Searcharxiv⌕ Search

arXiv subjects

Hao Fang

Publications and source records attributed to Hao Fang.

At least 37 records · Page 2Linked to original sources
arXiv2026

STBridge: Shared-Target Alignment for Bridging Understanding and Generation in UMMs

Unified multimodal models (UMMs) aim to integrate visual understanding and generation within a single architecture, but architectural unification alone does not ensure semantic consistency. A model may describe the intended target correctly while generating an inconsistent edit. This exposes an understanding-generation alignment gap: linguistic and visual outputs live in different spaces, yet should be governed by the same target semantics. We study this gap in image editing, where an instruction defines a target state that can be both described and visually realized. Given a source image and an edit instruction, we compare a UMM's target caption with its edited image to test whether the two outputs converge on the same result. Our analysis shows that existing UMMs remain weakly aligned, especially for fine-grained entities, attributes, spatial relations, and local details, indicating that semantic unification is not achieved by architecture alone. To bridge this gap, we propose STBridge, a shared-target alignment framework that connects understanding and generation through a common target state. Here the target caption expresses the desired visual result, while the edited image realizes it visually, replacing separate task-specific paths with a shared information flow from target expression to target realization. STBridge follows an align-then-optimize strategy: supervised fine-tuning first establishes the shared-target channel, and sequential reinforcement learning further refines target-centered coordination. Across visual understanding, image generation, and image editing benchmarks, STBridge consistently improves over the initialization model. Alignment analysis confirms that STBridge narrows the gap between what the model describes and what it generates, demonstrating shared-target alignment as an effective post-training strategy for bridging understanding and generation in UMMs.

cs.CV↗
arXiv2026

Ideal Gårding polynomials

We introduce ideal Gårding polynomials, a convexity-enhanced subclass of Gårding polynomials whose Gårding components are recursively convex under partial differentiation. This class strictly contains real stable polynomials and, after translation and homogenization, lies in the Lorentzian class. Our main result is that ideal Gårding polynomials still admit a robust structure theory despite this additional convexity: they are preserved under polarization, satisfy natural closure properties, and support a linear preserver theory. A key contribution of this paper is a universal model for univariate Gårding polynomials, described by monotone root sequences and equivalently by volume polynomials of Pitman--Stanley polytopes. We establish quotient concavity, and Newton--Maclaurin type inequalities, which leads to the polarization theorem, and suggests further connections with convex geometry and Lorentzian polynomials.

math.CO↗
arXiv2026

A unified framework for imitation dynamics on higher-order networks

Cooperation is central to human societies and often unfolds within groups. Higher-order networks, such as hypergraphs, naturally represent these groups as hyperedges. Network structures and update rules, by which individuals revise their strategies, are the two fundamental components that shape the evolution of cooperation in structured populations. Yet while the effects of network structure have been studied extensively, update rules have been examined mostly through isolated models, leaving their relationships and the origins of their differing evolutionary outcomes poorly understood. Here we develop a unified framework for imitation dynamics on higher-order networks, parameterizing imitation-based update rules by the number of groups an individual samples and the number of peers consulted within each group. Under weak selection, we derive a closed-form condition for the success of cooperation in any multiplayer social dilemma on homogeneous hypergraphs, encompassing games with both linear and nonlinear payoff structures. The framework places previously disconnected update rules within a single family and reduces their effects on cooperation to one interpretable quantity, which we term information diversity. Update rules inducing higher information diversity promote cooperation more effectively, and we prove that this ordering holds strictly across the entire space of multiplayer social dilemmas. Simulations extend this principle to heterogeneous hypergraphs constructed both synthetically and from empirical data. Our framework provides a systematic way to represent, analyze, and compare update rules on higher-order networks, turning a fragmented collection of microscopic updating mechanisms into a tractable and interpretable theory.

physics.soc-ph↗
arXiv2026

ICME 2026 Grand Challenge on Cross-Scenario Defect Detection and Fine-Grained Severity Grading for High-Precision Manufacturing

This paper presents the IEEE International Conference on Multimedia and Expo (ICME) 2026 Grand Challenge on Cross-Scenario Defect Detection and Fine-Grained Severity Grading for High-Precision Manufacturing. The challenge is motivated by two key limitations of existing industrial defect inspection systems: (1) current deep learning-based methods often suffer significant performance degradation when deployed in unseen production scenarios, and (2) most benchmarks neglect severity-aware assessment, which is critical for risk control and yield optimization. To address these limitations, we design two complementary tracks: Track 1 (Cross-Scenario Defect Detection) targets accurate defect detection, localization, and classification across diverse unseen production environments; Track 2 (Fine-Grained Severity Grading) requires assigning each detected defect an industry-standard severity level, including Acceptable, Marginal NG, NG, and Gross NG. We construct a large-scale industrial dataset of high-resolution microscopic images spanning seven representative defect categories, comprising over 3,800 images with pixel-level instance annotations for Track 1 and over 2,600 images with severity-grade labels for Track 2. The challenge attracted 86 registered participants with 130 submissions; during the final testing phase, 21 teams submitted results and 12 teams provided models with technical reports. The resulting benchmark, together with the diverse and effective solutions contributed by participating teams, sets a new standard for industrial defect analysis research.

cs.CV↗
arXiv2026

Admissibility, Topology, and the $σ_k$-Loewner--Nirenberg problem

The $σ_k$-Loewner--Nirenberg problem is a fully nonlinear generalization of the classical Loewner--Nirenberg problem of constructing complete conformal metrics with constant negative scalar curvature in the interior of domains. For the $σ_k$-version, once $k > 1$, one must impose a negative admissibility condition to ensure ellipticity of the equation. In this note, we exhibit topological obstructions to admissibility and illustrate this with examples.

math.DG↗
arXiv2026

MemVenom: Triggered Poisoning of Multimodal Memories in Web Agents

External memory has become a core component of modern web agents, enabling long-horizon reasoning through the retrieval of past experiences. However, this paradigm introduces a critical vulnerability: malicious content injected into memory can be persistently recalled and repeatedly influence agent behavior. In this work, we identify and systematically study multimodal memory poisoning, an overlooked yet practical attack surface in web-agent systems. We propose MemVenom, a unified black-box attack framework that poisons graph-structured external memory with coordinated text-image evidence. Our method consists of a two-stage design: (1) a trigger-conditioned retrieval attack that ensures high-probability recall of malicious memory, and (2) a post-retrieval attack induction that leverages adversarial perturbations and stealthy OCR injection to override the original user objective. Unlike prior attacks that operate on prompts or text-only memory, our approach enables persistent, reusable, and goal-agnostic attacks without modifying model parameters or re-optimizing malicious tasks. Experiments across multiple web-agent frameworks and vision-language models demonstrate that MemVenom achieves strong end-to-end attack success with minimal impact on benign performance, reaching up to 99.15% on GPT-5-family web agents, while transferring effectively across architectures and model scales.

cs.CR↗
arXiv2026

Bypassing Copyright Protection in Diffusion-based Customization via Two-Stage Latent Feature Optimization

With the growing concerns over copyright infringement in diffusion-based customization, adversarial attacks have emerged as a prominent defense strategy to prevent malicious content forgery in personalized image generation. However, current defenses typically introduce persistent perturbations in the latent space of Latent Diffusion Models (LDMs), which remain susceptible to adaptive bypasses by adversaries. In this paper, we introduce Two-Stage Latent Feature Optimization (TS-LFO), an efficient and effective copyright-stealing attack against protected diffusion-based customization. We begin by observing that existing defenses primarily disrupt the mapping between input images and their latent representations, thereby degrading the model's ability to produce personalized outputs. To counteract this, TS-LFO restores the broken mapping through a two-stage optimization process. In the Latent Denoising Stage, we enhance semantic consistency between latent codes and input images by jointly minimizing a Latent-Image Alignment Loss and a Latent Diffusion Loss with timestep-dependent weights, effectively suppressing the high-frequency noise introduced by defenses. In the Latent Reconstruction Stage, we recover low-frequency semantic information using pixel-level constraints to refine the latent features. Extensive experiments show that TS-LFO consistently bypasses state-of-the-art (SOTA) copyright defenses and outperforms SOTA copyright attacks such as DiffPure, GrIDPure and IMPRESS across diverse settings.

cs.CR↗
arXiv2026

Ionization energies for Rydberg $^4 \mathrm{He}$ ($1snp\,^{1,3}P$) states using the correlated B-spline basis function method

We extend the correlated B-spline basis function (C-BSBF) method to high-precision calculations of the ionization energies of helium Rydberg $n^{1,3}P$ states ($n=24$--$35$). Using a unified basis set, we evaluate nonrelativistic energies, relativistic corrections of order $mα^4$ (including finite-mass recoil), QED contributions of order $mα^5$, and partial $mα^6$ terms (singlet-triplet mixing, one- and two-loop radiative corrections). The remaining higher-order contributions are estimated via $1/n^3$ scaling. The resulting ionization energies achieve kHz-level accuracy and are in excellent agreement with independent Hylleraas calculations, thereby providing cross-validation between two distinct theoretical approaches. From these data, the quantum-defect parameters are determined and used to extrapolate the ionization energies up to $n=102$. Combining our Rydberg ionization energies with high-precision experimental $2S \rightarrow nP$ transition frequencies yields the ionization energies for the metastable $2^{1}S$ and $2^{3}S$ states as \num{960332040.533(10)}$_\mathrm{stat}(20)_ \mathrm{sys}$ MHz and \num{1152842742.7274(53)}$_\mathrm{stat}(25)_ \mathrm{sys}$ MHz, respectively. The C-BSBF result for the $2 \, ^1 S$ state is consistent with the experimental ionization energy obtained from Rydberg-series extrapolation, while for the $2 \, ^3 S$ state the difference is 0.019(10) MHz.

physics.atom-ph↗
arXiv2026

HOLO: Homography-Guided Pose Estimator Network for Fine-Grained Visual Localization on SD Maps

Visual localization on standard-definition (SD) maps has emerged as a promising low-cost and scalable solution for autonomous driving. However, existing regression-based approaches often overlook inherent geometric priors, resulting in suboptimal training efficiency and limited localization accuracy. In this paper, we propose a novel homography-guided pose estimator network for fine-grained visual localization between multi-view images and standard-definition (SD) maps. We construct input pairs that satisfy a homography constraint by projecting ground-view features into the BEV domain and enforcing semantic alignment with map features. Then we leverage homography relationships to guide feature fusion and restrict the pose outputs to a valid feasible region, which significantly improves training efficiency and localization accuracy compared to prior methods relying on attention-based fusion and direct 3-DoF pose regression. To the best of our knowledge, this is the first work to unify BEV semantic reasoning with homography learning for image-to-map localization. Furthermore, by explicitly modeling homography transformations, the proposed framework naturally supports cross-resolution inputs, enhancing model flexibility. Extensive experiments on the nuScenes dataset demonstrate that our approach significantly outperforms existing state-of-the-art visual localization methods. Code and pretrained models will be publicly released to foster future research.

cs.CV↗
arXiv2026

Do Joint Audio-Video Generation Models Understand Physics?

Joint audio-video generation models are rapidly approaching professional production quality, raising a central question: do they understand audio-visual physics, or merely generate plausible sounds and frames that violate real-world consistency? We introduce AV-Phys Bench, a benchmark for evaluating physical commonsense in joint audio-video generation. AV-Phys Bench tests models across three scene categories: Steady State, Event Transition, and Environment Transition. It covers physics-grounded subcategories drawn from real-world scenes, plus Anti-AV-Physics prompts that deliberately request physically inconsistent audio-video behavior. Each generation is evaluated along five dimensions: visual semantic adherence, audio semantic adherence, visual physical commonsense, audio physical commonsense, and cross-modal physical commonsense. Across three proprietary and four open-source models, we find that Seedance 2.0 performs best overall, but all models remain far from robust physical understanding. Performance drops sharply on event-driven and environment-driven transitions, and even strong proprietary systems collapse on Anti-AV-Physics prompts. We further introduce AV-Phys Agent, a ReAct-style evaluator that combines a multimodal language model with deterministic acoustic measurement tools, producing rankings that closely align with human ratings. Our results identify cross-modal physical consistency and transition-driven scene dynamics as key open challenges for joint audio-video generation.

cs.SD↗
arXiv2026

Reasoning Matters: Mitigate Hallucination in Multimodal Large Reasoning Models via Reasoning-Conditioned Preference Optimization

Multimodal Large Reasoning Models introduce the reasoning paradigm, demonstrating strong capabilities on complex vision-language tasks. However, they still suffer from severe hallucinations. Existing training-based methods typically mitigate hallucinations through response-level direct preference optimization (DPO), where the Chain-of-Thought (CoT) and the final answer are treated as a monolithic output and optimized jointly. We reveal that this formulation performs similarly to answer-only optimization, suggesting that it primarily learns answer-level preference, while leaving CoT-level supervision insufficiently exploited. To address this issue, we explicitly formulate a CoT-oriented preference term and derive Reasoning-Conditioned Direct Preference Optimization (RC-DPO), which models the CoT as a condition for answer generation and contrasts the preference for the same preferred answer under different CoT conditions, promoting answer-supportive reasoning chain alignment. To further improve optimization, we introduce a reasoning-enhanced preference data generation strategy that employs Monte Carlo Tree Search to discover visually grounded and logically consistent CoTs as positive samples, and attention-guided CoT token pruning to construct negative ones. Extensive experiments across various models and benchmarks show that RC-DPO effectively mitigates hallucinations and improves the reliability of the multimodal reasoning process.

cs.AI↗
arXiv2026

TCAP: Tri-Component Attention Profiling for Unsupervised Backdoor Detection in MLLM Fine-Tuning

Fine-Tuning-as-a-Service (FTaaS) facilitates the customization of Multimodal Large Language Models (MLLMs) but introduces critical backdoor risks via poisoned data. Existing defenses either rely on supervised signals or fail to generalize across diverse trigger types and modalities. In this work, we uncover a universal backdoor fingerprint-attention allocation divergence-where poisoned samples disrupt the balanced attention distribution across three functional components: system instructions, vision inputs, and user textual queries, regardless of trigger morphology. Motivated by this insight, we propose Tri-Component Attention Profiling (TCAP), an unsupervised defense framework to filter backdoor samples. TCAP decomposes cross-modal attention maps into the three components, identifies trigger-responsive attention heads via Gaussian Mixture Model (GMM) statistical profiling, and isolates poisoned samples through EM-based vote aggregation. Extensive experiments across diverse MLLM architectures and attack methods demonstrate that TCAP achieves consistently strong performance, establishing it as a robust and practical backdoor defense in MLLMs.

cs.AI↗
arXiv2026

Prompt2Fingerprint: Plug-and-Play LLM Fingerprinting via Text-to-Weight Generation

The widespread deployment and redistribution of large language models (LLMs) have made model provenance tracking a critical challenge. While existing LLM fingerprinting methods, particularly active approaches that embed identity signals via fine-tuning, achieve high accuracy and robustness, they suffer from significant scalability bottlenecks. These methods typically treat fingerprint injection as an independent, one-off optimization task rather than a reusable capability, necessitating separate, resource-intensive training for every new identity. This incurs prohibitive computational costs and deployment delays. To address this, we propose Prompt2Fingerprint (P2F), the first framework that reformulates fingerprinting as a conditional parameter generation task. By leveraging a specialized generator, P2F maps textual descriptions directly to low-rank parameter increments in a single forward pass, enabling plug-and-play LLM fingerprint injection without further model retraining. Our experiments demonstrate that P2F maintains high fingerprint accuracy, harmlessness, and robustness while significantly reducing computational overhead, offering a scalable and instant solution for LLM ownership management.

cs.CR↗
arXiv2026

Mistletoe: Stealthy Acceleration-Collapse Attacks on Speculative Decoding

Speculative decoding has become a widely adopted technique for accelerating large language model (LLM) inference by drafting multiple candidate tokens and verifying them with a target model in parallel. Its efficiency, however, critically depends on the average accepted length $τ$, i.e., how many draft tokens survive each verification step. In this work, we identify a new mechanism-level vulnerability in model-based speculative decoding: the drafter is trained to approximate the target model distribution, but this approximation is inevitably imperfect. Such a drafter-target mismatch creates a hidden attack surface where small perturbations can preserve the target model's visible behavior while substantially reducing draft-token acceptability. We propose Mistletoe, a stealthy acceleration-collapse attack against speculative decoding. Mistletoe directly targets the acceptance mechanism of speculative decoding. It jointly optimizes a degradation objective that decreases drafter-target agreement and a semantic-preservation objective that constrains the target model's output distribution. To resolve the conflict between these objectives, we introduce a null-space projection mechanism, where degradation gradients are projected away from the local semantic-preserving direction, suppressing draft acceptance while minimizing semantic drift. Experiments on various speculative decoding systems show that Mistletoe substantially reduces average accepted length $τ$, collapses speedup, and lowers averaged token throughput, while preserving output quality and perplexity. Our work highlights that speculative decoding introduces a mechanism-level attack surface beyond existing output robustness, calling for more robust designs of LLM acceleration systems.

cs.CL↗
arXiv2026

On transposed Poisson conformal superalgebras

We introduce and study transposed Poisson conformal superalgebras, the $\mathbb Z_2$-graded conformal analogues of transposed Poisson algebras, as well as their noncommutative variants. We derive a family of identities forced by the transposed conformal super-Leibniz rule and prove that the tensor product over $\mathbb C[\partial]$ of two such superalgebras again carries a natural transposed Poisson conformal superalgebra structure. Moreover, we display a close relationship between transposed Poisson conformal superalgebras and Hom-Lie conformal superalgebras, and give the compatibility conditions between a Poisson conformal superalgebra and a transposed Poisson conformal superalgebra. In addition, several constructions are obtained from modified Lie conformal brackets and from Novikov-Poisson, pre-Lie commutative, differential Novikov-Poisson, and pre-Lie Poisson conformal superalgebras. Finally, using the known classification of Lie conformal superalgebras of rank (1+1), we determine all compatible transposed Poisson conformal superalgebra structures on such superalgebras.

math.RA↗
arXiv2026

Overcoming noise-agility trade-off in integrated lasers for precision sensing

Lasers that combine narrow linewidths with rapid tunability are critical for applications such as coherent optical ranging, distributed fiber-optic sensing, and precision spectroscopy. Despite significant progress in integrated laser technologies, the concurrent realization of low phase noise and frequency agility on a single integrated platform remains challenging owing to a fundamental architectural trade-off: conventional integrated laser designs typically suppress phase noise via high-$Q$ resonators, yet the extended photon lifetimes inherent to such resonators intrinsically constrain tuning speed. Here, we address this noise-agility trade-off by introducing a laser architecture that achieves ultralow phase noise and ultrafast tunability simultaneously. Rather than relying on ultrahigh-$Q$ resonators for self-injection locking, our design employs strong synthetic feedback within a Pockels-tunable, resonator-enhanced distributed Bragg reflector to suppress phase noise. As a proof of concept, we demonstrate a hybrid integrated laser with a short-term linewidth of 29 Hz, realized using a lithium niobate external cavity with a loaded $Q$ of only 0.62 million. The adoption of a moderate resonator $Q$ relaxes the photon-lifetime constraint on tuning speed, enabling sub-exahertz-per-second tuning rates and a chirp nonlinearity as low as 0.14%. Leveraging this laser, we implement a frequency-modulated continuous-wave LiDAR system that achieves a relative ranging precision of $1.7 \times 10^{-4}$ at a measurement rate of $1\,\text{MSa s}^{-1}$, without requiring complex chirp linearization techniques. We further demonstrate fiber-optic acoustic sensing capable of detecting sub-$με$ dynamic strain, underscoring the platform's versatility for high-speed precision optical measurements. Our work provides a route toward cost-effective yet high-performance sensing and metrology systems.

physics.optics↗
arXiv2026

Generative Long-term User Interest Modeling for Click-Through Rate Prediction

Modeling long-term user interests with massive historical user behaviors enhances click-through rate (CTR) prediction performance in advertising and recommendation systems. Typically, a two-stage framework is widely adopted, where a general search unit (GSU) first retrieves top-$k$ relevant behaviors towards the target item, and an exact search unit (ESU) generates interest features via tailored attention. However, current target-centered GSU would ignore other latent user interests, leading to incomplete and biased interest features. Additionally, the matching-based retrieval process in GSUs depends on the pairwise similarity score between target item and each historical behavior, which not only becomes time-consuming for online services as user behaviors continue to grow, but also overlooks the interaction information among user behaviors. To combat these problems, we propose a \textbf{Gen}erative \textbf{L}ong-term user \textbf{I}nterest model named GenLI for CTR prediction. GenLI consists of an interest generation module (IGM), a behavior retrieval module (BRM), and an interest fusion module (IFM). The IGM generates multiple interest distributions to indicate different aspects of real-time user interests, which is target-independent and incorporates interaction information among behaviors, ensuring complete and diverse interest features. The BRM selects related behaviors via a simple lookup operation, reducing the time complexity for weighting each behavior to $O(1)$. Finally, the IFM uses delicate gating mechanisms to generate interest features. Based on the generation process, GenLI improves the diversity of user interests and avoids complex matching-based behavioral retrieval, achieving a better balance between accuracy and efficiency for CTR prediction.

cs.IR↗
arXiv2026

Sustainable Intelligence for the Wild: Democratizing Ecological Monitoring via Knowledge-Adaptive Edge Expert Agents

Rapid biodiversity loss underscore the urgency of effective monitoring, yet manual surveys remain resource-intensive. While on-device AI offers a scalable alternative, its performance in the wild is often challenged by environmental variability. Current methods rely heavily on cloud resource, which requires continuous uploading of field data for model retraining. This approach is unsuitable for remote deployments because it consumes limited power and network connectivity. To address these constraints, this research proposes a shift from model adaptation to knowledge adaptation. We introduce an architecture that separates visual perception from reasoning, combining a visual encoder with a dynamic knowledge base. We uses an explicit knowledge base to replace implicitly encoding expert knowledge into model parameters. This method also supports knowledge sustainability by preserving expert insights in a structured form. Through cross-disciplinary collaboration with biologists and Indigenous communities, this work advances ethical AI co-development, fostering responsible and culturally informed ecosystem management.

cs.AI↗