arXiv subjects

Ming Jiang

Publications and source records attributed to Ming Jiang.

At least 19 recordsLinked to original sources

arXiv2026

A Survey of Decentralized Physical Infrastructure Network,Research Directions, and Open Challenges

The Decentralized Physical Infrastructure Network (DePIN) represents a transformative paradigm that redefines the construction, operation, and governance of Information and Communication Technology (ICT) infrastructure in the Web 3.0 era. DePIN integrates physical resources, such as networking equipment, storage, and computing power, with decentralized digital governance, forming a self-incentivized ecosystem that is collaboratively built, shared, and governed by the community. It provides a foundational framework for future communication networks, facilitating decentralized edge intelligence, efficient resource sharing, and trustworthy coordination among heterogeneous devices. Focusing on the feasibility of this emerging paradigm, this paper examines the technology landscape in the pre-DePIN era and gaps between existing methodologies and the forthcoming decentralized infrastructure for Web 3.0. It provides a systematic and comprehensive survey of the background, core characteristics, technical architecture, and applications of DePIN across various vertical domains. The paper analyzes the DePIN technology stack from six layers: physical infrastructure, blockchain, interaction, trust, incentive, and application, with special attention to their cross-layer feedback loops, implementation readiness, and deployment limitations. To further bridge conceptual analysis and practical deployment, we propose a DePIN feasibility assessment framework covering technical, governance, and economic dimensions. Moreover, we highlight promising research directions, providing insights and guidance for further exploration and deployment of DePIN.

eess.SP↗

arXiv2026

Beyond Scores: Understanding LLM-as-a-Judge Mechanisms in Summarization Evaluation

LLM-based evaluators of natural language generation (NLG) quality are widely deployed as scoring tools and as automated training signals, yet the internal procedure by which they assign a rating remains poorly understood. We investigate this procedure mechanistically through an eight-attack perturbation taxonomy across the Readability and Adequacy dimensions of NLG quality, a generation pipeline that produces paired clean and corrupt summaries with controlled error intensity and explicit token-level modification maps, and a four-experiment battery of causal tracing, logit-lens vocabulary projection, and attention-head knockout applied to Themis (Llama-3-8B) and Prometheus (Mistral-7B). Both evaluators implement a structured, coherent evaluation pipeline operating in two stages: below layer 15, attention performs local error comparison and routes the result to the final input position; above it, the MLP cascade integrates the signal and writes the rating, with the decision crystallizing in the residual stream at a sharp late layer (L = 26 on Themis, L = 25 on Prometheus). Furthermore, a base-model control at the same scale (Llama-3-8B) reproduces the routing architecture and crystallization but not the stage separation, isolating the two mechanisms that fine-tuning specifically installs, suppression of below-L15 MLP contribution at the last position and a two-layer advance of the crystallization depth, indicating that fine-tuning sculpts an existing substrate rather than building the pipeline from scratch. We release the source code and data at https://github.com/himil-v/judge-mech

cs.CL↗

arXiv2026

MemeBridge: A Dataset for Benchmarking and Mitigating the Bidirectional Cultural Gap in Meme Interpretation

Communicating across cultures is inherently challenging, especially through culturally dense and ambiguous formats like memes. While people expect large language models (LLMs) to hold promise for bridging such gaps, existing benchmark datasets often fail to capture the cultural context necessary for accurate interpretation. To address this, we introduce MemeBridge, a curated dataset centered on U.S.-originated memes, designed to capture two complementary perspectives: (1) how Chinese participants interpret these memes, and (2) how U.S. participants anticipate how people from other cultures might misunderstand them. Here, context refers to implicit cultural knowledge, including background beliefs, norms, and shared assumptions that shape meme comprehension. The dataset was constructed via a multi-stage crowdsourcing pipeline with rigorous validation, including human agreement checks and GPT-based classification verification. Each meme is annotated with sentiment, emotion, cultural significance, and knowledge type, providing rich supervision for downstream tasks. Notably, we observe that the anticipated misunderstandings from U.S. participants are often inaccurate, highlighting the asymmetries in cultural understanding and the challenges of adopting perspectives beyond one's own. This bidirectional framing, which focuses on both expression and perception, enables more nuanced benchmarking of cross-cultural comprehension. Our probing of multiple LLMs reveals that while models developed in different cultural contexts exhibit partial cross-cultural understanding, they often struggle with sophisticated interpretations. By contrast, fine-tuning with MemeBridge improves model performance, underscoring the value of culturally grounded resources for training and evaluating LLMs in globally diverse settings.

cs.CL↗

arXiv2026

Fractional revival on oriented Cayley and semi-Cayley graphs over abelian groups

Fractional revival (FR), a generalization of perfect state transfer (PST), is a significant phenomenon in quantum state transfer that allows quantum information to be transmitted between two qubits with a certain probability. The existence of FR has been extensively studied on many classes of graphs. However, oriented graphs have not yet been investigated. In this paper, we investigate the existence of proper FR on oriented graphs. We first establish necessary and sufficient conditions for oriented graphs to admit proper FR between strongly cospectral vertices. Furthermore, we prove that oriented Cayley graphs over abelian groups do not admit proper FR, and we subsequently characterize the conditions under which oriented semi-Cayley graphs over abelian groups admit proper FR.

math.CO↗

arXiv2026

One Student, Many Teachers: Multi-Task On-Policy Distillation via Soft-Prompt Privileged Context

On-policy self-distillation (OPSD) teaches large language models new skills through a teacher that shares the student's backbone and supervises its own rollouts. Existing teachers either inject privileged context at the input -- inducing post-hoc rationalization -- or fine-tune weights, accumulating drift and forgetting across tasks. We propose \method, whose teacher differs from the student only by a learnable soft prompt: trained on $(x, y_\text{gold})$ pairs with the backbone frozen, the prompt yields a task-specific teacher that preserves the student's exact representational geometry. \method\ extends naturally to multi-task settings by routing each example in a merged corpus to its corresponding soft-prompt teacher, allowing a single student to absorb knowledge from $K$ teachers in parallel; at inference, all prompts are discarded. On Qwen3-1.7B-Base and Phi-4-mini-instruct across four tasks (Science, Tool Use, Biology, Math), the single-task variant (OPD with a PT teacher) matches or exceeds full fine-tuning while training orders of magnitude fewer parameters, and the multi-task variant achieves the best overall average ($56.2$ on Qwen3-1.7B-Base) while preserving general-capability benchmarks -- in contrast to sequential SFT, which degrades both.

cs.LG↗

arXiv2026

GeoDrive-Bench: Benchmarking Region-Specific Multimodal Reasoning in Autonomous Driving

Vision-language models (VLMs) for autonomous driving have shown promising performance, but their ability to handle region-specific traffic rules remains underexplored, raising uncertainties about their deployment across diverse global settings. We therefore introduce GeoDrive-Bench, a novel benchmark that enables the systematic investigation of VLMs' geo-culturally grounded driving reasoning. We curated 5,053 human-validated multiple-choice QA pairs across six countries covering diverse driving cultures. Specifically, we emphasize four driving tasks: perception, prediction, planning, and region reasoning. Each question requires models to infer the correct driving behavior from visual evidence and local traffic conventions without explicit country labels. Beyond evaluation, we further design a distillation algorithm that injects region-specific traffic-rule knowledge into the internal representations of VLMs, enabling models to better align visual scene understanding with local driving policies. Experiments on nine state-of-the-art VLMs show substantial performance variations across geo-driving cultures for each task, while our proposed baseline models exhibit improved geo-cultural reasoning across regions. These results suggest that current VLMs still lack robust region-aware driving intelligence and highlight GeoDrive-Bench as a diagnostic and training-oriented testbed for deployable autonomous driving foundation models.

cs.CV↗

arXiv2026

From Heads to Neurons: Causal Attribution and Steering in Multi-Task Vision-Language Models

Recent work has increasingly explored neuron-level interpretation in vision-language models (VLMs) to identify neurons critical to final predictions. However, existing neuron analyses generally focus on single tasks, limiting the comparability of neuron importance across tasks. Moreover, ranking strategies tend to score neurons in isolation, overlooking how task-dependent information pathways shape the write-in effects of feed-forward network (FFN) neurons. This oversight can exacerbate neuron polysemanticity in multi-task settings, introducing noise into the identification and intervention of task-critical neurons. In this study, we propose HONES (Head-Oriented Neuron Explanation & Steering), a gradient-free framework for task-aware neuron attribution and steering in multi-task VLMs. HONES ranks FFN neurons by their causal write-in contributions conditioned on task-relevant attention heads, and further modulates salient neurons via lightweight scaling. Experiments on four diverse multimodal tasks and two popular VLMs show that HONES outperforms existing methods in identifying task-critical neurons and improves model performance after steering. Our source code is released at: https://github.com/petergit1/HONES.

cs.CV↗

arXiv2026

A remark on an error analysis for classical and learned Tikhonov regularization schemes

This paper presents an error analysis of classical and learned Tikhonov regularization schemes for inverse problems. We first demonstrate, both theoretically and numerically, that using a fixed regularization parameter across varying noise levels-which is a common miss-specification in practice-has only a mild impact on the reconstruction error. As a special case, we then investigate scenarios where the true data resides in an unknown finite-dimensional subspace. Here, our results lead to an empirically supported strategy for estimating the unknown dimension based on numerical experiments. Finally, we examine the approach that motivated this study: a method where a sparsity-promoting term is learned from denoising tasks and subsequently applied to general inverse problems via a simple heuristic parameter selection. The corresponding error analysis is initially developed using classical concepts and subsequently refined through a more detailed investigation of the discretized setting.

math.NA↗

arXiv2026

MLB: A Scenario-Driven Benchmark for Evaluating Large Language Models in Clinical Applications

The proliferation of Large Language Models (LLMs) presents transformative potential for healthcare, yet practical deployment is hindered by the absence of frameworks that assess real-world clinical utility. Existing benchmarks test static knowledge, failing to capture the dynamic, application-oriented capabilities required in clinical practice. To bridge this gap, we introduce a Medical LLM Benchmark MLB, a comprehensive benchmark evaluating LLMs on both foundational knowledge and scenario-based reasoning. MLB is structured around five core dimensions: Medical Knowledge (MedKQA), Safety and Ethics (MedSE), Medical Record Understanding (MedRU), Smart Services (SmartServ), and Smart Healthcare (SmartCare). The benchmark integrates 22 datasets (17 newly curated) from diverse Chinese clinical sources, covering 64 clinical specialties. Its design features a rigorous curation pipeline involving 300 licensed physicians. Besides, we provide a scalable evaluation methodology, centered on a specialized judge model trained via Supervised Fine-Tuning (SFT) on expert annotations. Our comprehensive evaluation of 10 leading models reveals a critical translational gap: while the top-ranked model, Kimi-K2-Instruct (77.3% accuracy overall), excels in structured tasks like information extraction (87.8% accuracy in MedRU), performance plummets in patient-facing scenarios (61.3% in SmartServ). Moreover, the exceptional safety score (90.6% in MedSE) of the much smaller Baichuan-M2-32B highlights that targeted training is equally critical. Our specialized judge model, trained via SFT on a 19k expert-annotated medical dataset, achieves 92.1% accuracy, an F1-score of 94.37%, and a Cohen's Kappa of 81.3% for human-AI consistency, validating a reproducible and expert-aligned evaluation protocol. MLB thus provides a rigorous framework to guide the development of clinically viable LLMs.

cs.LG↗

arXiv2025

dVLM-AD: Enhance Diffusion Vision-Language-Model for Driving via Controllable Reasoning

The autonomous driving community is increasingly focused on addressing the challenges posed by out-of-distribution (OOD) driving scenarios. A dominant research trend seeks to enhance end-to-end (E2E) driving systems by integrating vision-language models (VLMs), leveraging their rich world knowledge and reasoning abilities to improve generalization across diverse environments. However, most existing VLMs or vision-language agents (VLAs) are built upon autoregressive (AR) models. In this paper, we observe that existing AR-based VLMs -- limited by causal attention and sequential token generation -- often fail to maintain consistency and controllability between high-level reasoning and low-level planning. In contrast, recent discrete diffusion VLMs equipped with bidirectional attention exhibit superior controllability and reliability through iterative denoising. Building on these observations, we introduce dVLM-AD, a diffusion-based vision-language model that unifies perception, structured reasoning, and low-level planning for end-to-end driving. Evaluated on nuScenes and WOD-E2E, dVLM-AD yields more consistent reasoning-action pairs and achieves planning performance comparable to existing driving VLM/VLA systems despite a modest backbone, outperforming AR-based baselines with a 9 percent improvement in behavior-trajectory consistency and a 6 percent increase in RFS on long-tail WOD-E2E scenarios. These results suggest a controllable and reliable pathway for scalable end-to-end driving.

cs.CV↗

arXiv2025

Deep learning with hybrid frequency differencing and principal component analysis for 21-cm foreground and beam mitigation

Twenty-one-centimeter intensity mapping is a powerful probe of the large-scale distribution of neutral hydrogen (HI) and cosmological observables such as baryon acoustic oscillations. A major challenge is contamination from bright foregrounds and frequency-dependent beam effects, which can lead to signal loss in traditional methods such as principal component analysis (PCA). We develop a hybrid approach that trains a U-shaped convolutional neural network (UNet) on two input channels derived from frequency differencing (FD) and PCA cleaning, enabling it to exploit their complementary behavior across different scales. This two-channel strategy achieves improved performance, maintaining the cross-correlation power spectrum close to unity on large scales under a cosine beam and improving by 5\%-8\% relative to either FD- or PCA-based UNet alone. We further show that the method can robustly recover the HI signal even when the beam model is imperfect and differs between training and testing, with the large-scale cross-correlation remaining close to unity within the $1\sigma$ level. These results demonstrate that the proposed approach provides a robust framework for HI signal reconstruction under realistic observational conditions.

astro-ph.CO↗

arXiv2025

Advancing Fluid Antenna-Assisted Non-Terrestrial Networks in 6G and Beyond: Fundamentals, State of the Art, and Future Directions

With the surging demand for ultra-reliable, low-latency, and ubiquitous connectivity in Sixth-Generation (6G) networks, Non-Terrestrial Networks (NTNs) emerge as a key complement to terrestrial networks by offering flexible access and global coverage. Despite the significant potential, NTNs still face critical challenges, including dynamic propagation environments, energy constraints, and dense interference. As a key 6G technology, Fluid Antennas (FAs) can reshape wireless channels by reconfiguring radiating elements within a limited space, such as their positions and rotations, to provide higher channel diversity and multiplexing gains. Compared to fixed-position antennas, FAs can present a promising integration path for NTNs to mitigate dynamic channel fading and optimize resource allocation. This paper provides a comprehensive review of FA-assisted NTNs. We begin with a brief overview of the classical structure and limitations of existing NTNs, the fundamentals and advantages of FAs, and the basic principles of FA-assisted NTNs. We then investigate the joint optimization solutions, detailing the adjustments of FA configurations, NTN platform motion modes, and resource allocations. We also discuss the combination with other emerging technologies and explore FA-assisted NTNs as a novel network architecture for intelligent function integrations. Furthermore, we delve into the physical layer security and covert communication in FA-assisted NTNs. Finally, we highlight the potential future directions to empower broader applications of FA-assisted NTNs.

cs.NI↗

arXiv2025

Pair state transfer in tensor product and double cover

Quantum state transfer, first introduced by Bose in 2003, is an important physical phenomenon in quantum networks, which plays a vital role in quantum communication and quantum computing. In 2004, Christandl et al. proposed the concept of perfect state transfer on graphs by modeling the quantum network using graphs, and unveiled the feasibility of applying graph theory to quantum state transfer. In 2018, Chen and Godsil proposed the definition of Laplacian perfect pair state transfer on graphs, which is a brilliant generalization of perfect state transfer. In this paper, we investigate the existence of Laplacian perfect pair state transfer in tensor product and double cover of two regular graphs, respectively, and reveal fundamental connections between perfect state transfer and Laplacian perfect pair state transfer. We give necessary and sufficient conditions for the tensor product of two regular graphs to admit Laplacian perfect pair state transfer, where one of the two regular graphs admits perfect state transfer or Laplacian perfect pair state transfer. Additionally, we characterize the existence of Laplacian perfect pair state transfer in the double cover of two regular graphs. By our results, a variety of families of graphs admitting Laplacian perfect pair state transfer can be constructed.

math.CO↗

arXiv2025

SciEvent: Benchmarking Multi-domain Scientific Event Extraction

Scientific information extraction (SciIE) has primarily relied on entity-relation extraction in narrow domains, limiting its applicability to interdisciplinary research and struggling to capture the necessary context of scientific information, often resulting in fragmented or conflicting statements. In this paper, we introduce SciEvent, a novel multi-domain benchmark of scientific abstracts annotated via a unified event extraction (EE) schema designed to enable structured and context-aware understanding of scientific content. It includes 500 abstracts across five research domains, with manual annotations of event segments, triggers, and fine-grained arguments. We define SciIE as a multi-stage EE pipeline: (1) segmenting abstracts into core scientific activities--Background, Method, Result, and Conclusion; and (2) extracting the corresponding triggers and arguments. Experiments with fine-tuned EE models, large language models (LLMs), and human annotators reveal a performance gap, with current models struggling in domains such as sociology and humanities. SciEvent serves as a challenging benchmark and a step toward generalizable, multi-domain SciIE.

cs.CL↗

arXiv2025

V-SEAM: Visual Semantic Editing and Attention Modulating for Causal Interpretability of Vision-Language Models

Recent advances in causal interpretability have extended from language models to vision-language models (VLMs), seeking to reveal their internal mechanisms through input interventions. While textual interventions often target semantics, visual interventions typically rely on coarse pixel-level perturbations, limiting semantic insights on multimodal integration. In this study, we introduce V-SEAM, a novel framework that combines Visual Semantic Editing and Attention Modulating for causal interpretation of VLMs. V-SEAM enables concept-level visual manipulations and identifies attention heads with positive or negative contributions to predictions across three semantic levels: objects, attributes, and relationships. We observe that positive heads are often shared within the same semantic level but vary across levels, while negative heads tend to generalize broadly. Finally, we introduce an automatic method to modulate key head embeddings, demonstrating enhanced performance for both LLaVA and InstructBLIP across three diverse VQA benchmarks. Our data and code are released at: https://github.com/petergit1/V-SEAM.

cs.CL↗

arXiv2025

MonoPartNeRF:Human Reconstruction from Monocular Video via Part-Based Neural Radiance Fields

In recent years, Neural Radiance Fields (NeRF) have achieved remarkable progress in dynamic human reconstruction and rendering. Part-based rendering paradigms, guided by human segmentation, allow for flexible parameter allocation based on structural complexity, thereby enhancing representational efficiency. However, existing methods still struggle with complex pose variations, often producing unnatural transitions at part boundaries and failing to reconstruct occluded regions accurately in monocular settings. We propose MonoPartNeRF, a novel framework for monocular dynamic human rendering that ensures smooth transitions and robust occlusion recovery. First, we build a bidirectional deformation model that combines rigid and non-rigid transformations to establish a continuous, reversible mapping between observation and canonical spaces. Sampling points are projected into a parameterized surface-time space (u, v, t) to better capture non-rigid motion. A consistency loss further suppresses deformation-induced artifacts and discontinuities. We introduce a part-based pose embedding mechanism that decomposes global pose vectors into local joint embeddings based on body regions. This is combined with keyframe pose retrieval and interpolation, along three orthogonal directions, to guide pose-aware feature sampling. A learnable appearance code is integrated via attention to model dynamic texture changes effectively. Experiments on the ZJU-MoCap and MonoCap datasets demonstrate that our method significantly outperforms prior approaches under complex pose and occlusion conditions, achieving superior joint alignment, texture fidelity, and structural continuity.

cs.CV↗

arXiv2025

Performance Bounds and Degree-Distribution Optimization of Finite-Length BATS Codes

Batched sparse (BATS) codes were proposed as a reliable communication solution for networks with packet loss. In the finite-length regime, the error probability of BATS codes under belief propagation (BP) decoding has been studied in the literature and can be analyzed by recursive formulae. However, all existing analyses have not considered precoding or have treated the BATS code and the precode as two separate entities. In this paper, we analyze the word-wise error probability of finite-length BATS codes with a precode under joint decoding, including BP decoding and maximum-likelihood (ML) decoding. The joint BP decoder performs peeling decoding on a joint Tanner graph constructed from both the BATS and the precode Tanner graphs, and the joint ML decoder solves a single linear system with all linear constraints implied by the BATS code and the precode. We derive closed-form upper bounds on the error probability for both decoders. Specifically, low-density parity-check (LDPC) precodes are used for BP decoding, and any generic precode can be used for ML decoding. Even for BATS codes without a precode, the derived upper bound for BP decoding is more accurate than the approximate recursive formula, and easier to compute than the exact recursive formula. The accuracy of the two upper bounds has been verified by many simulation results. Based on the two upper bounds, we formulate an optimization problem to optimize the degree distribution of LDPC-precoded BATS codes, which improves BP performance, ML performance, or both. In our experiments, to transmit 128 packets over a line network with packet loss, the optimized LDPC-precoded BATS codes reduce the transmission overhead to less than 50% of that of standard BATS codes under comparable decoding complexity constraints.

cs.IT↗

arXiv2024

No Preference Left Behind: Group Distributional Preference Optimization

Preferences within a group of people are not uniform but follow a distribution. While existing alignment methods like Direct Preference Optimization (DPO) attempt to steer models to reflect human preferences, they struggle to capture the distributional pluralistic preferences within a group. These methods often skew toward dominant preferences, overlooking the diversity of opinions, especially when conflicting preferences arise. To address this issue, we propose Group Distributional Preference Optimization (GDPO), a novel framework that aligns language models with the distribution of preferences within a group by incorporating the concept of beliefs that shape individual preferences. GDPO calibrates a language model using statistical estimation of the group's belief distribution and aligns the model with belief-conditioned preferences, offering a more inclusive alignment framework than traditional methods. In experiments using both synthetic controllable opinion generation and real-world movie review datasets, we show that DPO fails to align with the targeted belief distributions, while GDPO consistently reduces this alignment gap during training. Moreover, our evaluation metrics demonstrate that GDPO outperforms existing approaches in aligning with group distributional preferences, marking a significant advance in pluralistic alignment.

cs.CL↗