories so that arbitrary backgrounds can be rendered later with correct parallax. Across CineMatte-4K and public benchmarks (VideoMatte240K, YouTubeMatte), CineMatte not only excels in VP but also generalizes robustly to real-world footage.
arXiv:2401.14278v3 Announce Type: replace
Abstract: Blockchain performance has historically faced challenges posed by the throughput limitations of consensus algorithms. Recent breakthroughs in research have successfully alleviated these constraints by introducing a modular architecture that decouples consensus from execution. The move toward independent optimization of the consensus layer has shifted attention to the execution layer.
While concurrent transaction execution is a promising solution for increasing throughput, practical challenges persist. Its effectiveness varies based on the workloads, and the associated increased hardware requirements raise concerns about undesirable centralization. This increased requirement results in full nodes and stragglers synchronizing from signed checkpoints, decreasing the trustless nature of blockchain systems.
In response to these challenges, this paper introduces Chiron, a system designed to extract execution hints for the acceleration of straggling and full nodes. Notably, Chiron achieves this without compromising the security of the system or introducing overhead on the critical path of consensus. Evaluation results demonstrate a notable speedup of up to 30%, effectively addressing the gap between theoretical research and practical deployment. The quantification of this speedup is achieved through realistic blockchain benchmarks derived from a comprehensive analysis of Ethereum and Solana workloads, constituting an independent contribution.
arXiv:2402.12705v5 Announce Type: replace
Abstract: Reconfiguration problems ask whether one feasible solution can be transformed into another by a sequence of local moves while maintaining feasibility throughout. For integers $d \geq 1$ and $k \geq d+1$, the Distance Coloring problem asks if a given graph $G$ has a $(d, k)$-coloring, i.e., a coloring of the vertices of $G$ by $k$ colors such that any two vertices within distance $d$ from each other have different colors.
For ordinary proper colorings ($d=1$), the $k$-Coloring Reconfiguration problem is polynomial-time solvable for $k\le 3$ [Cereceda, van den Heuvel, and Johnson, J. Graph Theory 67(1):69--82, 2011] but is $\mathsf{PSPACE}$-complete for every fixed $k\ge 4$, even on bipartite graphs [Bonsma and Cereceda, Theor. Comput. Sci. 410(50):5215--5226, 2009]. In this work, we initiate a study of the distance-$d$ analogue, for $d \geq 2$. We show that even for planar, bipartite, and $2$-degenerate graphs, $(d, k)$-Coloring Reconfiguration remains $\mathsf{PSPACE}$-complete for every $d \geq 3$ via a reduction from the well-known Sliding Tokens problem. Our construction uses $k = k_0 + 2 + n(\lceil d/2\rceil-1)$ colors on instances of size $n$, where $k_0\in\{3d+3,3d+6\}$ (depending on the parity of $d$). For $d = 2$, the same reduction scheme can be adapted to show that the problem is $\mathsf{PSPACE}$-complete on planar and $2$-degenerate graphs with same values of $k$. Additionally, on split graphs, there is an interesting dichotomy: the problem is $\mathsf{PSPACE}$-complete when $d = 2$ and $k$ is large but can be solved efficiently when $d \geq 3$ and $k \geq d+1$. For chordal graphs, we show that the problem is $\mathsf{PSPACE}$-complete for even values of $d \geq 2$. Finally, we design a quadratic-time algorithm to solve the problem on paths for any $d \geq 2$ and $k \geq d+1$.
arXiv:2407.16216v4 Announce Type: replace
Abstract: Large language models (LLMs) trained via pretraining and supervised fine-tuning (SFT) can still produce harmful and misaligned outputs, or struggle in domains like math and coding. Reinforcement learning (RL)-based post-training methods, including Reinforcement Learning from Human Feedback (RLHF) methods like Direct Preference Optimization (DPO) and Reinforcement Learning with Verifiable Rewards (RLVR) approaches like PPO and GRPO, have made remarkable gains to alleviate these issues. Yet, no existing work offers a technically detailed comparison of the various methods driving this progress. In order to fill this gap, we present a timely survey that connects foundational components with latest advancements. We derive a single policy gradient framework that unifies pretraining, SFT, RLHF, and RLVR as special cases while also organizing the more recent techniques therein. The main contributions of our survey are as follows: (1) a self-contained introduction to MLE, RLHF, and RLVR foundations and the unified policy gradient framework; (2) detailed technical analysis of PPO- and GRPO-based methods alongside offline and iterative DPO approaches, decomposed along prompt sampling, response sampling, and gradient coefficient axes; (3) standardized notation enabling direct cross-method comparison; and (4) comprehensive comparison of implementation details and empirical results of each method in the appendix. We aim to serve as a technically grounded reference for researchers and practitioners working on LLM post-training.
arXiv:2605.11979v2 Announce Type: replace
Abstract: In this work, we propose a novel framework for accelerating the parareal algorithm, in which the coarse propagator is formulated as a two-step method and optimized with respect to the convergence factor.} We derive a rigorous error estimate for the proposed two-step parareal algorithm, yielding an explicit bound on the linear convergence factor. This estimate is not only of theoretical interest: it provides a quantitative guideline for selecting and designing coarse propagators. Guided by this estimate, we {consider the linear parabolic equation as an illustrative example and }construct an optimized two-step coarse propagator~(O2CP) that delivers very fast convergence in practice. The resulting method attains an optimized convergence factor of approximately $0.0064$, substantially smaller than that of commonly used practical coarse propagators in the classical parareal setting, while keeping the computational cost moderate. Numerical experiments on linear and nonlinear parabolic equations fully support the theoretical analysis and demonstrate rapid convergence of the two-step parareal algorithm equipped with the O2CP.
arXiv:2502.04055v2 Announce Type: replace
Abstract: Current evaluations of synthetic tabular data mainly focus on how well joint distributions are modeled, often overlooking the assessment of their effectiveness in preserving realistic event sequences and coherent entity relationships across columns.This paper proposes three evaluation metrics designed to assess the preservation of logical relationships among columns in synthetic tabular data. We validate these metrics by assessing the performance of both classical and state-of-the-art generation methods on a real-world industrial dataset.Experimental results reveal that existing methods often fail to rigorously maintain logical consistency (e.g., hierarchical relationships in geography or organization) and dependencies (e.g., temporal sequences or mathematical relationships), which are crucial for preserving the fine-grained realism of real-world tabular data. Building on these insights, this study also discusses possible pathways to better capture logical relationships while modeling the distribution of synthetic tabular data. The code is available at https://github.com/Yunbo-max/TabLogicEval.
arXiv:2502.17007v2 Announce Type: replace
Abstract: In this paper we argue that, to its detriment, transparency research overlooks many foundational concepts of artificial intelligence. As an illustrating example we focus on uncertainty quantification in the context of counterfactual explainability, demonstrating that its broader adoption could address key challenges in the field. To this end, we show how uncertainty can provide a principled unifying framework for counterfactual explainability by expressing the core counterfactual properties in terms of uncertainty, allowing us to build two variants of an explainer upon them -- one based solely on uncertainty estimates and another pairing them with distance measured in the feature space. Our comprehensive experiments illustrate highly competitive performance of our framework when compared to many state-of-the-art methods despite its radically simple design. More broadly, the paper demonstrates that integrating artificial intelligence fundamentals into transparency research promises to yield more reliable, robust and understandable predictive models. We posit that making artificial intelligence explainability truly uncertainty-aware is the first step towards this goal.
arXiv:2604.07649v4 Announce Type: replace
Abstract: Aggregating experimental data from papers enables materials scientists to build better property prediction models and to facilitate scientific discovery. Recently, interest has grown in extracting not only single material properties but also entire experimental measurements. To support this shift, we introduce LitXBench, a framework for benchmarking methods that extract experiments from literature. We also present LitXAlloy, a dense benchmark comprising 1426 total measurements from 19 alloy papers. By storing the benchmark's entries as Python objects, rather than text-based formats such as CSV or JSON, we improve auditability and enable programmatic data validation. We find that frontier language models, such as Gemini 3.1 Pro Preview, outperform existing multi-turn extraction pipelines by up to 0.37 F1. Our results suggest that this performance gap arises because extraction pipelines associate measurements with compositions rather than the processing steps that define a material.
arXiv:2501.12470v3 Announce Type: replace-cross
Abstract: With the growth of quantum platforms for gate-based quantum computation, compilation holds a crucial role in deciding the success of the implementation. While there has been rich research in compilation techniques for the superconducting-qubit regime. The trapped-ion architectures, currently leading in robust quantum computations for their reliable operations, still lack competitive compilation strategies. This work introduces a unifying hardware abstraction, the ``position graph'', representing various hardware architectures. With this abstraction, we model trapped-ion Quantum Charge-Coupled Device (QCCD) architectures, enabling high-quality, scalable compilation methods. Specifically, we propose scheduling algorithms called SHuttling-Aware PERmutative (SHAPER) and SHuttling-AWare (SHAW) heuristic searches to tackle the complex constraints and dynamics of trapped-ion machines, with the cooperation of state-of-the-art permutation-aware mapping. These approaches generate executable circuits and native instructions that respect the physical constraints of shuttling-based architectures. We evaluate proposed algorithms across theorized and real architectures using the position graph framework. For completeness, we also introduce a linear program of trapped-ion scheduling that yields the optimal schedules, enabling a direct comparison with our heuristics. Our algorithm can successfully compile programs for extreme architectures where priori algorithms fail. When the baseline does complete, our produced schedules are $1.45$ times faster on average, with best-case speedups up to $4$ times faster.
arXiv:2410.13846v3 Announce Type: replace
Abstract: Scaling language models to handle longer contexts introduces substantial memory challenges due to the growing cost of key-value (KV) caches. Motivated by the efficiency gains of hybrid models and the broad availability of pretrained large transformer backbones, we explore transitioning transformer models into hybrid architectures for a more efficient generation. In this work, we propose LightTransfer, a lightweight method that transforms models such as LLaMA into hybrid variants. Our approach identifies lazy layers -- those focusing on recent or initial tokens -- and replaces their full attention with streaming attention. This transformation can be performed without any training for long-context understanding tasks or with minimal fine-tuning for o1-like long reasoning generation tasks that require stronger reasoning capabilities. Experiments across diverse benchmarks and models (e.g., LLaMA, Mistral, QwQ-STILL) demonstrate that, even when half of the layers are identified as lazy, LightTransfer achieves up to 2.17$\times$ throughput improvement with minimal performance loss ($<1.5\%$ on LongBench) and achieves 53.3\% on math benchmark AIME24 of advanced o1-like long reasoning model QwQ-STILL.
arXiv:2503.14346v3 Announce Type: replace
Abstract: Multi-map Sparse Monocular visual Simultaneous Localization and Mapping applied to monocular endoscopic sequences has proven efficient to robustly recover tracking after the frequent losses in endoscopy due to motion blur, temporal occlusion, tools interaction or water jets. The sparse multi-maps are adequate for robust camera localization, however they are very poor for environment representation, they are noisy, with a high percentage of inaccurately reconstructed 3D points, including significant outliers, and more importantly with an unacceptable low density for clinical applications. We propose a method to remove outliers and densify the maps of the state of the art for sparse endoscopy multi-map CudaSIFT-SLAM. The NN LightDepth for up-to-scale depth dense predictions are aligned with the sparse CudaSIFT submaps by means of the robust to spurious LMedS. Our system mitigates the inherent scale ambiguity in monocular depth estimation while filtering outliers, leading to reliable densified 3D maps. We provide experimental evidence of accurate densified maps 4.15 mm RMS accuracy at affordable computing time in the C3VD phantom colon dataset. We report qualitative results on the real colonoscopy from the Endomapper dataset.
arXiv:2504.02676v2 Announce Type: replace
Abstract: In large-scale distributed applications, efficient and reliable broadcast protocols are essential for node communication. Tree-based broadcast lacks flexibility and may suffer performance degradation or even broadcast failure when cluster membership changes. Gossip-based broadcast incurs high bandwidth overhead and only provides probabilistic delivery guarantees. In tree-based broadcasting, when an internal node leaves, its child nodes need to reconnect to a new parent. This process may introduce instability, leading to potential message duplication and increased transmission latency. However, in cloud environments, node departures and arrivals are common, causing frequent performance degradation in tree-based broadcasting. This paper introduces Snow, a self-organizing broadcast protocol designed for cloud environments. Instead, it dynamically sends or forwards messages based on each node's membership view, ultimately forming a broadcast structure resembling a multi-way balanced tree(the height difference of leaf nodes is at most 1). Our experimental results showed that Snow maintains message delivery reliability and latency guarantees under node churn while maintaining low overhead without sending unnecessary redundant messages.
arXiv:2605.17625v1 Announce Type: new
Abstract: As Large Language Models (LLMs) evolve into persistent scientific collaborators, context window saturation has emerged as a critical bottleneck. Scientific workflows involving iterative data analysis and hypothesis refinement rapidly saturate even extended contexts with dense technical content, while monolithic approaches suffer from quadratic cost scaling and cognitive degradation. We evaluate a Dual Process Memory Architecture that decouples immediate episodic needs (constant 10-message window) from long-term consolidated knowledge (growing at approximately 3 tokens/message). Unlike prior social agent memory systems, our domain-specific consolidation addresses contradictory parameter evolution, multi-hop reasoning across experimental phases, and precise technical fact retention. Through large-scale evaluation spanning 15,000 messages with cross-model validation across six LLMs from three families (OpenAI, Anthropic, Google), totaling 1,440 queries, we establish three key findings. First, while full-context models fail at 10,000 messages due to context overflow, our system maintains 70-85% accuracy with 1-2 second latency using 62% fewer tokens (45,434 vs 120,000+ limit). Second, cross-model validation reveals architecture-level trade-offs independent of specific LLMs: Dual Process excels at numeric/temporal queries (65-90% accuracy) while RAG excels at historical retrieval (60-85%), suggesting complementary deployment strategies. Third, we identify a "Sim-to-Real" gap where synthetic tests maintain constant memory but realistic workflows exhibit linear growth (about 3 tokens/message), with consolidation quality emerging as the primary scalability bottleneck. The architecture successfully manages profiles with 14,000+ scientific facts (125k tokens), demonstrating that domain-specific memory consolidation enables sustained operation beyond full-context limits.
arXiv:2504.14965v2 Announce Type: replace
Abstract: Layer 2 (L2) protocols, payment channels, sidechains, and rollups, are central to blockchain scalability, enabling off-chain execution while preserving on-chain security. Despite growing deployment, existing security models remain protocol-specific and monolithic, hindering compositional reasoning and principled comparison of assumptions and requirements. We present a general security framework for L2 protocols in the IITM-style Universal Composability (iUC) model. At its core is a modular ideal functionality F_layer2 that abstracts mechanism-specific details while capturing the essential structure of L2 systems through composable subroutines for joining, submission, updating, reading, and settlement under adversarial conditions. This yields uniform definitions of safety, liveness, and data availability across a broad class of L2 protocols. We demonstrate generality by instantiating the framework for three representative constructions: the Brick payment channel, the Liquid sidechain, and the Arbitrum Nitro rollup. Each case study yields a protocol-specific ideal functionality derived from F_layer2 and tailored to its assumptions. Our analysis (i) establishes security via simulation-based proofs, (ii) exposes inherent trade-offs among safety, liveness, and data availability, and (iii) derives lower bounds characterizing fundamental limitations of each design class. Finally, we illustrate the framework as a design tool by presenting FRoll, the first optimistic rollup protocol with fast-finality guarantees, together with a security analysis in our model, showing how the framework supports requirement-driven design of L2 protocols.
arXiv:2505.06907v2 Announce Type: replace
Abstract: The rise of large language models (LLMs), such as ChatGPT, Gemini, and Grok, has reshaped the AI landscape. As prominent instances of foundational models (FMs), they exhibit remarkable capabilities in generating human-like content, pushing the boundaries towards artificial general intelligence (AGI). However, their large-scale nature, privacy sensitivity, and substantial computational demands pose significant challenges for personalized customization for end users. To bridge this gap, we present the vision of artificial personalized intelligence (API), which focuses on adapting FMs to individual users while ensuring privacy. As a central enabler of API, we propose personalized federated intelligence (PFI), a new paradigm that not only integrates the privacy benefits of federated learning (FL) with the generalization capabilities of FMs but also places personalization at its core. To this end, we first survey recent advances in FL and FMs that lay the foundation for PFI. We then explore core stages of the PFI pipeline: efficient personalization at the edge, trustworthy adaptation, and adaptive refinement via retrieval-augmented generation. Finally, we highlight future directions for enabling PFI. Overall, this survey aims to lay a foundation for the development of API as a complementary direction to AGI, with PFI as a key enabling paradigm.
arXiv:2505.20650v5 Announce Type: replace
Abstract: Accurate interpretation of numerical data in financial reports is critical for markets and regulators. Although XBRL (eXtensible Business Reporting Language) provides a standard for tagging financial figures, mapping thousands of facts to over 10k US GAAP concepts remains costly and error prone. Existing benchmarks oversimplify this task as flat, single step classification over small subsets of concepts, ignoring the hierarchical semantics of the taxonomy and the structured nature of financial documents. Consequently, these benchmarks fail to evaluate Large Language Models (LLMs) under realistic reporting conditions. To bridge this gap, we introduce FinTagging, the first comprehensive benchmark for structure aware and full scope XBRL tagging. We decompose the complex tagging process into two subtasks: (1) FinNI (Financial Numeric Identification), which extracts entities and types from heterogeneous contexts including text and tables; and (2) FinCL (Financial Concept Linking), which maps extracted entities to the full US GAAP taxonomy. This two stage formulation enables a fair assessment of LLMs' capabilities in numerical reasoning and taxonomy alignment. Evaluating diverse LLMs in zero shot settings reveals that while models generalize well in extraction, they struggle significantly with fine grained concept linking, highlighting critical limitations in domain specific structure aware reasoning.
arXiv:2505.20914v2 Announce Type: replace
Abstract: General object composition (GOC) aims to seamlessly integrate a target object into a background scene with desired geometric properties, while simultaneously preserving its fine-grained appearance details. Recent approaches derive semantic embeddings and integrate them into advanced diffusion models to enable geometry-editable generation. However, these highly compact embeddings encode only high-level semantic cues and inevitably discard fine-grained appearance details. We introduce a Disentangled Geometry-editable and Appearance-preserving Diffusion (DGAD) model that first leverages semantic embeddings to implicitly capture the desired geometric transformations and then employs a cross-attention retrieval mechanism to align fine-grained appearance features with the geometry-edited representation, facilitating both precise geometry editing and faithful appearance preservation in object composition. Specifically, DGAD builds on CLIP/DINO-derived and reference networks to extract semantic embeddings and appearance-preserving representations, which are then seamlessly integrated into the encoding and decoding pipelines in a disentangled manner. We first integrate the semantic embeddings into pre-trained diffusion models that exhibit strong spatial reasoning capabilities to implicitly capture object geometry, thereby facilitating flexible object manipulation and ensuring effective editability. Then, we design a dense cross-attention mechanism that leverages the implicitly learned object geometry to retrieve and spatially align appearance features with their corresponding regions, ensuring faithful appearance consistency. Extensive experiments on public benchmarks demonstrate the effectiveness of the proposed DGAD framework.
arXiv:2605.17653v1 Announce Type: new
Abstract: Sub-billion-parameter Transformer language models are increasingly deployed on edge devices, where the privacy, latency, and operating-cost advantages of on-device inference are constrained by tight memory-bandwidth, energy, and thermal budgets that make architectural choice and accelerator-specific cost central to efficient inference. We present LLMForge, a hardware-aware neural architecture search (NAS) framework whose three composable contributions together make edge-LM architecture search hardware-conditioned, since different substrates impose different hardware cost bottlenecks. Infinite-Head Attention (IHA) decouples the number of query heads, KV groups, and per-head query/key and value dimensions, expanding the feasible per-layer attention configuration space by approximately 400x over grouped-query attention within our search-space ranges. Forge-Former, an encoder-based surrogate for ranking architectural candidates, outperforms MLP and random-forest baselines. Forge-DSE, an NSGA-II-based design-space-exploration engine, pairs Forge-Former with a multi-backend hardware cost model spanning GPUs, systolic accelerators, and ring-dataflow edge accelerators. Across four different hardware substrates, the searches converge to visibly different architectures whose shapes track each substrate's cost bottleneck. On the multi-chip ring substrate, our co-search returns three 300M-scale deployment-aware variants on the Pareto front. Each is re-trained on FineWeb-Edu-10BT under matched recipe against SmolLM2-360M and Qwen-0.5B architecture baselines. The accurate variant has the lowest validation loss 2.798 and competitive benchmark performance with fewer parameters, the energy-optimized variant lowers energy per token by 40%, and the latency-optimized variant lowers TTFT and TPOT by 43%.
arXiv:2605.16659v1 Announce Type: cross
Abstract: The single-turn coil method is a destructive pulsed magnet for generating over 100 T with a few $\mu$-second pulse duration, and it inevitably causes the coil to explode. The temporal and spatial distributions of the electric current and magnetic field are highly inhomogeneous, arising from the skin effect, rapid temperature rise, and coil deformation. To grasp the dynamic phenomena in the single-turn coil, we conducted a finite element analysis using multiphysics simulation. We employed finite element method calculations using a fully 3D model of the single-turn coil with broken cylindrical symmetry. The calculated result revealed highly nonlinear diffusion of electric current, temperature, and magnetic fields, which are the sources of the inhomogeneous magnetic fields inside the single-turn coil in time and space.
arXiv:2505.24438v3 Announce Type: replace
Abstract: An important characteristic of temporal graphs is how the directed arrow of time influences their causal topology, i.e., which nodes can possibly influence each other causally via time-respecting paths. The resulting patterns are often neglected by temporal graph neural networks (TGNNs). To formally analyze the expressive power of TGNNs, we lack a generalization of graph isomorphism to temporal graphs that fully captures their causal topology. Addressing this gap, we introduce the notion of consistent event graph isomorphism, which utilizes a time-unfolded representation of time-respecting paths in temporal graphs. We compare this definition with existing notions of temporal graph isomorphisms. We illustrate and highlight the advantages of our approach and develop a temporal generalization of the Weisfeiler-Leman algorithm to heuristically distinguish non-isomorphic temporal graphs. Building on this theoretical foundation, we derive a novel message passing scheme for temporal graph neural networks that operates on the event graph representation of temporal graphs. An experimental evaluation shows that our approach performs well in a temporal graph classification experiment.
arXiv:2605.17661v1 Announce Type: new
Abstract: Autonomous agile robots need more than metric geometry: they must understand objects, rooms, places, and spatial relations for search, inspection, exploration, and human robot interaction. Conventional metric maps support localization and collision avoidance, but do not provide this semantic and relational structure. 3D scene graphs address this gap by connecting geometry with object level and room level understanding. Building such representations on agile platforms remains difficult because aerial and lightweight robots operate under strict payload, power, and compute limits, making RGB-D cameras and LiDAR sensors impractical for many onboard settings. We present Mono-Hydra++, a real time monocular RGB plus IMU pipeline for indoor metric semantic mapping and hierarchical 3D scene graph construction. The system combines M2H-MX, a DINOv3 based multi-task model for depth and semantics, with a deep feature visual inertial odometry front end, sparse predicted depth constraints in the VIO derived pose graph, semantic masking for dynamic regions, and pose aware temporal alignment before volumetric fusion in the Mono-Hydra backend. On the Go-SLAM ScanNet evaluation subset, Mono-Hydra++ achieves 1.6% lower average trajectory error than the strongest RGB-D baseline in our comparison, while using only monocular RGB plus IMU input. On calibrated 7-Scenes, it improves average ATE by 29.8% over the strongest competing calibrated baseline. We further validate Mono-Hydra++ in a real ITC building deployment using RealSense RGB plus IMU and demonstrate embedded feasibility by deploying the ONNX/TensorRT FP16 M2H-MX-L perception model at 25.53 FPS on a Jetson Orin NX 16GB. These results show that Mono-Hydra++ can provide real time metric semantic mapping and scene graph construction for resource constrained robotic platforms without relying on active depth sensors.
arXiv:2506.10959v3 Announce Type: replace
Abstract: While in-context learning (ICL) has achieved remarkable success in natural language and vision domains, its theoretical understanding-particularly in the context of structured geometric data-remains unexplored. This paper initiates a theoretical study of ICL for regression of H\"older functions on manifolds. We establish a novel connection between the attention mechanism and classical kernel methods, demonstrating that transformers effectively perform kernel-based prediction at a new query through its interaction with the prompt. This connection is validated by numerical experiments, revealing that the learned query-prompt scores for H\"older functions are highly correlated with the Gaussian kernel. Building on this insight, we derive generalization error bounds in terms of the prompt length and the number of training tasks. When a sufficient number of training tasks are observed, transformers give rise to the minimax regression rate of H\"older functions on manifolds, which scales exponentially with respect to the prompt length with the exponent depending on the intrinsic dimension of the manifold, rather than the ambient space dimension. Our result also characterizes how the generalization error scales with the number of training tasks, shedding light on the complexity of transformers as in-context kernel algorithm learners. Our findings provide foundational insights into the role of geometry in ICL and novels tools to study ICL of nonlinear models.
arXiv:2507.22136v3 Announce Type: replace
Abstract: Humans possess innate meta-learning capabilities, partly attributable to their exceptional color perception. In this paper, we pioneer an innovative viewpoint on few-shot learning by simulating human color perception mechanisms. We propose the ColorSense Learner, a bio-inspired meta-learning framework that capitalizes on inter-channel feature extraction and interactive learning. By strategically emphasizing distinct color information across different channels, our approach effectively filters irrelevant features while capturing discriminative characteristics. Color information represents the most intuitive visual feature, yet conventional meta-learning methods have predominantly neglected this aspect, focusing instead on abstract feature differentiation across categories. Our framework bridges the gap via synergistic color-channel interactions, enabling better intra-class commonality extraction and larger inter-class differences. Furthermore, we introduce a meta-distiller based on knowledge distillation, ColorSense Distiller, which incorporates prior teacher knowledge to augment the student network's meta-learning capacity. We've conducted comprehensive coarse/fine-grained and cross-domain experiments on eleven few-shot benchmarks for validation. Numerous experiments reveal that our methods have extremely strong generalization ability, robustness, and transferability, and effortless handle few-shot classification from the perspective of color perception.