Searcharxiv⌕ Search

arXiv subjects

Yikun Wang

Publications and source records attributed to Yikun Wang.

At least 19 recordsLinked to original sources
arXiv2026

TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents

Document parsing aims to transform unstructured documents into structured and machine-readable representations. Recent advances in Vision-Language Models (VLMs) have significantly advanced document parsing. However, existing approaches still face two major challenges. First, decoupled VLM-based methods heavily rely on accurate layout analysis, where geometric distortions in camera-captured documents can introduce cascading errors. Second, although end-to-end VLM-based methods alleviate the dependence on explicit layout detection, they often suffer from redundant generation, hallucinations, and insufficient structural reasoning in high-resolution scenarios. To address these challenges, we propose TeleOCR, a unified framework for document parsing. TeleOCR introduces deformation-aware learning to incorporate geometric perception into VLMs and proposes an adaptive sampling mechanism for complex layout representation. Furthermore, a content-structure decoupled learning strategy is developed to explicitly model formula grammars and table structures, enabling more effective structured representation learning. Extensive experiments demonstrate that TeleOCR achieves state-of-the-art performance across diverse document parsing benchmarks. It obtains overall scores of 96.87, 88.53 and 78.41 on OmniDocBench v1.6, Wild-OmniDocBench, and PureDocBench, respectively, and ranks first in the ICDAR 2026 Sci-ImageMiner Challenge. These results validate the effectiveness and generalization capability of TeleOCR in complex document parsing scenarios.

cs.CV↗
arXiv2026

Memory-Native Non-Terrestrial Networks for Embodied Intelligence

Non-terrestrial networks (NTN) provide ubiquitous connectivity for embodied intelligence (EI), enabling robots in the wilderness to leverage cloud resources or report critical information to remote centers. However, the synergy is nontrivial due to the highly dynamic, resource-constrained, topology-varying, and task-oriented environment. Existing memoryless NTN protocols become inefficient, since the decisions are driven by local channel conditions and instantaneous service demands. To address these limitations, this paper proposes the memory-native NTN (Mem-NTN) paradigm that leverages long-horizon contexts for memory-augmented system optimization. To realize this paradigm shift, we establish a dual-memory architecture that distinguishes between physical memory representing the state of the world and digital memory encoding historical network experience. We develop memory acquisition, compression, valuation, update, and utilization mechanisms that facilitate cross-layer, memory-native decision-making, spanning from the physical and access layers up to the network and application layers. Experiments in satellite embodied question answering (SEQA) demonstrate that the proposed Mem-NTN consistently outperforms conventional stateless NTN and terrestrial approaches.

cs.RO↗
arXiv2026

LAGS: Low-Altitude Gaussian Splatting with Groupwise Heterogeneous Graph Learning

Low-altitude Gaussian splatting (LAGS) facilitates 3D scene reconstruction by aggregating aerial images from distributed drones. However, as LAGS prioritizes maximizing reconstruction quality over communication throughput, existing low-altitude resource allocation schemes become inefficient. This inefficiency stems from their failure to account for image diversity introduced by varying viewpoints. To fill this gap, we propose a groupwise heterogeneous graph neural network (GW-HGNN) for LAGS resource allocation. GW-HGNN explicitly models the non-uniform contribution of different image groups to the reconstruction process, thus automatically balancing data fidelity and transmission cost. The key insight of GW-HGNN is to transform LAGS losses and communication constraints into graph learning costs for dual-level message passing. Experiments on real-world LAGS datasets demonstrate that GW-HGNN significantly outperforms state-of-the-art benchmarks across key rendering metrics, including PSNR, SSIM, and LPIPS. Furthermore, GW-HGNN reduces computational latency by approximately 100x compared to the widely-used MOSEK solver, achieving millisecond-level inference suitable for real-time deployment.

cs.CV↗
arXiv2026

The Impact of Splashback Galaxies on Galaxy Assembly Bias

The clustering of galaxies is affected by the assembly history of their underlying dark matter halos. This complex phenomenon, known as galaxy assembly bias, has been extensively studied, but the exact physical origin remains unclear. Splashback halos, typically low-mass halos that have traversed larger neighboring halos, have been suggested to be associated with halo assembly bias. Using a semi-analytic galaxy-formation model applied to the Millennium simulation, we explicitly explore the role that splasback galaxies play in galaxy assembly bias. We identify splashbacks as present-day central galaxies that were formerly satellites of a more massive host, and construct stellar-mass selected galaxy samples with the splashbacks either removed or reclassified as satellites of their former host halo. We find that splashbacks tend to reside in low-mass, highly concentrated halos and in dense environments, and that they have relatively high stellar-to-halo mass ratios. Splashbacks appear to be largely responsible for the low-mass tail of the occupancy variation for highly concentrated halos and for halos in dense environments. Finally, when computing the impact of assembly bias on galaxy clustering, we find that while removing the splashbacks significantly reduces the signal, reassigning them has little effect on its amplitude but shifts the transition scale. We repeat the analysis with the hydrodynamical simulation TNG300, confirming the robustness of our results. Our results provide insight into assembly bias and have potential implications for modeling the galaxy-halo connection.

astro-ph.CO↗
arXiv2026

Diagnosing and Mitigating Context Rot in Long-horizon Search

Extensive context has become the norm as Large Language Models (LLMs) are increasingly deployed in long-horizon search tasks. The concern that increasing context length degrades model capabilities, known as context rot, has become a widely recognized issue for these applications. However, in deep search scenarios, it remains unclear how models actually fail under extensive context, and to what extent existing methods can mitigate such failures. Through a systematic study of four flagship models across three benchmarks, we identify a previously overlooked phenomenon, which we term premature termination: under extensive context, models give up or provide uncertain incorrect answers long before exhausting the context window. By controlling for query difficulty, we show that the premature termination rate is positively correlated with context length. Based on the findings, we revisit methods to mitigate context rot, including context management and parallel sampling. For context management, we analyze seven methods across three categories and show that they are inherently test-time scaling strategies that reduce the premature termination rate to enable more exploration, and we further provide model-dependent principles for method selection. For parallel sampling, we develop a behavior-aware filtering strategy and observe a performance gain of 2.6% to 4.9% across three aggregation methods.

cs.IR↗
arXiv2026

DataOrchestra: Learning to Orchestrate Per-Example Curation of Pretraining Data

Pretraining data processing is critical to the downstream performance of Large Language Models (LLMs). However, many existing approaches define a fixed processing strategy at the corpus or domain level and apply it uniformly to many examples, without adapting to the needs of each example. We propose DataOrchestra, a framework that unifies different processing operations and orchestrates an example-specific pipeline for each example. Given a chunk of pretraining data, an orchestrator decides whether to drop, untouch, or clean it. For a chunk to be cleaned, it selects one or more downstream operations, ranging from programmatic editing to different forms of LLM-based rewriting. For each rewriting step, it further generates a concrete instruction, which is executed by the corresponding downstream tool model. We pretrain models from 0.5B to 7B from scratch on web data processed by DataOrchestra and observe stable average gains over individual data-processing methods across 11 benchmarks. DataOrchestra is also effective for math continued pretraining and outperforms stronger processing baselines, while reducing processing compute by skipping unnecessary downstream operations.

cs.CL↗
arXiv2026

A General Deep Learning Framework for Wireless Resource Allocation under Discrete Constraints

While deep learning (DL)-based methods have achieved remarkable success in continuous wireless resource allocation, efficient solutions for problems involving discrete variables remain challenging. This is primarily due to the zero-gradient issue in backpropagation, the difficulty of enforcing intricate constraints with discrete variables, and the inability in generating solutions with non-same-parameter-same-decision (non-SPSD) property. To address these challenges, this paper proposes a general DL framework by introducing the support set to represent the discrete variables. We model the elements of the support set as random variables and learn their joint probability distribution. By factorizing the joint probability as the product of conditional probabilities, each conditional probability is sequentially learned. This probabilistic modeling directly tackles all the aforementioned challenges of DL for handling discrete variables. By operating on probability distributions instead of hard binary decisions, the framework naturally avoids the zero-gradient issue. During the learning of the conditional probabilities, discrete constraints can be seamlessly enforced by masking out infeasible solutions. Moreover, with a dynamic context embedding that captures the evolving discrete solutions, the non-SPSD property is inherently provided by the proposed framework. We apply the proposed framework to two representative mixed-discrete wireless resource allocation problems: (a) joint user association and beamforming in cell-free systems, and (b) joint antenna positioning and beamforming in movable antenna-aided systems. Simulation results demonstrate that the proposed DL framework consistently outperforms existing baselines in terms of both system performance and computational efficiency.

cs.LG↗
arXiv2026

ETAS: An Effect-Typed Language for Agent Systems

ETAS is a programming language for agent systems that treats model-backed agents, tool calls, prompts, typed memory, human approvals, policies, and execution traces as semantic program elements rather than library conventions. It separates deterministic computation from agentic nondeterminism and externally visible actions while preserving a direct programming style. We present the core design of ETAS. Its static semantics assigns ordinary types through spec conformance and tracks each computation with two behavioral indices: an escaping effect row and a persistent abstraction of the typed action trace it may request. Specs form a terminating compile-time constraint calculus: type specs provide evidence for polymorphism and resource facts, callable specs constrain function and stage shapes, and trace specs express allow, deny, and temporal constraints. Typing checks requested traces against compiled monitors and emits residual obligations when dynamic resources preclude a complete static proof. The dynamic semantics distinguish requested, handled, denied, and committed events; handlers interpret typed actions without making their requests invisible to authorization or audit. We formalize a core calculus and state preservation, progress, type/effect soundness, handler trace-transparency, and policy safety. We also implement ETAS in Rust with a command-line interface, typed HIR checks, effect and policy diagnostics, handler checks, and trace-aware execution hooks. ETAS provides a programming-language foundation for reasoning about authorization, nondeterminism, recovery, and audit evidence before and during agent execution.

cs.PL↗
arXiv2026

HPIM: Heterogeneous Processing-In-Memory-based Accelerator for Large Language Models Inference

The deployment of large language models (LLMs) presents significant challenges due to their enormous memory footprints, low arithmetic intensity, and stringent latency requirements, particularly during the autoregressive decoding stage. Traditional compute-centric accelerators, such as GPUs, suffer from severe resource underutilization and memory bandwidth bottlenecks in these memory-bound workloads. To overcome these fundamental limitations, we propose HPIM, the first memory-centric heterogeneous Processing-In-Memory (PIM) accelerator that integrates SRAM-PIM and HBM-PIM subsystems designed specifically for LLM inference. HPIM employs a software-hardware co-design approach that combines a specialized compiler framework with a heterogeneous hardware architecture. It intelligently partitions workloads based on their characteristics: latency-critical attention operations are mapped to the SRAM-PIM subsystem to exploit its ultra-low latency and high computational flexibility, while weight-intensive GEMV computations are assigned to the HBM-PIM subsystem to leverage its high internal bandwidth and large storage capacity. Furthermore, HPIM introduces a tightly coupled pipeline strategy across SRAM-PIM and HBM-PIM subsystems to maximize intra-token parallelism, thereby significantly mitigating the serial dependency of the autoregressive decoding stage. Comprehensive evaluations using a cycle-accurate simulator demonstrate that HPIM significantly outperforms state-of-the-art accelerators, achieving a peak speedup of up to 23.1x compared to the NVIDIA A100 GPU. Moreover, HPIM exhibits superior performance over contemporary PIM-based accelerators, highlighting its potential as a highly practical and scalable solution for accelerating large-scale LLM inference.

cs.AR↗
arXiv2026

RiverONE: Generating Knowledge-Intensive VLM by Simulated Quantum Machines

Quantum computing provides a powerful paradigm for representing and transforming high-dimensional information through superposition, entanglement, and measurement-induced nonlinear features. While current quantum hardware is not yet practical for direct large-scale vision-language model (VLM) inference, simulated quantum computation can be used during model construction to generate structured parameters for compact classical AI systems. We build RiverONE, a lightweight vision-language model for quantum calibration plot understanding, using simulated quantum computation. It employs a specialized visual encoder and an InternVL-based language backbone. To compensate for compression-induced information loss, we introduce quantum-generated parameters, which are materialized as classical tensors after training. This allows RiverONE to run entirely on classical GPUs at inference time, with no quantum hardware or runtime quantum simulation. With approximately 1.9 billion parameters, RiverONE achieves at least 95\% of the performance of NVIDIA Ising Calibration 1 on quantum calibration plot understanding tasks while using less than 10\% of its parameter count. These results suggest that simulated quantum computation can serve as a practical construction-stage mechanism for building lightweight, knowledge-intensive scientific VLMs. Our code is available at https://github.com/THeWakeSystems/RiverOne.

quant-ph↗
arXiv2026

SW-$A^2$-Bench: Benchmarking Autonomous Software Agent Generation for Agentic Web

The Agentic Web is emerging as a paradigm in which autonomous software agents interact with online resources and with each other to accomplish user goals. However, the capacity of Agentic Web is still limited by insufficient autonomous software agent population, which has become a crucial challenge for scaling Agentic Web. In order to alleviate this, we study the task of automatically converting existing code repositories into autonomous software agents via coding agents, decompose the process into critical stages, and identify key technical hurdles. To systematically evaluate this capability, we propose SoftWare Agent generation for Agentic Web Bench (SW-$A^2$-Bench), the first benchmark designed for software agent generation. SW-$A^2$-Bench evaluates not only whether software agents can be generated, but also whether generated software agents are faithful to the source repositories and interoperable with other agents in multi-agent workflows. Our experiments demonstrate that our approach effectively activates the functional capabilities of code repositories and enables interoperable multi-agent collaboration in Agentic Web. We believe that this work will provide a standardized evaluation for software agent generation and will contribute to the future of scaling the capacity of Agentic Web.

cs.MA↗
arXiv2026

DPNet: Doppler LiDAR Motion Planning for Highly-Dynamic Environments

Existing motion planning methods often struggle with rapid-motion obstacles due to an insufficient understanding of environmental changes. To address this, we propose integrating motion planners with Doppler LiDARs, which provide not only ranging measurements but also instantaneous point velocities. However, this integration is nontrivial due to the requirements of high accuracy and high frequency. To this end, we introduce Doppler Planning Network (DPNet), which tracks and reacts to rapid obstacles via Doppler model-based learning. We first propose a Doppler Kalman neural network (D-KalmanNet) to track obstacle states under a partially observable Gaussian state space model. We then leverage the predicted motions of obstacles to construct a Doppler-tuned model predictive control (DT-MPC) framework for ego-motion planning, enabling runtime auto-tuning of controller parameters. These two modules allow DPNet to learn fast environmental changes from minimal data while remaining lightweight, achieving high frequency and high accuracy in both tracking and planning. Experiments on high-fidelity simulator and real-world datasets demonstrate the superiority of DPNet over extensive benchmark schemes. Code available at https://github.com/UUwei-zuo/DPNet

cs.RO↗
arXiv2026

Secondary Dependence of Baryonic Effects on the Density Profile of Dark Matter Halos

Baryonic physics is anticipated to be a major source of systematic uncertainty in current and future large-scale cosmological surveys. We investigate how baryonic effects on halo density profiles vary with secondary halo properties at fixed halo mass, using the large-volume MillenniumTNG hydrodynamical simulation and its dark matter-only counterpart. We focus on the impact of halo concentration and large-scale environment on the ratio of density profiles of matched halos in the hydrodynamical and dark matter-only simulations. At redshift $z = 0.0$, we find a strong dependence on halo concentration, especially at lower halo mass ($12.5 < \log(M_h/h^{-1}M_{\odot}) < 13.0$), where more concentrated halos exhibit weaker inner enhancement and stronger intermediate-radius suppression at fixed halo mass, with variations reaching $\sim 15\%$ at small scales and decreasing toward larger scales. This trend weakens and reverses at higher halo mass. In contrast, the secondary dependence on large-scale environment is weaker ($\sim 2\%$) and largely scale-independent, with halos in denser regions exhibiting slightly weaker intermediate suppression. By separating internal profile redistribution from total mass suppression, we show that concentration impacts both components, whereas the environmental dependence is primarily associated with an overall mass shift. These secondary dependencies persist at $ z = 0.5$ and correlate with variations in internal baryonic properties. We examine additional halo properties, including halo spin and velocity dispersion, and find significant secondary dependence. Overall, our results highlight the important role of secondary halo properties in modulating baryonic effects on halo density profiles, with potential implications for future modeling efforts.

astro-ph.CO↗
arXiv2026

Gradient-Produced Neutrinos

Sufficiently strong electric fields can produce charged-particle pairs via the Schwinger effect. We argue that steep matter-density gradients, as can arise in neutron star interiors, would analogously produce neutrino-antineutrino pairs. We then discuss observational signatures of these gradient-produced (anti)neutrinos and how they could provide new probes of neutron-star structure and baryon-dense QCD.

hep-ph↗
arXiv2026

Efficient Transceiver Design for Aerial Image Transmission and Large-scale Scene Reconstruction

Large-scale three-dimensional (3D) scene reconstruction in low-altitude intelligent networks (LAIN) demands highly efficient wireless image transmission. However, existing schemes struggle to balance severe pilot overhead with the transmission accuracy required to maintain reconstruction fidelity. To strike a balance between efficiency and reliability, this paper proposes a novel deep learning-based end-to-end (E2E) transceiver design that integrates 3D Gaussian Splatting (3DGS) directly into the training process. By jointly optimizing the communication modules via the combined 3DGS rendering loss, our approach explicitly improves scene recovery quality. Furthermore, this task-driven framework enables the use of a sparse pilot scheme, significantly reducing transmission overhead while maintaining robust image recovery under low-altitude channel conditions. Extensive experiments on real-world aerial image datasets demonstrate that the proposed E2E design significantly outperforms existing baselines, delivering superior transmission performance and accurate 3D scene reconstructions.

cs.CV↗
arXiv2026

GeometryZero: Advancing Geometry Solving via Group Contrastive Policy Optimization

Recent progress in large language models (LLMs) has boosted mathematical reasoning, yet geometry remains challenging where auxiliary construction is often essential. Prior methods either underperform or depend on very large models (e.g., GPT-4o), making them costly. We argue that reinforcement learning with verifiable rewards (e.g., GRPO) can train smaller models to couple auxiliary construction with solid geometric reasoning. However, naively applying GRPO yields unconditional rewards, encouraging indiscriminate and sometimes harmful constructions. We propose Group Contrastive Policy Optimization (GCPO), an RL framework with two components: (1) Group Contrastive Masking, which assigns positive/negative construction rewards based on contextual utility, and (2) a Length Reward that encourages longer reasoning chains. On top of GCPO, we build GeometryZero, an affordable family of geometry reasoning models that selectively use auxiliary construction. Experiments on Geometry3K and MathVista show GeometryZero consistently outperforms RL baselines (e.g., GRPO, ToRL). The code has been available at https://github.com/ekonwang/GeometryZero.

cs.CL↗
arXiv2026

VideoThinker: Building Agentic VideoLLMs with LLM-Guided Tool Reasoning

Long-form video understanding remains a fundamental challenge for current Video Large Language Models. Most existing models rely on static reasoning over uniformly sampled frames, which weakens temporal localization and leads to substantial information loss in long videos. Agentic tools such as temporal retrieval, spatial zoom, and temporal zoom offer a natural way to overcome these limitations by enabling adaptive exploration of key moments. However, constructing agentic video understanding data requires models that already possess strong long-form video comprehension, creating a circular dependency. We address this challenge with VideoThinker, an agentic Video Large Language Model trained entirely on synthetic tool interaction trajectories. Our key idea is to convert videos into rich captions and employ a powerful agentic language model to generate multi-step tool use sequences in caption space. These trajectories are subsequently grounded back to video by replacing captions with the corresponding frames, yielding a large-scale interleaved video and tool reasoning dataset without requiring any long-form understanding from the underlying model. Training on this synthetic agentic dataset equips VideoThinker with dynamic reasoning capabilities, adaptive temporal exploration, and multi-step tool use. Remarkably, VideoThinker significantly outperforms both caption-only language model agents and strong video model baselines across long-video benchmarks, demonstrating the effectiveness of tool augmented synthetic data and adaptive retrieval and zoom reasoning for long-form video understanding.

cs.CV↗
arXiv2026

Learning to Jointly Optimize Antenna Positioning and Beamforming for Movable Antenna-Aided Systems

The recently emerged movable antenna (MA) and fluid antenna technologies offer promising solutions to enhance the spatial degrees of freedom in wireless systems by dynamically adjusting the positions of transmit or receive antennas within given regions. In this paper, we aim to address the joint optimization problem of antenna positioning and beamforming in MA-aided multi-user downlink transmission systems. This problem involves mixed discrete antenna position and continuous beamforming weight variables, along with coupled distance constraints on antenna positions, which pose significant challenges for optimization algorithm design. To overcome these challenges, we propose an end-to-end deep learning framework, consisting of a positioning model that handles the discrete variables and the coupled constraints, and a beamforming model that handles the continuous variables. Simulation results demonstrate that the proposed framework achieves superior sum rate performance, yet with much reduced computation time compared to existing methods.

eess.SP↗