Searcharxiv⌕ Search

arXiv subjects

Yu Liu

Publications and source records attributed to Yu Liu.

At least 271 records · Page 15Linked to original sources
arXiv2026

Routing Matters in MoE: Scaling Diffusion Transformers with Explicit Routing Guidance

Mixture-of-Experts (MoE) has emerged as a powerful paradigm for scaling model capacity while preserving computational efficiency. Despite its notable success in large language models (LLMs), existing attempts to apply MoE to Diffusion Transformers (DiTs) have yielded limited gains. We attribute this gap to fundamental differences between language and visual tokens. Language tokens are semantically dense with pronounced inter-token variation, while visual tokens exhibit spatial redundancy and functional heterogeneity, hindering expert specialization in vision MoE. To this end, we present ProMoE, an MoE framework featuring a two-step router with explicit routing guidance that promotes expert specialization. Specifically, this guidance encourages the router to partition image tokens into conditional and unconditional sets via conditional routing according to their functional roles, and refine the assignments of conditional image tokens through prototypical routing with learnable prototypes based on semantic content. Moreover, the similarity-based expert allocation in latent space enabled by prototypical routing offers a natural mechanism for incorporating explicit semantic guidance, and we validate that such guidance is crucial for vision MoE. Building on this, we propose a routing contrastive loss that explicitly enhances the prototypical routing process, promoting intra-expert coherence and inter-expert diversity. Extensive experiments on ImageNet benchmark demonstrate that ProMoE surpasses state-of-the-art methods under both Rectified Flow and DDPM training objectives. Code is available at https://github.com/ali-vilab/ProMoE.

cs.CV↗
arXiv2026

Mechanism-Resolved PFM of Ferroionic and Ferroelectric Responses in Thickness-Gradient Hf0.5Zr0.5O2 Libraries

Resolving growth mechanisms and thickness evolution of functional properties is one of the key tasks in materials discovery and optimization involving thin-film materials, traditionally requiring significant experimental budgets. Here we introduce the combination of thickness-gradient libraries and automated scanning probe microscopy as a systematic pathway to elucidate growth modes and disentangle ferroelectric and electrochemical contributions in ferroelectric thin films. As a model system, we explore the Hf0.5Zr0.5O2 (HZO) gradient thin films grown on LaxSr1-xMnO3 (LSMO) bottom electrode thin films. Automated piezoresponse force microscopy, spectroscopy, and lithography reveals that irreversible topographic deformation arises from electrochemical activity at the LSMO surface, whereas reversible phase inversion in HZO reflects ferroelectric switching. Automated topography height-map scans are used to further quantify nucleation density, particle-size evolution, and roughness correlations across the thickness-gradient, demonstrating that improved plume stabilization during growth suppresses interfacial reactions and promotes dense, fine-grained HZO conducive to ferroelectric phase formation. This combined materials-engineering and automated-SPM framework establishes a platform for high-throughput, mechanism-resolved characterization of ferroionic and ferroelectric responses in complex oxide films.

cond-mat.mtrl-sci↗
arXiv2026

G4Splat: Geometry-Guided Gaussian Splatting with Generative Prior

Despite recent advances in leveraging generative prior from pre-trained diffusion models for 3D scene reconstruction, existing methods still face two critical limitations. First, due to the lack of reliable geometric supervision, they struggle to produce high-quality reconstructions even in observed regions, let alone in unobserved areas. Second, they lack effective mechanisms to mitigate multi-view inconsistencies in the generated images, leading to severe shape-appearance ambiguities and degraded scene geometry. In this paper, we identify accurate geometry as the fundamental prerequisite for effectively exploiting generative models to enhance 3D scene reconstruction. We first propose to leverage the prevalence of planar structures to derive accurate metric-scale depth maps, providing reliable supervision in both observed and unobserved regions. Furthermore, we incorporate this geometry guidance throughout the generative pipeline to improve visibility mask estimation, guide novel view selection, and enhance multi-view consistency when inpainting with video diffusion models, resulting in accurate and consistent scene completion. Extensive experiments on Replica, ScanNet++, DeepBlending and Mip-NeRF 360 show that our method consistently outperforms existing baselines in both geometry and appearance reconstruction, particularly for unobserved regions. Moreover, our method naturally supports single-view inputs and unposed videos, with strong generalizability in both indoor and outdoor scenarios with practical real-world applicability. The project page is available at https://dali-jack.github.io/g4splat-web/.

cs.CV↗
arXiv2026

RandSet: Randomized Corpus Reduction for Fuzzing Seed Scheduling

Seed explosion is a fundamental problem in fuzzing seed scheduling, where a fuzzer maintains a huge corpus and fails to choose promising seeds. Existing works focus on seed prioritization but still suffer from seed explosion since corpus size remains huge. We tackle this from a new perspective: corpus reduction, i.e., computing a seed corpus subset. However, corpus reduction could lead to poor seed diversity and large runtime overhead. Prior techniques like cull_queue, AFL-Cmin, and MinSet suffer from poor diversity or prohibitive overhead, making them unsuitable for high-frequency seed scheduling. We propose RandSet, a novel randomized corpus reduction technique that reduces corpus size and yields diverse seed selection simultaneously with minimal overhead. Our key insight is introducing randomness into corpus reduction to enjoy two benefits of a randomized algorithm: randomized output (diverse seed selection) and low runtime cost. Specifically, we formulate corpus reduction as a set cover problem and compute a randomized subset covering all features of the entire corpus. We then schedule seeds from this small, randomized subset rather than the entire corpus, effectively mitigating seed explosion. We implement RandSet on three popular fuzzers: AFL++, LibAFL, and Centipede, and evaluate it on standalone programs, FuzzBench, and Magma. Results show RandSet achieves significantly more diverse seed selection than other reduction techniques, with average subset ratios of 4.03% and 5.99% on standalone and FuzzBench programs. RandSet achieves a 16.58% coverage gain on standalone programs and up to 3.57% on FuzzBench in AFL++, triggers up to 7 more ground-truth bugs than the state-of-the-art on Magma, while introducing only 1.17%-3.93% overhead.

cs.SE↗
arXiv2026

DenseGRPO: From Sparse to Dense Reward for Flow Matching Model Alignment

Recent GRPO-based approaches built on flow matching models have shown remarkable improvements in human preference alignment for text-to-image generation. Nevertheless, they still suffer from the sparse reward problem: the terminal reward of the entire denoising trajectory is applied to all intermediate steps, resulting in a mismatch between the global feedback signals and the exact fine-grained contributions at intermediate denoising steps. To address this issue, we introduce \textbf{DenseGRPO}, a novel framework that aligns human preference with dense rewards, which evaluates the fine-grained contribution of each denoising step. Specifically, our approach includes two key components: (1) we propose to predict the step-wise reward gain as dense reward of each denoising step, which applies a reward model on the intermediate clean images via an ODE-based approach. This manner ensures an alignment between feedback signals and the contributions of individual steps, facilitating effective training; and (2) based on the estimated dense rewards, a mismatch drawback between the uniform exploration setting and the time-varying noise intensity in existing GRPO-based methods is revealed, leading to an inappropriate exploration space. Thus, we propose a reward-aware scheme to calibrate the exploration space by adaptively adjusting a timestep-specific stochasticity injection in the SDE sampler, ensuring a suitable exploration space at all timesteps. Extensive experiments on multiple standard benchmarks demonstrate the effectiveness of the proposed DenseGRPO and highlight the critical role of the valid dense rewards in flow matching model alignment.

cs.CV↗
arXiv2026

BioX-Bridge: Model Bridging for Unsupervised Cross-Modal Knowledge Transfer across Biosignals

Biosignals offer valuable insights into the physiological states of the human body. Although biosignal modalities differ in functionality, signal fidelity, sensor comfort, and cost, they are often intercorrelated, reflecting the holistic and interconnected nature of human physiology. This opens up the possibility of performing the same tasks using alternative biosignal modalities, thereby improving the accessibility, usability, and adaptability of health monitoring systems. However, the limited availability of large labeled datasets presents challenges for training models tailored to specific tasks and modalities of interest. Unsupervised cross-modal knowledge transfer offers a promising solution by leveraging knowledge from an existing modality to support model training for a new modality. Existing methods are typically based on knowledge distillation, which requires running a teacher model alongside student model training, resulting in high computational and memory overhead. This challenge is further exacerbated by the recent development of foundation models that demonstrate superior performance and generalization across tasks at the cost of large model sizes. To this end, we explore a new framework for unsupervised cross-modal knowledge transfer of biosignals by training a lightweight bridge network to align the intermediate representations and enable information flow between foundation models and across modalities. Specifically, we introduce an efficient strategy for selecting alignment positions where the bridge should be constructed, along with a flexible prototype network as the bridge architecture. Extensive experiments across multiple biosignal modalities, tasks, and datasets show that BioX-Bridge reduces the number of trainable parameters by 88--99\% while maintaining or even improving transfer performance compared to state-of-the-art methods.

cs.AI↗
arXiv2026

Phonon frequency comb close to an isolated Einstein mode in InSiTe3

The emergence of phonon frequency combs exemplifies a rare and intriguing phenomenon in quantum solids. Materials with distinctive phonon band structures are especially promising for hosting such states, as their vibrational dispersion landscape across the Brillouin zone can facilitate the formation of long-lived, collective lattice excitations. In the layered Van der Waals compound InSiTe$_3$, polarization-resolved Raman spectroscopy reveals a pronounced anharmonicity in symmetry-predicted modes and the formation of a self-organized frequency domain structure (coherent-like state), in the range of a localized highenergy A$_{1g}$ phonon mode near 500 cm$^{-1}$. This strong phonon-phonon coupling manifests itself as an anomalous temperature dependence around 200 K, coinciding with the appearance of higher-order excitations within the phonon density of states gap. These findings position InSiTe$_3$ as an unconventional platform where intrinsic highly structured phonon spectral correlations and unusually strong anharmonic effects coexist, opening new avenues for exploring emergent vibrational phenomena in low-dimensional materials.

cond-mat.mtrl-sci↗
arXiv2026

Distilling human mobility models with symbolic regression

Human mobility is a fundamental aspect of social behavior, with broad applications in transportation, urban planning, and epidemic modeling. Represented by the gravity model and the radiation model, established analytical models for mobility phenomena are often discovered by analogy to physical processes. Such discoveries can be challenging and rely on intuition, while the potential of emerging social observation data in model discovery is largely unexploited. Here, we propose a systematic approach that leverages symbolic regression to automatically discover interpretable models from human mobility data. Our approach finds several well-known formulas, such as the distance decay effect and classical gravity models, as well as previously unknown ones, such as an exponential-power-law decay that can be explained by the maximum entropy principle. By relaxing the constraints on the complexity of model expressions, we further show how key variables of human mobility are progressively incorporated into the model, making this framework a powerful tool for revealing the underlying mathematical structures of complex social phenomena directly from observational data.

physics.soc-ph↗
arXiv2026

Smartphone-based iris recognition through high-quality visible-spectrum iris image capture.V2

Smartphone-based iris recognition in the visible spectrum (VIS) remains difficult due to illumination variability, pigmentation differences, and the absence of standardized capture controls. This work presents a compact end-to-end pipeline that enforces ISO/IEC 29794-6 quality compliance at acquisition and demonstrates that accurate VIS iris recognition is feasible on commodity devices. Using a custom Android application performing real-time framing, sharpness evaluation, and feedback, we introduce the CUVIRIS dataset of 752 compliant images from 47 subjects. A lightweight MobileNetV3-based multi-task segmentation network (LightIrisNet) is developed for efficient on-device processing, and a transformer matcher (IrisFormer) is adapted to the VIS domain. Under a standardized protocol and comparative benchmarking against prior CNN baselines, OSIRIS attains a TAR of 97.9% at FAR=0.01 (EER=0.76%), while IrisFormer, trained only on UBIRIS.v2, achieves an EER of 0.057% on CUVIRIS. The acquisition app, trained models, and a public subset of the dataset are released to support reproducibility. These results confirm that standardized capture and VIS-adapted lightweight models enable accurate and practical iris recognition on smartphones.

eess.IV↗
arXiv2026

DM0: An Embodied-Native Vision-Language-Action Model towards Physical AI

Moving beyond the traditional paradigm of adapting internet-pretrained models to physical tasks, we present DM0, an Embodied-Native Vision-Language-Action (VLA) framework designed for Physical AI. Unlike approaches that treat physical grounding as a fine-tuning afterthought, DM0 unifies embodied manipulation and navigation by learning from heterogeneous data sources from the onset. Our methodology follows a comprehensive three-stage pipeline: Pretraining, Mid-Training, and Post-Training. First, we conduct large-scale unified pretraining on the Vision-Language Model (VLM) using diverse corpora--seamlessly integrating web text, autonomous driving scenarios, and embodied interaction logs-to jointly acquire semantic knowledge and physical priors. Subsequently, we build a flow-matching action expert atop the VLM. To reconcile high-level reasoning with low-level control, DM0 employs a hybrid training strategy: for embodied data, gradients from the action expert are not backpropagated to the VLM to preserve generalized representations, while the VLM remains trainable on non-embodied data. Furthermore, we introduce an Embodied Spatial Scaffolding strategy to construct spatial Chain-of-Thought (CoT) reasoning, effectively constraining the action solution space. Experiments on the RoboChallenge benchmark demonstrate that DM0 achieves state-of-the-art performance in both Specialist and Generalist settings on Table30.

cs.RO↗
arXiv2026

Towards Sequence Modeling Alignment between Tokenizer and Autoregressive Model

Autoregressive image generation aims to predict the next token based on previous ones. However, this process is challenged by the bidirectional dependencies inherent in conventional image tokenizations, which creates a fundamental misalignment with the unidirectional nature of autoregressive models. To resolve this, we introduce AliTok, a novel Aligned Tokenizer that alters the dependency structure of the token sequence. AliTok employs a bidirectional encoder constrained by a causal decoder, a design that compels the encoder to produce a token sequence with both semantic richness and forward-dependency. Furthermore, by incorporating prefix tokens and employing a two-stage tokenizer training process to enhance reconstruction performance, AliTok achieves high fidelity and predictability simultaneously. Building upon AliTok, a standard decoder-only autoregressive model with just 177M parameters achieves a gFID of 1.44 and an IS of 319.5 on ImageNet-256. Scaling to 662M, our model reaches a gFID of 1.28, surpassing the SOTA diffusion method with 10x faster sampling. On ImageNet-512, our 318M model also achieves a SOTA gFID of 1.39. Code and weights at https://github.com/ali-vilab/alitok.

cs.CV↗
arXiv2026

GSM-GS: Geometry-Constrained Single and Multi-view Gaussian Splatting for Surface Reconstruction

Recently, 3D Gaussian Splatting has emerged as a prominent research direction owing to its ultrarapid training speed and high-fidelity rendering capabilities. However, the unstructured and irregular nature of Gaussian point clouds poses challenges to reconstruction accuracy. This limitation frequently causes high-frequency detail loss in complex surface microstructures when relying solely on routine strategies. To address this limitation, we propose GSM-GS: a synergistic optimization framework integrating single-view adaptive sub-region weighting constraints and multi-view spatial structure refinement. For single-view optimization, we leverage image gradient features to partition scenes into texture-rich and texture-less sub-regions. The reconstruction quality is enhanced through adaptive filtering mechanisms guided by depth discrepancy features. This preserves high-weight regions while implementing a dual-branch constraint strategy tailored to regional texture variations, thereby improving geometric detail characterization. For multi-view optimization, we introduce a geometry-guided cross-view point cloud association method combined with a dynamic weight sampling strategy. This constructs 3D structural normal constraints across adjacent point cloud frames, effectively reinforcing multi-view consistency and reconstruction fidelity. Extensive experiments on public datasets demonstrate that our method achieves both competitive rendering quality and geometric reconstruction. See our interactive project page

cs.CV↗
arXiv2026

Dialogue Model Optimization via Agent Game and Adaptive Tree-based GRPO

Open-ended dialogue agents aim to deliver engaging, personalized interactions by adapting to users' traits, but existing methods face critical limitations: over-reliance on pre-collected user data, and short-horizon biases in reinforcement learning (RL) that neglect long-term dialogue value. To address these, we propose a novel long-horizon RL framework integrating online personalization with Adaptive Tree-based Group Relative Policy Optimization (AT-GRPO). Adopting a two-agent game paradigm, a user agent constructs dynamic environments via style mimicry (learning user-specific conversational traits) and active termination (predicting turn-level termination probabilities as immediate rewards), forming an iterative cycle that drives the dialogue agent to deepen interest exploration. AT-GRPO reinterprets dialogue trajectories as trees and introduces adaptive observation ranges. Unlike full tree expansion that incurs exponential overhead, it limits each node to aggregate rewards from a stage-aware range: larger ranges support early-stage topic exploration, while smaller ranges facilitate late-stage dialogue maintenance. This design reduces rollout budgets from exponential to polynomial in the dialogue length, while preserving long-term reward capture. Extensive experiments show our framework's superior performance, sample efficiency, and robustness.

cs.AI↗
arXiv2026

Pressure-induced superconductivity beyond magnetic quantum criticality in a Kondo ferromagnet

Quantum phase transitions are an established setting for emergent phenomena driven by strong electronic correlations, including strange metals and unconventional superconductivity. These have been explored extensively in Kondo lattice materials tuned to an antiferromagnetic quantum critical point (QCP), but superconductivity emerging near ferromagnetic quantum criticality is not yet observed, and the conditions under which it occurs in proximity to ferromagnetism are undetermined. Here, we report a new setting for superconductivity in the ferromagnetic Kondo-lattice material Ce5CoGe2, where there is a ferromagnetic ground state at ambient pressure, which evolves to antiferromagnetism under applied pressures. The antiferromagnetic transition is suppressed to a zero-temperature QCP, which is accompanied by strange-metal behavior. Superconductivity does not occur at the QCP, but instead appears at pressures beyond the magnetic instability. These findings suggest that Ce5CoGe2 represents a distinct class of correlated materials exhibiting a unique scenario for the emergence of superconductivity, likely associated with unconventional pairing mechanisms beyond spin-fluctuations.

cond-mat.supr-con↗
arXiv2026

High-Probability Heralded Entanglement via Repeated Spin-Photon Phase Encoding with Moderate Cooperativity

We propose a heralded high-probability scheme to generate remote entanglement between moderate-cooperativity spin-cavity registers with high fidelity. In conventional single-shot interfaces, limited cooperativity restricts the spin-conditional optical response and thus strongly suppresses the success probability. Our proposal instead recycles a single incident photon for repeated interactions with the spin-cavity register, such that a small spin-conditional phase shift acquired on each round trip accumulates coherently to enable remote entanglement. Moreover, the repeated scheme enables higher spin-photon encoding efficiency by using a spectral-width-scaling photon pulse with a shorter duration. We show that, for realistic imperfections and losses, this repeated phase-encoding approach produces high-fidelity entangled states with an appreciable success probability even at cooperativity $C\sim1$. Our protocol is particularly well suited to weakly coupled, cavity-based solid-state spin platforms and provides a route toward hybrid, photon-loss-tolerant distributed quantum computing.

quant-ph↗
arXiv2026

Lithium niobate quadratic integrated nonlinear photonics: enabling ultra-wide bandwidth and ultrafast photonic engines

Integrated photonic coherent light sources capable of generating emission with broad spectral coverage and ultrashort pulse durations are critical for both fundamental science and emerging technologies. In this Perspective, we start by discussing emerging quantum and classical photonic applications from the standpoint of operating wavelength and timescale, highlighting the technological gaps that persist in current integrated photonic light sources. Next, we introduce the unique properties of lithium niobate-based integrated quadratic nonlinear photonics, and discuss several promising strategies that exploit this platform to realize wavelength-tunable continuous wave light sources and broadband, ultra-short light pulse generation. We also assessed their advantages and limitations while discussing potential solutions. Finally, we outline future prospects and challenges that need to be addressed, aiming at inspiring continued research and innovation in this rapidly evolving field.

physics.optics↗
arXiv2026

Open-Text Aerial Detection: A Unified Framework For Aerial Visual Grounding And Detection

Open-Vocabulary Aerial Detection (OVAD) and Remote Sensing Visual Grounding (RSVG) have emerged as two key paradigms for aerial scene understanding. However, each paradigm suffers from inherent limitations when operating in isolation: OVAD is restricted to coarse category-level semantics, while RSVG is structurally limited to single-target localization. These limitations prevent existing methods from simultaneously supporting rich semantic understanding and multi-target detection. To address this, we propose OTA-Det, the first unified framework that bridges both paradigms into a cohesive architecture. Specifically, we introduce a task reformulation strategy that unifies task objectives and supervision mechanisms, enabling joint training across datasets from both paradigms with dense supervision signals. Furthermore, we propose a dense semantic alignment strategy that establishes explicit correspondence at multiple granularities, from holistic expressions to individual attributes, enabling fine-grained semantic understanding. To ensure real-time efficiency, OTA-Det builds upon the RT-DETR architecture, extending it from closed-set detection to open-text detection by introducing several high efficient modules, achieving state-of-the-art performance on six benchmarks spanning both OVAD and RSVG tasks while maintaining real-time inference at 34 FPS.

cs.CV↗
arXiv2026

Resource state generation for a multispin register in a hybrid matter-photon quantum information processor

Hybrid quantum architectures that integrate matter and photonic degrees of freedom present a promising pathway toward scalable, fault-tolerant quantum computing. This approach needs to combine well-established entangling operations between distant registers using photonic degrees of freedom with direct interactions between matter qubits within a solid-state register. The high-fidelity control of such a register, however, poses significant challenges. In this work, we address these challenges with pulsed control sequences which modulate all inter-spin interactions to preserve the nearest-neighbor couplings while eliminating unwanted long-range interactions. We derive pulse sequences, including broadband and selective gates, using composite pulse and shaped pulse techniques as well as optimal control methods. This ensures a general pulse sequence in the presence of spin-position bias, and robustness against static offset detunings, and Rabi frequency fluctuations of the control fields. The control techniques developed here apply well beyond the present setting to a broad range of physical platforms. We demonstrate the efficacy of our methods for the resource state generation for fusion-based quantum computing in four- and six-spin systems encoded in the electronic ground states of nitrogen-vacancy centers or other molecular solid-state qubits. We also outline other elements of the proposed architecture, highlighting its potential for advancing quantum computing technology.

quant-ph↗