arXiv subjects

Bin Han

Publications and source records attributed to Bin Han.

At least 19 recordsLinked to original sources

arXiv2026

NSFlow: End-to-End Differentiable Neuro-Symbolic Optical Flow for Visual Odometry

Sparse optical flow provides stable inter-frame correspondence, playing a key role in Visual Odometry (VO) and Visual-Inertial Odometry (VIO). Classical optimization-based methods, such as Lucas-Kanade (LK), perform well under small displacements but are sensitive to large motions and illumination changes. Modern regression-based learning methods, while more robust in complex scenes, are often computationally heavy and lack explicit geometric consistency, making them less suitable for efficient VO/VIO front-ends. To bridge this gap, we propose a hybrid neuro-symbolic framework that combines the strengths of both paradigms. Our method uses a Convolutional Neural Network (CNN) to extract robust feature representations, which is fed into a differentiable LK optimizer to estimate optical flow in an end-to-end trainable manner. Through implicit differentiation, gradients are propagated across the iterative solver, enabling joint optimization of feature extraction and flow estimation. The resulting system integrates seamlessly into existing VO/VIO pipelines and runs in real-time on embedded platforms. Experiments show that our method outperforms conventional optimization-based flow in challenging conditions such as dynamic lighting and low texture, while also achieving higher accuracy and lower latency than purely regression-based alternatives. When deployed in a VIO system, our method demonstrates significant performance improvement, achieving an average error reduction of 42\% on challenging datasets while enhancing tracking stability. The code is publicly available.

cs.CV↗

arXiv2026

Symbol-Domain Chase Combining on Fourier-Curve Constellations: Exact Penalties of Per-Round Bit Reduction

A Fourier-curve constellation places $M$ symbols on a closed curve in $\R^{2k}$ and injects artificial noise along the tangent at the transmitted symbol, so every symbol candidate carries its own rank-one noise covariance; a Chase retransmission repeats one such $M$-ary symbol. How should the covariance-aware receiver combine the repeated observations? It can accumulate the $M$ candidate metrics and form bit log-likelihood ratios (LLRs) once, or it can form bit LLRs in every round and add them. The rounds are independent given the symbol but not given a single label bit, so even exact per-round bit LLRs do not add up to the joint-round LLR. We derive exact identities for the gap under log-sum-exp and max-log reduction, with their equality conditions; they hold for any repeated $M$-ary symbol, grow with the number of rounds, and vanish for binary signaling. On the Fourier channel with a rate-$1/2$ LDPC code after $L=4$ rounds, per-round max-log reduction needs $1.95$ dB more per-slot SNR at block error rate $10^{-1}$ than even covariance-ignorant Euclidean accumulation. Optimized bit-metric generalized mutual information puts the SNR penalty of per-round exact reduction at the code-rate threshold at $2.7$ dB on the Fourier channel and $1.5$ dB on Gray 64-QAM, joint max-log costs less than $0.1$ dB, and a 5G NR LDPC code on Gray 64-QAM loses $1.6$ dB at $L=4$. Controls with Gray labeling, isotropic noise, and $\beta=0$ show that the loss does not depend on the symbol-dependent covariance, whose own effect is the separate matched-versus-Euclidean correction. The Fourier receiver should therefore accumulate matched candidate metrics across rounds and reduce to bits once.

eess.SP↗

arXiv2026

Orchra: Stateful-aware Cross-slice Workload Migrations in the 6G Control Plane

Network slicing is a foundational capability of Fifth Generation (5G)-Advanced and emerging Sixth Generation (6G) networks, yet practical support for seamless runtime slice transitions remains limited. Standard cloud-native 5G architectures lack native support for stateful inter/intra-slice session migration, relying instead on high-overhead Non-Access Stratum (NAS) re-registrations, container redeployment etc., which disrupt userplane traffic for up to 245.50 ms. To address this limitation, we present Orchra, an intelligent orchestrator for stateful, low-latency context transfer. By externalizing critical user equipment state-including NAS context, security keys, and Protocol Data Unit (PDU) session information-into a transient staging layer, Orchra preserves session continuity across slice boundaries without requiring full re-registration. Experimental evaluation shows that Orchra reduces this userplane interruption by more than twice in comparison to conventional Third Generation Partnership Project (3GPP)-based approaches while incurring negligible security overhead. These results demonstrate a practical and reproducible approach for enabling seamless, state-preserving slice transitions in cloud-native 5G-Advanced networks.

cs.NI↗

arXiv2026

TraversRL: Traversable Pedestrian Pathway Generation With Reinforcement Learning

Automatically generating pedestrian pathways from aerial images requires producing a connected network suitable for routing, not just detecting where sidewalks appear. Sidewalks and crossings, in contrast to roads, may be partially occluded, implicitly defined, and exhibit complex connectivity patterns. Existing segmentation-based approaches focus on labeling pixels to infer segments, but often produce disconnected or fragmentary graphs that are unreliable for navigation. We introduce TraversRL, a vision-conditioned model that iteratively grows a pathway network from an aerial image, simulating a traveler navigating the built environment. TraversRL uses an action space of short and long direction-distance segments designed to adapt to complex patterns and span occlusions, and uses a combination of graph-level and step-wise rewards to balance overall connectivity with precise edge placement. Across three visual backbones and three intersection datasets, TraversRL substantially improves buffered IoU with the ground-truth graph relative to a state-of-the-art segmentation baseline, and more than doubles metrics of connectivity. Moreover, combining global and local rewards produces cleaner graphs with fewer spurious branches while further improving overall performance. These results demonstrate that modeling pathway extraction as a sequential decision process from the perspective of a traveler, while optimizing for final graph quality with reinforcement learning, produces significantly more reliable pedestrian networks.

cs.CV↗

arXiv2026

GDPR-Aware Trajectory Sharing for ISAC-Assisted Robot Navigation: A Case Study on FID-Constrained Collision Prediction

Integrated sensing and communication (ISAC) enables intelligent wireless infrastructure but raises growing regulatory concern as fine-grained personal trajectory histories become a byproduct of sensing. General Data Protection Regulation (GDPR) Articles 5(1)(c) and 5(1)(f) require that personal data be limited to what is necessary and protected through appropriate technical measures against unauthorised reconstruction. This paper addresses both requirements through a Fisher information density (FID)-constrained trajectory sharing scheme for robot collision avoidance, where sensing estimates are perturbed according to local information content before sharing. Experiments on real pedestrian traces show that FID-controlled sharing achieves a strictly better privacy-utility tradeoff than fixed-error perturbation: at matched missed-conflict rates, reconstruction leakage and sustained exposure lengths are consistently lower, establishing information-aware perturbation as a principled technical measure aligned with GDPR data minimisation and integrity requirements.

cs.RO↗

arXiv2026

Global nonlinear stability of the 2D incompressible viscous non-resistive MHD under sheared magnetic field

We study the two-dimensional incompressible viscous non-resistive magnetohydrodynamics in the periodic strip $\mathbb T\times\mathbb R$, subject to a smooth sheared background magnetic field $(\xi(x_2),0)^{\top}$, where $\xi(x_2)$ is bounded and away from zero. For sufficiently smooth perturbations satisfying even-odd symmetry, we prove global-in-time well-posedness and nonlinear stability in Lagrangian coordinates. The spatial inhomogeneity of the shear profile generates persistent linear contributions, most critically a nontrivial pressure term that precludes the uniform-in-time estimates. We straighten the integral curves of the initial magnetic field and construct a volume-preserving corrector. This geometric reduction transforms the intractable linear pressure into a quadratic nonlinearity. These structures yield the global energy bounds and the anisotropic algebraic decay rate for the system. This mechanism appears to provide the first rigorous framework for establishing global nonlinear stability for viscous non-resistive magnetohydrodynamics near the genuinely nonuniform sheared magnetic profile.

math.AP↗

arXiv2026

MedBench v5: A Dynamic, Process-Oriented, and Hallucination-Aware Benchmark for Clinical Multimodal Models

Existing medical AI benchmarks lack process visibility, atomic skill evaluation, and integrated hallucination detection. We introduce MedBench v5, a redesigned benchmark for clinical multimodal models (language, vision-language, and agent systems) that moves from static QA to dynamic, process-oriented evaluation. MedBench v5 features: (1) a dual-dimensional framework combining Clinical Cognitive Responsiveness (13 sub-dimensions) and Medical Atomic Skills (4 agent environments), covering 63 tasks; (2) three switchable information-flow stressors (omission, contradiction, evidence delay) for factorized degradation analysis; (3) a dynamic process audit protocol with five reasoning nodes that produces model-specific failure fingerprints; (4) hallucination propagation monitoring across initiation, propagation, anchoring, and contradiction interaction-capturing silent hallucination. Experiments on frontier models show that strong overall task performance does not guarantee process stability: stressors mainly disrupt contradiction detection, diagnosis updating, hallucination propagation, and contradiction-based self-correction, while final evidence grounding can remain superficially stable. MedBench v5 provides a unified infrastructure for capability profiling, controllable stress testing, process auditing, and hallucination trajectory analysis in clinical AI evaluation.

cs.CL↗

arXiv2026

Ling and Ring 2.6 Technical Report: Efficient and Instant Agentic Intelligence at Trillion-Parameter Scale

Efficient and scalable agentic intelligence requires models that can deliver both low-latency responses and strong reasoning capabilities while remaining practical to train, serve, and deploy. In this report, we present Ling-2.6 and Ring-2.6, a family of models designed to address this challenge at scale. Ling-2.6 is optimized for instant response generation and high capability per output token, whereas Ring-2.6 is tailored for deeper reasoning and more advanced agentic workflows. Instead of training from scratch, we upgrade the Ling-2.0 base model through architectural migration pre-training and large-scale post-training. This upgrade is guided by a unified co-design of model architecture, optimization objectives, serving systems, and agent training environments, enabling improvements in both model capability and deployment efficiency. At the architectural level, we introduce a hybrid linear attention design that integrates Lightning Attention with MLA, improving the efficiency of long-context training and decoding. To further enhance token efficiency, we optimize capability per output token through Evolutionary Chain-of-Thought, Linguistic Unit Policy Optimization, bidirectional preference alignment, and shortest-correct-response distillation. For agentic capabilities, we propose KPop, a reinforcement learning framework designed to support stable training of Ring-2.6-1T on large-scale environment-grounded data. KPop improves training efficiency through asynchronous scheduling across coding, search, tool use, and workflow execution, enabling scalable learning from complex agent-environment interactions. Together, Ling-2.6 and Ring-2.6 provide a practical pathway toward efficient, scalable, and open agentic systems. We open-source all checkpoints in the 2.6 family to support further research and development in practical agentic intelligence.

cs.CL↗

arXiv2026

RATrain: A Resource-Aware Training Runtime for Large Language Models on Bandwidth-Constrained Heterogeneous Supercomputing Platforms

Production heterogeneous supercomputing platforms are increasingly used to host large language model (LLM) training workloads. However, existing GPU-oriented training runtimes typically rely on high-bandwidth device memory, fast interconnects, and mature collective communication libraries, making them difficult to directly adapt to MT-3000, a platform with an explicit memory hierarchy, limited usable DDR capacity, and constrained inter-cluster communication. This paper presents RATrain, a resource-aware training runtime for dense LLMs on bandwidth-constrained heterogeneous supercomputing platforms. RATrain formulates standard non-interleaved 1F1B training as a training-state lifecycle scheduling problem, and schedules gradient synchronization, parameter update, parameter-view prefetching, and activation recovery at layer-level and stage-local granularity. RATrain further combines an MT-3000-aware execution backend for efficient and predictable FP16 GEMM, Attention Backward, and explicit data movement with a resource-aware planner that selects feasible training configurations under the 20GB usable-DDR constraint per compute cluster. We implement RATrain on a real MT-3000 platform and evaluate it using LLaMA-2-7B, Baichuan2-13B, Qwen2.5-32B, and LLaMA-2-70B configurations. Results show that RATrain achieves up to 1.35$\times$ end-to-end speedup over MT-3000-adapted GPU-style training strategies. For LLaMA-2-7B, RATrain scales to 1024 compute clusters, reaches 112,790.55 tokens/s, and achieves 97.0\% scaling efficiency. A further 1.028B-token correctness run shows that RATrain preserves the loss trajectory of a semantically equivalent Baseline-1F1B run, with a maximum relative loss deviation of 0.081\%.

cs.DC↗

arXiv2026

Bandwidth-Aware LLM Inference on Heterogeneous Many-Core Supercomputers

Large language model (LLM) inference is limited by high computational cost and memory bandwidth demands, making deployment on heterogeneous many-core processors challenging. Taking the MT-3000 processor used in the Tianhe supercomputer as an example, its limited main-memory bandwidth and distributed memory hierarchy exemplify these bottlenecks, making it difficult to directly migrate existing GPU-based inference frameworks. To address this problem, we propose THInfer, a hardware-aware inference framework that maximizes data locality under bandwidth-constrained conditions through hardware-software co-design and parallel strategy optimization. THInfer incorporates three key techniques: (1) a high-performance operator library for the VLIW SIMD architecture, providing hand-optimized FP16 kernels that achieve up to 70 percent of the peak performance per cluster; (2) a density-driven computation graph fusion and unified kernel scheduling mechanism, combined with a staged pipelined attention fusion method; and (3) a Prefill-Buffer-Decode (P-B-D) pipeline and bounded buffer management strategy, which supports hybrid parallelism and enables efficient multi-cluster collaboration through two-level communication based on MPI and hthreads. Experiments on the Llama model series show that THInfer improves throughput on the 7B model by 62 percent to 73 percent over DeepSpeed on two V100S GPUs and by 67 percent to 84 percent over the A800 GPU. The 13B and 30B models also demonstrate comparable or better performance. Moreover, THInfer maintains stable performance on the 70B model, whereas typical GPU-based frameworks fail to run under the same setting. Overall, THInfer significantly enhances throughput, reduces latency, and improves scalability, providing a feasible system solution for efficient and scalable LLM inference on heterogeneous many-core architectures.

cs.DC↗

arXiv2026

Efficient and simple fourth-order compact finite difference methods for convection-diffusion-reaction equations on arbitrary curved domains

In this paper, we discuss the 2D convection-diffusion-reaction equation with variable smooth coefficients and the Dirichlet boundary condition on a complicated, thin, and curved domain. We propose the fourth-order compact FDM at every grid point with the uniform Cartesian mesh. For the regular stencil center, we utilize the fourth-order compact 9-point FDM to approximate the solution. According to the preliminary analysis, we use vertical and horizontal transformations to derive fourth-order compact FDMs in 10 cases for all irregular stencil centers. To obtain the left-hand side of the stencil of the fourth-order FDM in each case, we only need to solve an at most $6 \times 24$ linear system which is presented with the explicit formula. The right-hand side of the FDM is constructed in explicit expression for any irregular stencil centers too. To achieve the fourth-order consistency, up to second-order partial derivatives of convection, diffusion, reaction, and source terms are used for the FDM at the regular stencil center, and the FDM at an irregular stencil center only requires first-order partial derivatives of convection, diffusion, reaction, and source terms, and up to third-order derivatives of the Dirichlet boundary function and the parametric expression of the boundary curve. We test challenging domains with 100-leaf, high-curvature, high-frequency, sharply varying, and nearly overlapping boundary curves, the proposed FDM produces the high accuracy and the stable fourth-order convergence rate in $l_2$ and $l_{\infty}$ norms. All stencils of our FDMs have a simple desired structure by only keeping grid points inside $\Omega$ in the standard compact 9-point stencil for both regular stencils and boundary stencils, but without assuming any information outside the domain $\Omega$.

math.NA↗

arXiv2026

Covariance-Aware Demapping on Fourier-Curve Constellations

Injecting artificial noise (AN) along the tangent space of a curved constellation makes each transmitted symbol induce a Gaussian observation with a symbol-dependent rank-one covariance, so the matched maximum-likelihood (ML) decoder differs from the Euclidean nearest-neighbor decoder by a single rank-one correction per candidate. We develop a baseband-demapper realization of this correction for the Fourier-curve constellation and instantiate a regular $(3,6)$ low-density parity-check (LDPC)-coded link at $(k,M){=}(20,64)$. Against four baselines (Euclidean-mismatched, flat-constellation isotropic-AN, no-AN, and same-spectral-efficiency narrowband), the matched decoder extends the BLER${=}10^{-1}$ operating range by approximately $5$\,dB over the Euclidean-mismatched counterpart on the same tangent-AN transmitter, at a cost of $2kM$ additional multiply-accumulate operations per symbol ($+50\%/+100\%$ under residual/template-correlation accounting) and a $20$\,KB constellation--tangent lookup table ($10$\,KB incremental over a Euclidean template-only LUT). A bit-interleaved coded-modulation achievable-rate (BICM-AIR) computation supports the same matched-metric advantage at the tested labeling and max-log demapper, indicating that the BLER gain is not merely an artifact of this particular LDPC simulation, and a Woodbury extension generalizes the rank-one correction to per-tone Ricean fading. In the tested Monte-Carlo runs, a design-aware bounded-search eavesdropper without the phase-key shows no successful LDPC decoding at any tested $k\in\{2,8,20\}$ within a $B{=}10^{3}$ non-code-aided search budget; code-aided, multi-frame, and known-preamble attacks are left to follow-up work. LUT quantization down to $6$ bits yields no measurable coded-BLER degradation at the tested operating points.

cs.IT↗

arXiv2026

Matched and Euclidean-Mismatched Decoding on Fourier-Curve Constellations with Tangent Noise

We study matched and Euclidean-mismatched decoding on finite Fourier-curve constellations with tangent-space artificial noise. Each hypothesis induces a Gaussian law with symbol-dependent rank-one covariance. We derive exact Euclidean pairwise errors for arbitrary pairs and an exact Gaussian-expectation representation for matched decoding on bilaterally tangent-orthogonal pairs. For uniform even constellations, the Euclidean side yields explicit distance spectra and symbol-error bounds across all offset classes; the matched side is exact on antipodal pairs and benchmarked numerically at the full-codebook level via Monte Carlo. By isolating the detection-theoretic consequence of tangent-space artificial noise, these results clarify analytically how noise fraction and constellation density enter the mismatch behavior; secrecy-rate implications require additional channel and adversary modeling.

cs.IT↗

arXiv2026

The Price of Ignorance: Information-Free Quotation for Data Retention in Machine Unlearning

When users exercise data deletion rights under the General Data Protection Regulation (GDPR) and similar regulations, mobile network operators face a tradeoff: excessive machine unlearning degrades model accuracy and incurs retraining costs, yet existing pricing mechanisms for data retention require the server to know every user's private privacy and accuracy preferences, which is infeasible under the very regulations that motivate unlearning. We ask: what is the welfare cost of operating without this private information? We design an information-free ascending quotation mechanism where the server broadcasts progressively higher prices and users self-select their data supply, requiring no knowledge of users' parameters. Under complete information, the protocol admits a unique subgame-perfect Nash equilibrium characterized by single-period selling. We formalize the Price of Ignorance -- the welfare gap between optimal personalized pricing (which knows everything) and our information-free quotation (which knows nothing) -- and prove a three-regime efficiency ordering. Numerical evaluation across seven mechanisms and 5000 Monte Carlo runs shows that this price is near zero: the information-free mechanism achieves >=99% of the welfare of its information-intensive benchmarks, while providing noise-robust guarantees and comparable fairness.

cs.GT↗

arXiv2026

Quality-Aware Denoising of Ultra-Short TDoA Measurements for 5G-NR UAV Localization

Reliable positioning is essential for Uncrewed Aerial Vehicles (UAVs) in safety-critical urban operations, yet achieving sub-meter accuracy under stringent latency constraints remains challenging. While 3rd Generation Partnership Project (3GPP) specifies repeated Positioning Reference Signals (PRS) transmissions for accurate Time Difference of Arrival (TDoA) measurements, denoising techniques specifically tailored for extremely limited measurement sequences within 3GPP frameworks remain underexplored. We propose Adaptive Gain Exponential Smoother (AGES), a lightweight filter combining exponentially weighted averaging with adaptive gains informed by 3GPP measurement quality reports. Simulations demonstrate AGES achieves 30-40% reduction in positioning error with only 3-5 repeated measurements while maintaining Fifth Generation New Radio (5G-NR) infrastructure compatibility.

eess.SP↗

arXiv2026

Balancing Functionality and GDPR-Driven Privacy in ISAC Trajectory Sharing

Integrated Sensing and Communications (ISAC) enables trajectory sharing that enhances beamforming, resource allocation, and cooperative perception, yet raises fundamental privacy concerns under the General Data Protection Regulation (GDPR) data minimisation principle. This paper proposes a Fisher Information Density (FID)-constrained trajectory sharing framework that enforces a local lower bound on estimation uncertainty, providing hard, quantifiable privacy guarantees by construction. Unlike fixed-noise approaches, the proposed method bounds the Privacy Leak Ratio (PLR) regardless of sensing power or adversarial post-processing, ensuring that no trajectory segment can be reconstructed beyond a prescribed accuracy threshold. Simulations on the OpenTraj dataset demonstrate that the framework keeps the average PLR below 20-25% and the maximum leakage segment duration under 2-2.5 s, while preserving data utility for downstream tasks such as movement prediction. The resulting criterion is interpretable, model-agnostic, and compatible with GDPR-compliant ISAC system design.

eess.SP↗

arXiv2026

Arbitrarily High-Order Convergence of Wavelet-based Galerkin Scheme for 1D Elliptic Interface Problems

The solution $u$ of an elliptic interface problem in a domain $\Omega$ is often smooth away from the interface $\Gamma\subset \Omega$, but its gradient is discontinuous across $\Gamma$. Consequently, $u$ has low global regularity and generally does not belong to $H^{3/2}(\Omega)$. This paper studies 1D elliptic interface problems using wavelet methods. We propose a Galerkin method based on compactly supported biorthogonal wavelet bases on bounded intervals with approximation order $m$, for any integer $m \ge 2$. Our approach involves incorporating wavelet basis functions from higher scale levels to capture the singularity in the neighbourhood of the interface $\Gamma$. A principal contribution of this paper is a rigorous convergence analysis establishing the optimal orders $m-1$ in the $H^1(\Omega)$-norm and $m$ in the $L^2(\Omega)$-norm. The proof combines careful decay estimates for dual wavelet coefficients associated with wavelets supported away from the interface $\Gamma$ and with those supported in its neighborhood, wavelet characterizations of Sobolev spaces, and standard convergence arguments from the finite element method (FEM). Various numerical experiments are provided to verify the theoretical findings, including a special two-dimensional elliptic interface problem with vertical interface lines.

math.NA↗

arXiv2026

Generative Semantic HARQ: Latent-Space Text Retransmission and Combining

Semantic communication conveys meaning rather than raw bits, but reliability at the semantic level remains an open challenge. We propose a semantic-level hybrid automatic repeat request (HARQ) framework for text communication, in which a Transformer-variational autoencoder (VAE) codec operates as a lightweight overlay on the conventional protocol stack. The stochastic encoder inherently generates diverse latent representations across retransmissions-providing incremental knowledge (IK) from a single model without dedicated protocol design. On the receiver side, a soft quality estimator triggers retransmissions and a quality-aware combiner merges the received latent vectors within a consistent latent space. We systematically benchmark six semantic quality metrics and four soft combining strategies under hybrid semantic distortion that mixes systematic bias with additive noise. The results suggest combining Weighted-Average or MRC-Inspired combining with self-consistency-based HARQ triggering for the best performance.

eess.SP↗