arXiv subjects

Ming Lu

Publications and source records attributed to Ming Lu.

At least 19 recordsLinked to original sources

arXiv2026

SteerVTE: Seamless Video Text Editing with Style and Glyph Control

Visual text editing aims to precisely modify text in images and videos while preserving stylistic consistency and visual realism. Despite significant advances in the image domain, video text editing remains largely unexplored: it is a localized task demanding stroke-level precision within small text regions, which compounds the challenges of cross-frame accuracy, temporal coherence, and stylistic fidelity. We introduce SteerVTE, a unified framework that steers a frozen video diffusion model to perform precise Video Text Editing through style and glyph control. Built on a frozen diffusion transformer, SteerVTE attaches a lightweight text context adapter with two complementary modules: a style encoder capturing the original text's visual attributes, and dual-granularity glyph encoders encoding the target text at both the line and character levels. To overcome the inherently weak text rendering priors of video foundation models, we further propose a glyph-aware spatial-focal loss and a three-stage progressive training curriculum that scales from image to video data. To support large-scale training, we also develop an automatic synthesis pipeline and construct SteerVTE-1M, a dataset of one million triplets spanning diverse scenes, fonts, and stylistic effects. Extensive experiments demonstrate that SteerVTE substantially outperforms existing video editing baselines across text accuracy, style consistency, and temporal coherence. Our project page is available at https://zengkaiya.github.io/SteerVTE/.

cs.CV↗

arXiv2026

EGGPlacer: Energy-Guided Generative Chip Placement with Diffusion Models

Chip placement strongly affects routed wirelength and thermal behavior, yet these downstream metrics are difficult to evaluate during macro placement. Learning-based macro placers commonly optimize the macro-only half-perimeter wirelength (HPWL), denoted mHPWL, which ignores standard cell connectivity and spatial demand. In contrast, analytical mixed-size placers optimize differentiable full netlist wirelength and density objectives but are typically unaware of thermal effects. We propose EGGPlacer, an energy-guided diffusion framework that incorporates analytical placement feedback and thermal feedback into macro placement generation. An analytical placer acts as an online physical response model, exposing the standard cell distribution and a full netlist wirelength proxy induced by each intermediate macro placement, while a differentiable thermal model provides temperature feedback. These signals are formulated as composable energies and injected throughout reverse diffusion without retraining the underlying generative model. Experiments on public placement benchmarks show that EGGPlacer achieves competitive mixed-size HPWL relative to strong analytical and learning-based macro placers. In the end-to-end evaluation, EGGPlacer also obtains the lowest average routed wirelength and peak temperature among the evaluated methods. Ablation studies further demonstrate that analytical and thermal guidance provide distinct and complementary benefits across wirelength proxies, routed wirelength, and thermal objectives.

cs.AR↗

arXiv2026

Drinfeld presentation of affine iquantum groups via iHopf algebras

Affine quantum groups $\widetilde{\mathbf{U}}$ and affine iquantum groups $\widetilde{\mathbf {U}}^\imath$ admit two complementary descriptions: a Serre-type presentation and a Drinfeld (current) presentation. While iquantum groups $\widetilde{\mathbf {U}}^\imath$ are typically defined via the Serre presentation, their Drinfeld presentations are substantially more subtle and less well understood. In this paper, we give a conceptual derivation of the Drinfeld presentation of $\widetilde{\mathbf {U}}^\imath$ starting directly from the Drinfeld presentation of $\widetilde{\mathbf {U}}$, working within the framework of iHopf algebras. This approach leads naturally to the definition of iquantum affinization associated with arbitrary Kac-Moody algebras $\mathfrak{g}$. We further show that, in this general setting, these iquantum affinizations can be realized as coideal subalgebras of quantum affinizations with respect to the Drinfeld coproduct. Finally, in the affine case, we describe the imaginary root vectors $Θ_{i,r}$ of $\widetilde{\mathbf {U}}^\imath$ explicitly in terms of the root vectors $ψ^\pm_{i,r}$ of $\widetilde{\mathbf {U}}$, thereby extending the results of Li and Przeździecki for certain affine types of $\widetilde{\mathbf {U}}^\imath$.

math.QA↗

arXiv2026

MASC: Metal-Aware Sampling and Correction via Reinforcement Learning for Accelerated MRI

Metal implants in MRI cause severe artifacts that degrade image quality and hinder clinical diagnosis. Traditional approaches address metal artifact reduction (MAR) and accelerated MRI acquisition as separate problems. We propose MASC, a unified reinforcement learning framework that jointly optimizes metal-aware k-space sampling and artifact correction for accelerated MRI. To enable supervised training, we construct a paired MRI dataset using physics-based simulation, generating k-space data and reconstructions for phantoms with and without metal implants. This paired dataset provides simulated 3D MRI scans with and without metal implants, where each metal-corrupted sample has an exactly matched clean reference, enabling direct supervision for both artifact reduction and acquisition policy learning. We formulate active MRI acquisition as a sequential decision-making problem, where an artifact-aware Proximal Policy Optimization (PPO) agent learns to select k-space phase-encoding lines under a limited acquisition budget. The agent operates on undersampled reconstructions processed through a U-Net-based MAR network, learning patterns that maximize reconstruction quality. We further propose an end-to-end training scheme where the acquisition policy learns to select k-space lines that best support artifact removal while the MAR network simultaneously adapts to the resulting undersampling patterns. Experiments demonstrate that MASC's learned policies outperform conventional sampling strategies, and end-to-end training improves performance compared to using a frozen pre-trained MAR network, validating the benefit of joint optimization. Cross-dataset experiments on FastMRI with physics-based artifact simulation further confirm generalization to realistic clinical MRI data. The code and models of MASC have been made publicly available: https://github.com/hrlblab/masc

cs.CV↗

arXiv2026

End-to-End Learned Image Coding: From Rate-Distortion Optimization to Practical Deployment

End-to-end learned image coding (LIC) has achieved substantial improvements in rate--distortion (R--D) performance, yet practical deployment requires addressing a broader set of system-level constraints. This article provides a deployment-oriented review of LIC, with particular attention to the transition from high-performance neural compression models to practical codecs. We first summarize the basic end-to-end coding framework, including learned transforms, quantization, entropy modeling, and R--D optimization. We then review practical extensions that are increasingly important for deployment, including variable-rate coding and rate control, integer-precision inference and cross-platform consistency, robustness and communication resilience, lightweight and hardware-aware implementation, and standardization and interoperability. To study these issues under a common setting, we further introduce TinyLIC as an open benchmark and reproducible case study for rate--distortion--complexity analysis. Experimental results illustrate the trade-offs among compression efficiency, computational complexity, numerical consistency, and robustness. In particular, TinyLIC with approximately 10 KMACs/pixel decoding complexity substantially outperforms the H.265/HEVC image-profile anchor on Kodak, while the 50 KMACs/pixel configuration achieves performance comparable to the H.266/VVC image-profile anchor on several test sets. The review highlights practical constraints and design trade-offs that remain central to the deployment and interoperability of learned image codecs. Materials are accessible at https://njuvision.github.io/TinyLIC.

eess.IV↗

arXiv2026

MMG-Vid: Maximizing Marginal Gains at Segment-level and Token-level for Efficient Video LLMs

Video Large Language Models (VLLMs) excel in video understanding, but their excessive visual tokens pose a significant computational challenge for real-world applications. Current methods aim to enhance inference efficiency by visual token pruning. However, they do not consider the dynamic characteristics and temporal dependencies of video frames, as they perceive video understanding as a multi-frame task. To address these challenges, we propose MMG-Vid, a novel training-free visual token pruning framework that removes redundancy by Maximizing Marginal Gains at both segment-level and token-level. Specifically, we first divide the video into segments based on frame similarity, and then dynamically allocate the token budget for each segment to maximize the marginal gain of each segment. Subsequently, we propose a temporal-guided DPC algorithm that jointly models inter-frame uniqueness and intra-frame diversity, thereby maximizing the marginal gain of each token. By combining both stages, MMG-Vid can maximize the utilization of the limited token budget, significantly improving efficiency while maintaining strong performance. Extensive experiments demonstrate that MMG-Vid can maintain over 99.5% of the original performance, while effectively reducing 75% visual tokens and accelerating the prefilling stage by 3.9x on LLaVA-OneVision-7B. Code is available at https://github.com/ylnxxts/MMG-Vid.

cs.CV↗

arXiv2026

RollPlace: Improving Macro Placement via Monte Carlo Rollout Search

The application of Reinforcement Learning (RL) in Electronic Design Automation (EDA), particularly for chip placement, has attracted considerable attention in recent years. While existing machine learning (ML)-based approaches have achieved notable progress, they predominantly focus on generating optimal layouts in a single attempt, often producing solutions that require subsequent refinement. To address this limitation, we propose RollPlace, a novel and generalized macro placement framework. RollPlace adopts a two-stage optimization strategy: generating initial placement solutions via machine learning methods or heuristic-based strategies, and refining these layouts efficiently by adjusting specific macros derived from the initial stage. This strategy circumvents the sequential generation constraints inherent in traditional RL-based placement methods. Furthermore, RollPlace seamlessly integrates Monte Carlo Tree Search (MCTS) to balance exploration and exploitation, and employs a rollout mechanism for efficient local search. Extensive experiments on the ISPD 2005 benchmark demonstrate that RollPlace outperforms state-of-the-art methods. Additionally, end-to-end experimental results based on OpenROAD across 19 benchmarks show that RollPlace excels in multiple metrics. The proposed framework offers a robust and scalable solution for addressing the growing complexity of modern chip design challenges.

cs.AI↗

arXiv2026

Dynamical transition in non-Hermitian Chern insulator

We unveil a peculiar dynamical transition for the propagation of wave packets in non-Hermitian Chern insulators, where the evolution of the topological wave packets at the edge is not solely determined by the topological Chern number. Unlike the Hermitian Chern insulator, where a wave packet initiated at the edge propagates along the system boundary, here it may instead penetrate into the bulk. This behavior is attributed to the competition between the localization induced by conventional topology and the non-Hermitian skin effect. Specifically, when the former dominant, the wave packet will evolve along the boundary; otherwise, it will spread into the bulk. These features demonstrate that while the generalized-Brillouin zone framework reliably predicts topological phase transitions, it does not on its own specify the dynamical transitions.

cond-mat.mes-hall↗

arXiv2026

OpenMASC: An Open-Source Pipeline for Cross-Trajectory Metal-Aware Sampling and Correction in Accelerated MRI

Metal implants corrupt MRI measurements throughout $k$-space, yet existing accelerated MRI methods assume clean data and most metal artifact reduction approaches assume fully sampled acquisitions. No public dataset provides paired $k$-space and images with and without metal for the same anatomy, and no framework jointly addresses artifact-aware acquisition and reconstruction across sampling trajectories. We present OpenMASC, an open-source pipeline covering the full workflow from data generation to deployment. A physics-based data generation module converts public CT volumes into paired clean and metal-corrupted MRI data in both Cartesian and radial formats. MA-VarNet, an unrolled reconstruction network with a per-cascade DC Rectifier, corrects artifacts that data-consistency steps reintroduce from corrupted measurements. A reinforcement learning agent actively selects $k$-space readouts and co-trains with the reconstruction network through a decoupled three-stage procedure. The framework is trajectory-agnostic except for the data-consistency operator, supporting both Cartesian and radial acquisition without architectural changes. Experiments on two datasets at $4\times$ and $8\times$ acceleration demonstrate consistent improvements over conventional and learned baselines on both trajectories.

cs.CV↗

arXiv2026

Representation-tame Geiß-Leclerc-Schröer algebras and a revised GLS conjecture on root systems

Using Galois covering theory and equivariant techniques, we classify all connected representation-tame Geiß--Leclerc--Schröer (GLS) algebras in terms of their defining triples $(C,D,Ω)$. We then study the GLS algebras $H(\widetilde{CD}_n)$ with minimal symmetrizers, where $n\geq 2$ and $\widetilde{CD}_2=\widetilde{B}_2$. By realizing these algebras as basic algebras of $\mathbb{Z}_2$-skew group algebras of the string algebras $H(\widetilde{C}_{2n-2})$, we introduce extended strings and extended bands to parameterize the connected components of the Auslander--Reiten quivers of $H(\widetilde{CD}_n)$ and determine their shapes. We further classify the indecomposable $τ$-locally free modules over representation-tame GLS algebras of affine type and show that their rank vectors form precisely the set of positive roots together with explicitly described non-root vectors in the positive cone of the root lattice. This yields a precise revision of the GLS conjecture for representation-tame GLS algebras of affine type.

math.RT↗

arXiv2026

Dynamic Thermal Gaussians: Multimodal 4D Gaussian Splatting

Thermography plays a vital role in military and broader thermal analysis applications. Recent progress in 3D thermal reconstruction has extended temperature analysis from 2D to 3D space, yet most existing works assume static temperature distributions, neglecting the temporal dynamics of heat transfer in real-world environments. To address this limitation, we propose the first dynamic RGB-Thermal reconstruction framework for complex scenes. Our method jointly models RGB appearance, thermal observations, and scene geometry as they change over time. Specifically, we introduce a multimodal dynamic scene representation that anchors both the color and thermal modalities to a shared geometric substrate, ensuring their consistency under spatiotemporal deformations. We further design multimodal embeddings to enhance the motion expressiveness for each modality, and propose a multimodal routing mechanism that retains a unified set of shared multimodal Gaussians as the geometric backbone while adaptively spawning modality-specific Gaussians to strengthen the representational capacity in detail-rich regions of each individual modality. In addition, we contribute a novel benchmark dataset featuring high-frequency temperature variations to facilitate the evaluation of 4D reconstruction. Extensive experiments demonstrate that our method achieves high-fidelity spatiotemporal reconstruction of both appearance and temperature. Our code and dataset are available at: https://github.com/LinLif1869/DTG.

cs.CV↗

arXiv2026

Non-Hermitian Topology from Edge Transport in Hermitian Quantum Anomalous Hall Systems

Non-Hermitian physics, known for exotic phenomena like exceptional points and the skin effect, has been most prominently realized in engineered systems relying on controlled gain and loss. Here we show that it can also arise naturally as an intrinsic transport response of a globally Hermitian quantum anomalous Hall system, without the need for external non-Hermitian engineering. We show that the interplay between unidirectional chiral edge modes and diffusive normal edge modes induces intrinsic non-reciprocal transport described by a continuum Hatano-Nelson model. Consequently, the non-Hermitian skin effect is encoded directly in experimentally accessible Hall-bar observables: the electrochemical potential and local heat dissipation acquire chirality-dependent exponential spatial profiles, while the longitudinal conductance decays exponentially with system size and the Hall conductance remains quantized. Using Landauer--B{"u}ttiker simulations, we confirm these transport signatures and identify magnetic topological insulators as a realistic platform for an intrinsic non-Hermitian transport response. Our results bridge non-Hermitian topology with mesoscopic transport, opening a pathway toward non-Hermitian topological devices in solid-state systems.

cond-mat.mes-hall↗

arXiv2026

ReX-Shot: Single-Image Rephotography via Geometry- and Camera-Grounded Generation

Single-image rephotography aims to synthesize new shots of a scene from a single reference image with specified viewpoints, focal lengths, and photographic effects, which are intrinsically coupled in imaging. Existing methods typically treat these factors separately and struggle under joint control: novel-view synthesis may introduce geometric distortions under focal-length changes, while super-resolution and instruction-guided editing remain confined to 2D and cannot reliably extend detail restoration or appearance control to novel viewpoints. We attribute these limitations to imperfect single-image 3D reconstruction and the sampling limit of continuous focal-length enlargement. To reduce projection bias from geometric errors, we use implicitly transformed foundation-model features for robust target-view guidance. We further formulate focal-length enlargement as a geometry-guided super-resolution problem and exploit generative detail priors to recover details lost during sparse 3D resampling. Built on this 3D-aware generative backbone, we lift photographic-effect control from 2D filtering to 3D-aware appearance editing, preserving content consistency across viewpoints and focal lengths. These components form ReX-Shot, a geometry- and camera-grounded generative framework for single-image rephotography. To our knowledge, ReX-Shot is the first unified framework to jointly control viewpoint, focal length, and parameterized photographic effects from a single image. Experiments show that ReX-Shot outperforms representative baselines across all three controls while enabling near-real-time interactive rephotography.

cs.CV↗

arXiv2026

VCU-Bridge: Hierarchical Visual Connotation Understanding via Semantic Bridging

While Multimodal Large Language Models (MLLMs) excel on benchmarks, their processing paradigm differs from the human ability to integrate visual information. Unlike humans who naturally bridge details and high-level concepts, models tend to treat these elements in isolation. Prevailing evaluation protocols often decouple low-level perception from high-level reasoning, overlooking their semantic and causal dependencies, which yields non-diagnostic results and obscures performance bottlenecks. We present VCU-Bridge, a framework that operationalizes a human-like hierarchy of visual connotation understanding: multi-level reasoning that advances from foundational perception through semantic bridging to abstract connotation, with an explicit evidence-to-inference trace from concrete cues to abstract conclusions. Building on this framework, we construct HVCU-Bench, a benchmark for hierarchical visual connotation understanding with explicit, level-wise diagnostics. Comprehensive experiments demonstrate a consistent decline in performance as reasoning progresses to higher levels. We further develop a data generation pipeline for instruction tuning guided by Monte Carlo Tree Search (MCTS) and show that strengthening low-level capabilities yields measurable gains at higher levels. Interestingly, it not only improves on HVCU-Bench but also brings benefits on general benchmarks (average +2.53%), especially with substantial gains on MMStar (+7.26%), demonstrating the significance of the hierarchical thinking pattern and its effectiveness in enhancing MLLM capabilities. The project page is at https://vcu-bridge.github.io .

cs.CV↗

arXiv2026

GIM and Elliptic Lie algebras via Ringel--Hall Lie algebras

For any symmetrizable generalized intersection matrix (GIM) $C$, we construct an acyclic valued quiver $(Q,\mathbf{d})$ endowed with an involution $θ$. Let $\mathcal{D}$ be the bounded derived category of finite-dimensional representations of $(Q,\mathbf{d})$, and let $Σ$ stand for the suspension functor of $\mathcal{D}$. We show that the orbit category $\mathcal{D}/(θ\circΣ)$ carries a canonical triangulated structure and is $2$-periodic. Applying Peng--Xiao's construction to this orbit category, we prove that the GIM algebra $\operatorname{gim}(C)$ is isomorphic to the integral Ringel--Hall Lie algebra associated with $\mathcal{D}/(θ\circΣ)$. As a further application of the above machinery, we investigate elliptic Lie algebras of types $D_4^{(1,1)}$, $E_6^{(1,1)}$, $E_7^{(1,1)}$ and $E_8^{(1,1)}$. For each elliptic Dynkin diagram, we define a finite-dimensional algebra $A$ by taking an appropriate quotient of the acyclic quiver $Q$ attached to the GIM matrix $C$. From the resulting $2$-periodic triangulated categories, we build the corresponding Ringel--Hall Lie algebras, and establish a surjective Lie algebra homomorphism from each elliptic Lie algebra to its integral Ringel--Hall counterpart. This map is conjectured to be injective, and its injectivity on real root spaces is confirmed.

math.RT↗

arXiv2026

iQuantum groups and iHopf algebras I: foundation

We introduce the notion of iHopf algebra, a new associative algebra structure defined on a Hopf algebra equipped with a Hopf pairing. The iHopf algebra on a Borel quantum group endowed with a $τ$-twisted Hopf pairing is shown to be a quasi-split universal iquantum group. In particular, the Drinfeld double quantum group is realized as the iHopf algebra on the double Borel. This iHopf approach allows us to develop connections between Lusztig's braid group action and ibraid group action. It will further lead to the construction of dual canonical basis in a sequel.

math.QA↗

arXiv2026

ZoomV: Temporal Zoom-in for Efficient Long Video Understanding

Long video understanding poses a fundamental challenge for large video-language models (LVLMs) due to the overwhelming number of frames and the risk of losing essential context through naive downsampling. Inspired by the way humans watch videos on mobile phones, constantly zooming in on frames of interest, we propose ZoomV, a query-aware temporal zoom-in framework designed for efficient and accurate long video understanding. Specifically, ZoomV operates in three stages: (1) Temporal interests grounding: guided by the query, ZoomV retrieves relevant events and their associated temporal windows as candidates. (2) Event interests spotlighting: within pools of candidate windows, each window is scored through the model itself reflection and filtered accordingly, where higher-confidence windows are more representative. (3) Compact representation: the selected events are encoded and temporally downsampled to preserve critical semantics while significantly reducing redundancy. Extensive experiments demonstrate that ZoomV substantially outperforms prior video agent approaches. On temporal grounding, ZoomV unlocks the latent capability of LVLMs, achieving an 11.8% mIoU gain on Charades-STA. Remarkably, ZoomV further boosts accuracy on LVBench by 9.7%, underscoring its effectiveness on long-video benchmarks.

cs.CV↗

arXiv2026

Hadamard-Domain Model Quantization for Learned Image Coding

Uniform INT8 quantization is attractive for deploying learned image coding (LIC), but its rate--distortion (R--D) performance is often limited by heavy-tailed tensors and large inter-channel variations. Existing methods mainly adapt the quantizer through mixed precision or non-uniform codebooks. We propose Hadamard-Transform-domain Quantization (HaTQ), which uses orthogonal Hadamard reparameterization before quantization to redistribute weight and activation responses in the original domain across channels. The reparameterization preserves the original function mapping of each linear operator, while making its weights and activations more amenable to uniform INT8 quantization. HaTQ provides two complementary forms. Double-Hadamard quantization transforms both the input activations and weights, whereas weight-only Hadamard quantization transforms only the weights. This distinction is important because the constant Hadamard basis can coherently accumulate a nonzero channel mean and enlarge the activation range in sensitive layers. We identify these sensitive layers through offline profiling and assign the appropriate form to each layer without input-dependent branching. HaTQ supports both post-training quantization (PTQ) and quantization-aware training (QAT), uses uniform INT8 quantizers, and is compatible with integer-only execution. Experiments on representative LIC architectures and datasets demonstrate consistent improvements across different quantization settings. The resulting QAT models further outperform competing mixed-precision and non-uniform quantization methods. TensorRT deployment results demonstrate practical INT8 inference efficiency. The source code will be publicly released.

eess.IV↗