arXiv subjects

Fan Jiang

Publications and source records attributed to Fan Jiang.

At least 19 recordsLinked to original sources

arXiv2026

ABot-World-0: Infinite Interactive World Rollout on a Single Desktop GPU

We present ABot-World-0, an action-conditioned video world model for real-time, long-horizon closed-loop interaction, supported by a multi-source data infrastructure spanning AAA games, simulation engines, and internet videos to learn controllable world dynamics. WorldExplorer performs agent-driven collection guided by training feedback, while a unified pipeline applies 14 deterministic quality checks, VLM-based assessment, and synchronized action and text annotation. We progressively distill a bidirectional action-conditioned teacher into a causal student through teacher forcing and ODE distillation, and introduce LongForcing to align long student self-rollouts with an extended-horizon teacher, mitigating accumulated distribution shift and autoregressive drift. Raw keyboard actions provide a unified control interface for scene roaming and third-person character interaction, while reference-character memory provides persistent appearance cues for identity consistency during third-person rollouts. For deployment, we co-design a streaming inference stack with a lightweight VAE decoder, efficient attention, memory-aware scheduling, and low-bit DiT inference. Across optimized low-bit configurations, ABot-World-0 streams 720P video at up to 16 FPS on a single NVIDIA RTX 5090 desktop GPU, with 1.2s action-to-first-frame latency and approximately 19GiB peak VRAM. Experiments on WorldRoamBench and extended interactive rollouts demonstrate competitive controllability and coherent long-horizon world evolution.

cs.CV↗

arXiv2026

WorldRoamBench: An Open-World Benchmark for Long-Horizon Stability of Interactive World Models

Despite rapid progress in interactive world models (IWMs), existing benchmarks evaluate action following only at trajectory level and ignore memory and interaction physics. We introduce WorldRoamBench, an open-world benchmark for long-horizon stability across four dimensions, each with tailored innovations: (i) Action: per-frame action metric bypassing cross-model semantic scale disparity and exposing failures hidden by trajectory; (ii) Vision: segment-based drift metric capturing non-monotonic mid-sequence collapse missed by start-vs-end comparisons; (iii) Physics: controllability-gated evaluation over mechanics, optics, and 3D consistency, scoring plausibility under faithful action execution; (iv) Memory: action-decoupled protocol evaluating scene memory via transition-localized 3D point-cloud reconstruction and subject memory via tracking-plus-VLM reasoning. The benchmark comprises 600+ test cases across Nature, Urban, and Indoor scenes in first/third-person views with WASD 10-60s continuous interaction. Evaluating 10+ open/closed-source models reveals none reliably satisfies all dimensions; even the best achieves only moderate scores. Advances on WorldRoamBench are steps toward IWMs that are stable, physically grounded, memory-faithful, and deployable in real-world applications.

cs.CV↗

arXiv2026

Mid-infrared-to-ultraviolet supercontinuum generation in low-loss tantalum pentoxide nanophotonic waveguides

Optical frequency combs on photonic integrated platforms are revolutionizing precision metrology, bio-imaging, atomic and molecular sensing, and ultrafast photonics, yet most remain confined to the near-infrared. This restriction prevents access to the ultraviolet, visible, and mid-infrared bands critical for a vast array of quantum, atomic, and molecular systems. The fundamental obstacle has been the lack of a nanophotonic waveguide that simultaneously provides an ultra-broad transparency window, engineered dispersion, ultra-low propagation loss, and a strong Kerr nonlinearity, all while suppressing detrimental two-photon absorption at short wavelengths. Here, we overcome this challenge by exploring tantalum pentoxide for ultra-broadband supercontinuum spanning continuously from the ultraviolet to the mid-infrared, leveraging its broad transparency window (300-8000 nm), a high nonlinear refractive index three times larger than that of silicon nitride, and a wide bandgap that suppresses two-photon absorption. Critically, by using a photolithography assisted chemo-mechanical etching process that avoids a lossy SiO2 upper cladding, we achieve dispersion engineered waveguides with record-low propagation losses of 0.066 dB/cm at telecom wavelengths and 0.43 dB/cm at 780 nm, significantly facilitating the supercontinuum spectral extension into the ultraviolet and the mid-infrared. Pumping these anomalous-dispersion waveguides with femtosecond pulses at 1550 nm yields a gap-free, 3.2-octave supercontinuum spanning from 350 to 3200 nm via a soliton-based dynamics at only 54 pJ pulse energy, representing the broadest comb spectrum on this platform. We further demonstrate a relatively flat spectrum with a -30 dB bandwidth of 1182 nm by engineering normal dispersion, validate the comb coherence via heterodyne detection, and achieve soliton-effect pulse self-compression from 126.7 fs to 19.2 fs.

physics.optics↗

arXiv2026

Marginal Advantage Accumulation for Memory-Driven Agent Self-Evolution

In batch-style trace distillation, the same memory operation may receive contradictory feedback across different batches. Existing methods lack a cross-batch, operation-level evidence accumulation mechanism, making it impossible to distinguish stably effective operations from accidental hits. This paper formalizes the requirement as two structural conditions, alignability and comparability, and proposes Marginal Advantage Accumulation (MAA). MAA constructs differential signals to make them comparable across batches, accumulates signed evidence per operation via EMA, and ensures cross-batch traceability through semantic identity merging. As a post-processing architecture, MAA achieves the best results in 14 out of 16 settings across 4 benchmarks and 4 target models, consistently outperforming existing batch-level distillation baselines and matching or surpassing online alternatives in most settings, while reducing optimization-phase token consumption by approximately 75%.

cs.LG↗

arXiv2026

Learning-Assisted Day-Ahead Energy Scheduling for Frequency-Secure Inverter-Dominated Grids with Grid-Forming Battery Energy Storage Systems

As grid-forming (GFM) battery energy storage systems (BESS) are increasingly deployed to enhance power system inertial response and frequency stability, incorporating their frequency support capabilities into day-ahead energy scheduling (DAES) is essential for achieving both frequency security and operational efficiency. However, accurately determining frequency metrics in grids with coexisting GFM inverters and synchronous generators requires electromagnetic transient (EMT) simulations, which are computationally prohibitive for direct embedding in grid operational optimization models. To bridge the gap between modeling accuracy and computational efficiency, a learning-assisted DAES (LA-DAES) framework is proposed in this work. By leveraging a surrogate model to represent the frequency support dynamics of GFM BESS, the proposed framework ensures frequency security with a reasonable solve time. Comparative results demonstrate that, relative to analytical frequency-constrained DAES, the proposed LA-DAES framework more accurately captures grid frequency metrics and improves the utilization of GFM BESS.

eess.SY↗

arXiv2026

Who Is in Mind Matters: Attachment Representations in Early Childhood Synchronize Child-Adult Interacting Brains

Human attachment is distinguished by enduring internalized representations that shapes neurodevelopment and social-emotional functioning. However, as unobservable inner processes mixed with social cues and partner-specific factors, the neurocognitive mechanisms of these representations during real-time interaction remain unclear. Using a novel Remote Partner-Belief Manipulation paradigm in 40 child-mother-stranger trios, we experimentally isolated attachment representations in 3-4-year-olds by manipulating children's partner-belief during remote cooperation. The inner processes were captured from synchrony between partners' EEG, showing that children's mother-partner belief, regardless of the actual partner, significantly enhanced interbrain synchrony. This partner-belief modulation concentrated on children's P4 channel (overlaying the attachment-designated right temporoparietal junction), where synchrony strength correlated to attachment security and children's response acceleration due to mother-partner belief. These findings established attachment representations as an independent, endogenous driver of interbrain synchrony, potentially via children's heightened attention towards their attachment figure, implying the role of symbolic attachment activation when separation.

q-bio.NC↗

arXiv2026

LISA: Linear-Indexed Sparse Attention for Efficient Long-Context Reasoning

Recent advances in long chain-of-thought reasoning models such as DeepSeek-R1 have led to increasingly longer inference context lengths under the test-time scaling paradigm. However, the O(n^2) computational complexity of standard self-attention causes inference costs to grow sharply with long sequences, limiting the deployment of long-CoT reasoning in production settings. To address this, we propose LISA (Linear-Indexed Sparse Attention), a plug-and-play attention replacement module that requires no pretraining from scratch. LISA integrates two lightweight components in parallel within the original model: (1) a Linear Attention module that provides long-range memory with O(n) time complexity; (2) a Lightning Indexer that selects the top-M important tokens from the full context to feed into a Sparse Self-Attention. The two branches are fused via a gating mechanism, reducing inference complexity from O(n^2) to O(nM) (M << n) for generating n tokens. We design a two-stage training pipeline: Stage 1 initializes the model by integrating the linear attention to capture long-range dependencies, complemented by a sliding-window attention mechanism that is optimized via knowledge distillation to approximate the full self-attention distribution of a frozen teacher model. In Stage 2, we further introduce the Indexer to replace the static sliding-window mechanism, enabling dynamic token selection from broader contexts. The Indexer is trained using a novel per-head KL divergence loss, which aligns its selection behavior with the attention patterns of the teacher model. Experiments on DeepSeek-distilled-Qwen models demonstrate that LISA achieves a 50% inference speedup under 16K-token context, while improving average performance by 5.6% on reasoning benchmarks including AIME and MATH-500.

cs.AI↗

arXiv2026

SiriusHelper: An LLM Agent-Based Operations Assistant for Big Data Platforms

Big data platforms are widely used in modern enterprises, and an in-production intelligent assistant is increasingly important to help users quickly find actionable guidance and reduce operational burden. While recent LLM+RAG assistants provide a natural interface, they face practical challenges in real deployments: limited scenario coverage across both general consultation and domain-specific troubleshooting workflows, inefficient knowledge access due to inadequate multi-hop retrieval and flat knowledge organization, and high maintenance cost because escalated tickets are unstructured and hard to convert into assistant improvements and reusable SOPs. In this paper, we present SiriusHelper, a deployed intelligent assistant for big data platforms. SiriusHelper serves as a unified online assistant that automatically identifies user intent and routes queries to the right handling path, including dedicated expert workflows for specialized scenarios (e.g., SQL execution diagnosis). To support complex troubleshooting, SiriusHelper combines a DeepSearch-driven mechanism with a priority-based hierarchical knowledge base to enable multi-hop retrieval without context overload, thus improving answer reliability and latency. To reduce expert overhead, SiriusHelper further introduces automated ticket understanding and SOP distillation: it diagnoses the assistant failure reason (e.g., missing knowledge or wrong routing) and extracts domain-specific SOPs to continuously enrich the knowledge base. Experiments and online deployment on Tencent Big Data platform show that SiriusHelper outperforms representative alternatives and reduces online ticket volume by 20.8\%.

cs.DB↗

arXiv2026

Marco-MoE: Open Multilingual Mixture-of-Expert Language Models with Efficient Upcycling

We present Marco-MoE, a suite of fully open multilingual sparse Mixture-of-Experts (MoE) models. Marco-MoE features a highly sparse design in which only around 5\% of the total parameters are activated per input token. This extreme sparsity, combined with upcycling from dense models, enables efficient pre-training on 5T tokens. Our models surpass similarly-sized competitors on English and multilingual benchmarks, achieving a best-in-class performance-to-compute ratio. We further post-train these models to create Marco-MoE-\textsc{Instruct} variants, which surpass the performance of competing models possessing $3$--$14\times$ more activated parameters. Our analysis reveals that Marco-MoE learns structured expert activation patterns shared across related languages, while maintaining highly specialized utilization for linguistically isolated ones. We further show that Marco-MoE allows for scalable language expansion without the interference typical of dense models. To support the community, we disclose our full training datasets, recipes, and model weights.

cs.CL↗

arXiv2026

CulturALL: Benchmarking Multilingual and Multicultural Competence of LLMs on Grounded Tasks

Large language models (LLMs) are now deployed worldwide, inspiring a surge of benchmarks that measure their multilingual and multicultural abilities. However, these benchmarks prioritize generic language understanding or superficial cultural trivia, leaving the evaluation of grounded tasks -- where models must reason within real-world, context-rich scenarios -- largely unaddressed. To fill this gap, we present CulturALL, a comprehensive and challenging benchmark to assess LLMs' multilingual and multicultural competence on grounded tasks. CulturALL is built via a human--AI collaborative framework: expert annotators ensure appropriate difficulty and factual accuracy, while LLMs lighten the manual workload. By incorporating diverse sources, CulturALL ensures comprehensive scenario coverage. Each item is carefully designed to present a high level of difficulty, making CulturALL challenging. CulturALL contains 2,610 samples in 14 languages from 51 regions, distributed across 16 topics to capture the full breadth of grounded tasks. Experiments show that the best LLM achieves 44.48% accuracy on CulturALL, underscoring substantial room for improvement.

cs.CL↗

arXiv2026

HISA: Efficient Hierarchical Indexing for Fine-Grained Sparse Attention

Token-level sparse attention mechanisms, exemplified by DeepSeek Sparse Attention (DSA), achieve fine-grained key selection by scoring every historical key for each query through a lightweight indexer, then computing attention only on the selected subset. While the downstream sparse attention itself scales favorably, the indexer must still scan the entire prefix for every query, introducing an per-layer bottleneck that grows prohibitively with context length. We propose HISA (Hierarchical Indexed Sparse Attention), a plug-and-play replacement for the indexer that rewrites the search path from a flat token scan into a two-stage hierarchical procedure: (1) a block-level coarse filtering stage that scores pooled block representations to discard irrelevant regions, followed by (2) a token-level refinement stage that applies the original indexer exclusively within the retained candidate blocks. HISA preserves the identical token-level top-sparse pattern consumed by the downstream Sparse MLA operator and requires no additional training. On kernel-level benchmarks, HISA achieves up to speedup at 64K context. On Needle-in-a-Haystack and LongBench, we directly replace the indexer in DeepSeek-V3.2 and GLM-5 with our HISA indexer, without any finetuning. HISA closely matches the original DSA in quality, while substantially outperforming block-sparse baselines.

cs.LG↗

arXiv2026

Integrated Channel Sounding and Communication: Requirements, Architecture, Challenges, and Key Technologies

Channel models are essential for the design, evaluation, and optimization of wireless communication systems. The emerging space-air-ground-sea integrated network (SAGSIN), characterized by diverse service applications and extended-spectrum operations, places even greater demands on highly accurate channel models. However, conventional channel sounding is limited by generalized measurement campaigns, inadequate cross-band consistency, and insufficient real-time adaptability, making it unable to meet the needs of SAGSIN for scenario-specific and high-precision channel modeling. To address this challenge, we propose a novel technological framework, termed integrated channel sounding and communication (ICSC). By deeply integrating sounding and communication, the ICSC enables efficient and real-time acquisition of dynamic channel characteristics during communication processes, supporting fine-grained site- and scenario-specific measurements. Furthermore, leveraging artificial intelligence techniques, ICSC can identify channel conditions and adapt waveform parameters in real-time according to scenario variations, which in turn enhances communication performance. This article first introduces the fundamental principles of the ICSC framework, elaborates on its core concepts and key advantages, and demonstrates its feasibility through the development of an integrated verification system (IVS). Subsequently, the potential applications and opportunities of the ICSC are analyzed in depth, followed by a discussion of its future development directions and remaining challenges.

eess.SP↗

arXiv2026

On the Optimal Integer-Forcing Precoding: A Geometric Perspective and a Polynomial-Time Algorithm

The joint optimization of the integer matrix $\mathbf{A}$ and the power scaling matrix $\mathbf{D}$ is central to achieving the capacity-approaching performance of Integer-Forcing (IF) precoding. This problem, however, is known to be NP-hard, presenting a fundamental computational bottleneck. In this paper, we reveal that the solution space of this problem admits a intrinsic geometric structure: it can be partitioned into a finite number of conical regions, each associated with a distinct full-rank integer matrix $\mathbf{A}$. Leveraging this decomposition, we transform the NP-hard problem into a search over these regions and propose the Multi-Cone Nested Stochastic Pattern Search (MCN-SPS) algorithm. Our main theoretical result is that MCN-SPS finds a near-optimal solution with a computational complexity of $\mathcal{O}\left(K^4\log K\log_2(r_0)\right)$, which is polynomial in the number of users $K$. Numerical simulations corroborate the theoretical analysis and demonstrate the algorithm's efficacy.

cs.IT↗

arXiv2026

ABot-N0: Technical Report on the VLA Foundation Model for Versatile Embodied Navigation

Embodied navigation has long been fragmented by task-specific architectures. We introduce ABot-N0, a unified Vision-Language-Action (VLA) foundation model that achieves a ``Grand Unification'' across 5 core tasks: Point-Goal, Object-Goal, Instruction-Following, POI-Goal, and Person-Following. ABot-N0 utilizes a hierarchical ``Brain-Action'' architecture, pairing an LLM-based Cognitive Brain for semantic reasoning with a Flow Matching-based Action Expert for precise, continuous trajectory generation. To support large-scale learning, we developed the ABot-N0 Data Engine, curating 16.9M expert trajectories and 5.0M reasoning samples across 7,802 high-fidelity 3D scenes (10.7 $\text{km}^2$). ABot-N0 achieves new SOTA performance across 7 benchmarks, significantly outperforming specialized models. Furthermore, our Agentic Navigation System integrates a planner with hierarchical topological memory, enabling robust, long-horizon missions in dynamic real-world environments.

cs.RO↗

arXiv2026

Deep Neural Network-Enhanced Frequency-Constrained Optimal Power Flow with Multi-Governor Dynamics

To ensure frequency security in power systems, both the rate of change of frequency (RoCoF) and the frequency nadir (FN) must be explicitly accounted for in real-time frequency-constrained optimal power flow (FCOPF). However, accurately modeling sys-tem frequency dynamics through analytical formulations is chal-lenging due to their inherent nonlinearity and complexity. To address this issue, deep neural networks (DNNs) are utilized to capture the nonlinear mapping between system operating condi-tions and key frequency performance metrics. In this paper, a DNN-based frequency prediction model is developed and trained using the high-fidelity time-domain simulation data generated in PSCAD/EMTDC. The trained DNN is subsequently transformed into an equivalent mixed-integer linear programming (MILP) form and embedded into the FCOPF problem as additional con-straints to explicitly enforce frequency security, leading to the proposed DNN-FCOPF formulation. For benchmarking, two alternative models are considered: a conventional optimal power flow without frequency constraints and a linearized FCOPF in-corporating system-level RoCoF and FN constraints. The effec-tiveness of the proposed method is demonstrated by comparing the solutions of these three models through extensive PSCAD/EMTDC time-domain simulations under various loading scenarios.

eess.SY↗

arXiv2026

Difficulty-Estimated Policy Optimization

Recent advancements in Large Reasoning Models (LRMs), exemplified by DeepSeek-R1, have underscored the potential of scaling inference-time compute through Group Relative Policy Optimization (GRPO). However, GRPO frequently suffers from gradient signal attenuation when encountering problems that are either too trivial or overly complex. In these scenarios, the disappearance of inter-group advantages makes the gradient signal susceptible to noise, thereby jeopardizing convergence stability. While variants like DAPO attempt to rectify gradient vanishing, they do not alleviate the substantial computational overhead incurred by exhaustive rollouts on low-utility samples. In this paper, we propose Difficulty-Estimated Policy Optimization (DEPO), a novel framework designed to optimize the efficiency and robustness of reasoning alignment. DEPO integrates an online Difficulty Estimator that dynamically assesses and filters training data before the rollout phase. This mechanism ensures that computational resources are prioritized for samples with high learning potential. Empirical results demonstrate that DEPO achieves up to a 2x reduction in rollout costs without compromising model performance. Our approach significantly lowers the computational barrier for training high-performance reasoning models, offering a more sustainable path for reasoning scaling. Code and data will be released upon acceptance.

cs.AI↗

arXiv2026

FantasyVLN: Unified Multimodal Chain-of-Thought Reasoning for Vision-Language Navigation

Achieving human-level performance in Vision-and-Language Navigation (VLN) requires an embodied agent to jointly understand multimodal instructions and visual-spatial context while reasoning over long action sequences. Recent works, such as NavCoT and NavGPT-2, demonstrate the potential of Chain-of-Thought (CoT) reasoning for improving interpretability and long-horizon planning. Moreover, multimodal extensions like OctoNav-R1 and CoT-VLA further validate CoT as a promising pathway toward human-like navigation reasoning. However, existing approaches face critical drawbacks: purely textual CoTs lack spatial grounding and easily overfit to sparse annotated reasoning steps, while multimodal CoTs incur severe token inflation by generating imagined visual observations, making real-time navigation impractical. In this work, we propose FantasyVLN, a unified implicit reasoning framework that preserves the benefits of CoT reasoning without explicit token overhead. Specifically, imagined visual tokens are encoded into a compact latent space using a pretrained Visual AutoRegressor (VAR) during CoT reasoning training, and the model jointly learns from textual, visual, and multimodal CoT modes under a unified multi-CoT strategy. At inference, our model performs direct instruction-to-action mapping while still enjoying reasoning-aware representations. Extensive experiments on LH-VLN show that our approach achieves reasoning-aware yet real-time navigation, improving success rates and efficiency while reducing inference latency by an order of magnitude compared to explicit CoT methods.

cs.CV↗

arXiv2025

Frequency-Dynamics-Aware Economic Dispatch with Optimal Grid-Forming Inverter Allocation and Reserved Power Headroom

The high penetration of inverter-based resources (IBRs) reduces system inertia, leading to frequency stability concerns, especially during synchronous generator (SG) outages. To maintain frequency dynamics within secure limits while ensuring economic efficiency, frequency-constrained optimal power flow (FCOPF) is employed. However, existing studies either neglect the frequency support capability and allocation of grid-forming (GFM) IBRs or suffer from limited accuracy in representing frequency dynamics due to model simplifications. To address this issue, this paper proposes a deep learning (DL)-based FCOPF (DL-FCOPF) framework. A DL model is first developed as a predictor to accurately estimate frequency-related metrics: the required reserved headroom and allocation of GFM IBRs, the rate of change of frequency and frequency nadir. After being trained with data obtained from electromagnetic transient simulations, the DL model is reformulated and incorporated into FCOPF. Case studies conducted on two test systems demonstrate the effectiveness of the proposed approach. Compared with the traditional OPF and linear FCOPF benchmarks, the DL-FCOPF can optimally coordinate SGs and IBRs with minimum cost, achieving desired frequency response, within an acceptable computing time. Further-more, sensitivity analyses are conducted to identify the most suit-able structure and linearization approach of the DL-based frequency predictor.

eess.SY↗