arXiv subjects

Qian Zhang

Publications and source records attributed to Qian Zhang.

At least 91 records · Page 5Linked to original sources

arXiv2026

ERNIE-Image Technical Report

We introduce ERNIE-Image, an open-source text-to-image generation model built upon an 8B single-stream DiT architecture. ERNIE-Image aims to bridge the gap between current open-source models and leading closed-source systems through more effective mining of large-scale pre-training data and improved supervision quality throughout training. During pre-training, we adopt a bottom-up data construction pipeline that combines fine-grained image categorization, rich caption annotation, aesthetic assessment, and hierarchical sampling. This strategy reduces data noise while preserving long-tail concepts and detailed real-world knowledge, providing a stronger foundation for complex generation tasks. In the post-training stage, we use a top-down data construction pipeline for high-demand scenarios, diversify prompt annotations to better match real user inputs, and apply a stabilized DPO strategy to align the model with human aesthetic preferences. We further train ERNIE-Image-Turbo for efficient 8-NFE generation and propose MT-DMD to mitigate capability drift during distillation. To make the model easier to use in practical scenarios, we equip it with a lightweight Prompt Enhancer that expands concise user intents into structured visual descriptions. In addition, we develop ERNIE-Image-Aes, an industrial-grade aesthetic model, together with ERNIE-Image-Aes-1K, a human-annotated benchmark for realistic aesthetic evaluation. Extensive qualitative and quantitative experiments show that ERNIE-Image achieves leading performance among open-source models and approaches top-tier commercial models in instruction following, text rendering, and aesthetic quality. We release the trained models and aesthetic resources to facilitate further academic research and technical progress in the AIGC community.

cs.CV↗

arXiv2026

DyCoRM: Dynamic Criterion-Aware Reward Modeling for Text-to-Image Generation

With the continued advancement of text-to-image (T2I) generation, producing high-quality images is becoming increasingly attainable; consequently, user demands are shifting toward images that better satisfy their specific requirements. As reward models play an increasingly important role in assessing whether generated images align with user preference, this trend introduces an important challenge for reward modeling: rather than relying solely on static and general evaluation dimensions, reward models should account for the task-relevant and fine-grained criteria through which users assess whether generated images meet their specific requirements. To address this challenge, we propose DyCoRM, a dynamic, criterion-aware reward model that grounds task-relevant criteria and performs criterion-aware preference comparison. To support this setting, we construct DyCoDataset-20K, which provides dynamic criteria together with criterion-level annotations, and further derive DyCoBench-1K, a benchmark for systematically evaluating reward models under dynamic criteria. We further introduce DyCoPick, which applies criterion-aware reward modeling to selecting T2I images. Our contributions establish the first reward modeling framework for dynamic and fine-grained evaluation and practical application in T2I generation.

cs.CV↗

arXiv2026

Two-Stage Coded-Sliding Beam Training and QoS-Constrained Sum-Rate Maximization for SIM-Assisted Wireless Communications

Stacked intelligent metasurfaces (SIM) provide a cost-effective and scalable solution for large-scale antenna communications.However, efficient channel state information acquisition and phase shift optimization remain critical challenges. In this paper, we develop a unified framework of low-complexity algorithms for SIM-assisted communication systems to address these issues. Specifically, we propose a generalized two-step codebook construction (TSCC) method that leverages two-dimensional angular-domain decoupling to transform planar array beamformer design into two independent one-dimensional linear array beamformer design problems, efficiently solved via the Gerchberg-Saxton algorithm and our proposed majorization-minimization-based proximal distance (PDMM) algorithm. We further develop a two-stage coded-sliding beam training (TSCSBT) method for low-overhead and high-accuracy beam training, where error-correcting codes are embedded in the first-stage training to enhance robustness against noise, and sliding sampling is subsequently performed around the matched angular samples to improve angular resolution. The proposed framework is further extended to multi-path user channels. Finally, a variable decoupling-based block successive upper bound minimization (VD-BSUM) algorithm is proposed to directly solve the QoS-constrained sum-rate maximization problem through closed-form iterative updates with substantially reduced computational complexity. Simulation results demonstrate the effectiveness of the proposed methods in achieving precise beam pattern realization, improved beam training accuracy and angular resolution, and enhanced sum-rate performance.

cs.IT↗

arXiv2026

HorizonDrive: Self-Corrective Autoregressive World Model for Long-horizon Driving Simulation

Closed-loop driving simulation requires real-time interaction beyond short offline clips, pushing current driving world models toward autoregressive (AR) rollout. Existing AR distillation approaches typically rely on frame sinks or student-side degradation training. The former transfers poorly to driving due to fast ego-motion and rapid scene changes, while the latter remains bounded by the teacher's single-pass output length and thus provides only a limited supervision horizon. A natural question is: can the teacher itself be extended via AR rollout to provide unbounded-horizon supervision at bounded memory cost? The key difficulty is that a standard teacher drifts under its own predictions, contaminating the supervision it provides. Our key insight is to make the teacher rollout-capable, ensuring reliable supervision from its own AR rollouts. This is instantiated as HorizonDrive, an anti-drifting training-and-distillation framework for AR driving simulation. First, scheduled rollout recovery (SRR) trains the base model to reconstruct ground-truth future clips from prediction-corrupted histories, yielding a teacher that remains stable across long AR rollouts. Second, the rollout-capable teacher is extended via AR rollout, providing long-horizon distribution-matching supervision under bounded memory, while a short-window student aligns to it with teacher rollout DMD (TRD) for efficient real-time deployment. HorizonDrive natively supports minute-scale AR rollout under bounded memory; on nuScenes, HorizonDrive reduces FID by 52% and FVD by 37%, and lowers ARE and DTW by 21% and 9% relative to the strongest long-horizon streaming baselines, while remaining competitive with single-pass driving video generators.

cs.CV↗

arXiv2026

Operator Learning for Reconstructing Flow Fields from Sparse Measurements: a Language Model Approach

Reconstructing flow fields from sparse measurements is a fundamental problem in fluid mechanics with broad implications for modeling, control, and design. In this work, we propose a novel operator learning framework that leverages the architecture of language models to perform flow reconstruction in a mesh-free manner. We reformulate flow field reconstruction as a sequence-to-sequence learning task, where sparse measurements are treated as context and unobserved locations as queries. Our model learns to reconstruct the full flow field from sparse inputs, effectively capturing spatial correlations and long-range dependencies. We evaluate the proposed approach on four benchmark datasets: (1) two-dimensional vortex street simulations, (2) daily average temperature data across the contiguous United States, (3) three-dimensional blood flow simulations based on dissipative particle dynamics, and (4) three-dimensional turbulent jet flow measurements obtained via particle tracking velocimetry. Across all cases, our method demonstrates competitive reconstruction accuracy, even with highly incomplete data (less than 10\% observed), and achieves efficient performance. The results highlight the potential of language models as robust and scalable tools for scientific data reconstruction, and suggest a promising direction toward the development of foundation models for scientific and engineering applications.

cs.CE↗

arXiv2026

EponaV2: Driving World Model with Comprehensive Future Reasoning

Data scaling plays a pivotal role in the pursuit of general intelligence. However, the prevailing perception-planning paradigm in autonomous driving relies heavily on expensive manual annotations to supervise trajectory planning, which severely limits its scalability. Conversely, although existing perception-free driving world models achieve impressive driving performance, their real-world reasoning ability for planning is solely built on next frame image forecasting. Due to the lack of enough supervision, these models often struggle with comprehensive scene understanding, resulting in unsatisfactory trajectory planning. In this paper, we propose EponaV2, a novel paradigm of driving world models, which achieves high-quality planning with comprehensive future reasoning. Inspired by how human drivers anticipate 3D geometry and semantics, we train our model to forecast more comprehensive future representations, which can be additionally decoded to future geometry and semantic maps. Extracting the 3D and semantic modalities enables our model to deeply understand the surrounding environment, and the future prediction task significantly enhances the real-world reasoning capabilities of EponaV2, ultimately leading to improved trajectory planning. Moreover, inspired by the training recipe of Large Language Models (LLMs), we introduce a flow matching group relative policy optimization mechanism to further improve planning accuracy. The state-of-the-art (SOTA) performances of EponaV2 among perception-free models on three NAVSIM benchmarks (+1.3PDMS, +5.5EPDMS) demonstrate the effectiveness of our methods.

cs.CV↗

arXiv2026

Di-BiLPS: Denoising induced Bidirectional Latent-PDE-Solver under Sparse Observations

Partial differential equations (PDEs) are fundamental for modeling complex natural and physical phenomena. In many real-world applications, however, observational data are extremely sparse, which severely limits the applicability of both classical numerical solvers and existing neural approaches. While neural methods have shown promising results under moderately sparse observations, their inference efficiency at high resolutions is limited, and their accuracy degrades substantially in the extremely sparse regime. In this work, we propose the Di-BiLPS, a unified neural framework that effectively handle both forward and inverse PDE problems under extremely sparse observations. Di-BiLPS combines a variational autoencoder to compress high-dimensional inputs into a compact latent space, a latent diffusion module to model uncertainty, and contrastive learning to align representations. Operating entirely in this latent space, the framework achieves efficient inference while retaining flexible input-output mapping. In addition, we introduce a PDE-informed denoising algorithm based on a variance-preserving diffusion process, which further improves inference efficiency. Extensive experiments on multiple PDE benchmarks demonstrate that Di-BiLPS consistently achieves SOTA performance under extremely sparse inputs (as low as 3%), while substantially reducing computational cost. Moreover, Di-BiLPS enables zero-shot super-resolution, as it allows predictions over continuous spatial-temporal domains.

cs.LG↗

arXiv2026

A Simplicial Approach to Higher Geometric Quantization

This paper develops a unified framework for observables in n-plectic geometry, extending the L_infty-algebra of Hamiltonian (n-1)-forms to Hamiltonian forms of all degrees via a degree-shifting Grassmann variable u that encodes submanifold codimension. Interpreting k-form observables as k-dimensional topological defects yields a recursive gluing construction that assembles into a semi-simplicial set sOb_bullet(M), which we prove satisfies the Kan filling property, thereby providing an n-groupoid model for observables. From this semi-simplicial perspective we extract cohomological invariants and construct a recursive inner product leading to a categorified pre-n-Hilbert space. The hierarchical structure of polarizations yields a natural quantization scheme matching the 1-polarization classification of multisymplectic geometry. The resulting framework bridges higher algebraic structures with higher categorical geometry and establishes a systematic foundation for the geometric quantization of extended objects.

math-ph↗

arXiv2026

REAP: Reinforcement-Learning End-to-End Autonomous Parking with Gaussian Splatting Simulator for Real2Sim2Real Transfer

In recent years, autonomous parking has made significant advances, yet parking tasks still face challenges in extreme scenarios such as mechanical and dead-end parking slots, often resulting in failures. This is mainly due to traditional parking methods adopting a multistage approach, lacking the ability to optimize the parking problem as a whole. End-to-end methods enable joint optimization across perception and planning modules to eliminate the accumulation of errors, enhancing algorithm performance in extreme scenarios. Although several end-to-end parking methods use imitation or reinforcement learning, the former is limited by data cost and distribution coverage, while the latter suffers from inefficient exploration. To address these challenges, we propose a Reinforcement learning End-to-end Autonomous Parking method (REAP). REAP employs Soft Actor-Critic (SAC) within an asymmetric reinforcement learning framework to improve training efficiency and inference performance. To accelerate model convergence, we distill the capabilities of a rule-based planner into the end-to-end network through behavior cloning. We further introduce a soft predictive collision penalty mechanism to reduce collision rates by penalizing obstacle-approaching actions. To ensure that the trained reinforcement learning network can directly transfer to real-world scenarios, we have established a Real2Sim2Real simulator. In the Real2Sim step, we use 3D Gaussian Splatting (3DGS) to transform real-world scenes into digital scenes. In the Sim2Real step, we deploy the end-to-end model onto the vehicle to bridge the Sim2Real gap. Trained in the 3DGS simulator and deployed on physical vehicles, REAP successfully parks in various types of parking spaces, especially demonstrating the feasibility of end-to-end RL parking in extremely narrow mechanical slots.

cs.RO↗

arXiv2026

Adaptive Coordinate Transforms for Neural Operators

Neural operators have achieved promising performance on partial differential equations (PDEs), but most existing models are built on fixed Eulerian coordinates. This mismatch between evolving physical structures and static coordinates creates spatial misalignment, leading to unnecessarily non-local operator mappings and reinforcing a smoothness preference near sharp transitions. Inspired by adaptive coordinate transformations in classical PDE analysis, we propose the Adaptive Coordinate Transform (ACT) block, a plug-and-play module for data-driven geometric adaptation in neural operators. ACT blocks resolve this structural limitation by learning adaptive coordinate systems within the operator learning pipeline. Specifically, given an input feature, the ACT block learns a coordinate transformation and represents the same feature under the transformed coordinates via differentiable sampling. This operation preserves the underlying signal while changing its spatial representation, equivalent to expressing the same physical quantity in different coordinate systems. By adapting the coordinate system to the data, ACT allows the network to better track evolving structures, reduce operator complexity, and dynamically focus on critical features to improve learning. We evaluate the proposed approach across diverse PDE benchmarks and multiple neural operator architectures. Experimental results demonstrate consistent and significant improvements in predictive accuracy, indicating that learning coordinate systems provides a powerful mechanism for enhancing operator learning.

cs.CE↗

arXiv2026

Molecular-optomechanical phonon laser

Molecular cavity optomechanics (COM) leverages ultrastrong interactions between confined optical fields and high-frequency molecular vibration, providing a unique platform for exploring high-frequency phonon dynamics. In this work, we theoretically propose the use of a hybrid molecular COM system for realizing an ultra-low-threshold mid-infrared (MIR) phonon laser. Despite an optical quality factor of only $Q_a=100$, an ultra-low threshold power of $\mathrm{P}_{\mathrm{th}} = 17.5~\mathrm{nW}$ is achieved, enabled by giant single-photon optomechanical coupling and molecular collective effect. Moreover, the mechanical gain and threshold power can be further tuned by adjusting the distance between mirrors of the Fabry-Pérot cavity. Our findings establish the first direct connection between molecular COM and MIR phonon lasers, with potential applications in MIR acoustics and biomedical imaging.

physics.optics↗

arXiv2026

DRL-Based Antenna Position Optimization For MA-Assisted OTFS System Under Imperfect CSI

In this paper, we introduce movable antenna (MA) technology into orthogonal time frequency space (OTFS) systems to enable wavelength-level antenna position optimization under imperfect channel state information (CSI), thereby mitigating deep fading. To accurately acquire CSI, we develop a sparse Bayesian learning method with variational inference (SBLVI) method. Based on estimated CSI, we formulate an MA position optimization problem with the objective of maximizing channel gain. Due to the highly non-convex character of the problem, we further develop a deep reinforcement learning (DRL) strategy to intelligently optimize MA positions. Simulation results show that the proposed SBLVI method significantly improves channel estimation accuracy over benchmark methods, and MA position optimization based on estimated CSI achieves substantially higher channel gains than the fixed-position antenna (FPA), demonstrating the effectiveness of the proposed MA-assisted OTFS system.

cs.IT↗

arXiv2026

UNIKIE-BENCH: Benchmarking Large Multimodal Models for Key Information Extraction in Visual Documents

Key Information Extraction (KIE) from real-world documents remains challenging due to substantial variations in layout structures, visual quality, and task-specific information requirements. Recent Large Multimodal Models (LMMs) have shown promising potential for performing end-to-end KIE directly from document images. To enable a comprehensive and systematic evaluation across realistic and diverse application scenarios, we introduce UNIKIE-BENCH, a unified benchmark designed to rigorously evaluate the KIE capabilities of LMMs. UNIKIE-BENCH consists of two complementary tracks: a constrained-category KIE track with scenario-predefined schemas that reflect practical application needs, and an open-category KIE track that extracts any key information that is explicitly present in the document. Experiments on 15 state-of-the-art LMMs reveal substantial performance degradation under diverse schema definitions, long-tail key fields, and complex layouts, along with pronounced performance disparities across different document types and scenarios. These findings underscore persistent challenges in grounding accuracy and layout-aware reasoning for LMM-based KIE. All codes and datasets are available at https://github.com/NEUIR/UNIKIE-BENCH.

cs.CV↗

arXiv2026

CAST: Modeling Semantic-Level Transitions for Complementary-Aware Sequential Recommendation

Sequential Recommendation (SR) aims to predict the next interaction of a user based on their behavior sequence, where complementary relations often provide essential signals for predicting the next item. However, mainstream models relying on sparse co-purchase statistics often mistake spurious correlations (e.g., due to popularity bias) for true complementary relations. Identifying true complementary relations requires capturing the fine-grained item semantics (e.g., specifications) that simple cooccurrence statistics would be unable to model. While recent semantics-based methods utilize discrete semantic codes to represent items, they typically aggregate semantic codes into coarse item representations. This aggregation process blurs specific semantic details required to identify complementarity. To address these critical limitations and effectively leverage semantics for capturing reliable complementary relations, we propose a Complementary-Aware Semantic Transition (CAST) framework that introduces a new modeling paradigm built upon semantic-level transitions. Specifically, a semantic-level transition module is designed to model dynamic transitions directly in the discrete semantic code space, effectively capturing fine-grained semantic dependencies often lost in aggregated item representations. Then, a complementary prior injection module is designed to incorporate LLM-verified complementary priors into the attention mechanism, thereby prioritizing complementary patterns over co-occurrence statistics. Experiments on multiple e-commerce datasets demonstrate that CAST consistently outperforms the state-of-the-art approaches, achieving up to 17.6% Recall and 16.0% NDCG gains with 65x training acceleration. This validates its effectiveness and efficiency in uncovering latent item complementarity beyond statistics. The code will be released upon acceptance.

cs.IR↗

arXiv2026

VADv2: End-to-End Vectorized Autonomous Driving via Probabilistic Planning

Learning a human-like driving policy from large-scale driving demonstrations is promising, but the uncertainty and non-deterministic nature of planning make it challenging. Existing learning-based planning methods follow a deterministic paradigm to directly regress the action, failing to cope with the uncertainty problem. In this work, we propose a probabilistic planning model for end-to-end autonomous driving, termed VADv2. We resort to a probabilistic field function to model the mapping from the action space to the probabilistic distribution. Since the planning action space is a high-dimensional continuous spatiotemporal space and hard to tackle, we first discretize the planning action space to a large planning vocabulary and then tokenize the planning vocabulary into planning tokens. Planning tokens interact with scene tokens and output the probabilistic distribution of action. Mass driving demonstrations are leveraged to supervise the distribution. VADv2 achieves state-of-the-art closed-loop performance on the CARLA Town05 benchmark, significantly outperforming existing methods, and also leads the recent Bench2Drive benchmark. We further provide comprehensive evaluations on NAVSIM and a large-scale 3DGS-based benchmark, demonstrating its effectiveness in real-world applications. Code is available at https://github.com/hustvl/VAD.

cs.CV↗

arXiv2026

RAD-2: Scaling Reinforcement Learning in a Generator-Discriminator Framework

High-level autonomous driving requires motion planners capable of modeling multimodal future uncertainties while remaining robust in closed-loop interactions. Although diffusion-based planners are effective at modeling complex trajectory distributions, they often suffer from stochastic instabilities and the lack of corrective negative feedback when trained purely with imitation learning. To address these issues, we propose RAD-2, a unified generator-discriminator framework for closed-loop planning. Specifically, a diffusion-based generator is used to produce diverse trajectory candidates, while an RL-optimized discriminator reranks these candidates according to their long-term driving quality. This decoupled design avoids directly applying sparse scalar rewards to the full high-dimensional trajectory space, thereby improving optimization stability. To further enhance reinforcement learning, we introduce Temporally Consistent Group Relative Policy Optimization, which exploits temporal coherence to alleviate the credit assignment problem. In addition, we propose On-policy Generator Optimization, which converts closed-loop feedback into structured longitudinal optimization signals and progressively shifts the generator toward high-reward trajectory manifolds. To support efficient large-scale training, we introduce BEV-Warp, a high-throughput simulation environment that performs closed-loop evaluation directly in Bird's-Eye View feature space via spatial warping. RAD-2 reduces the collision rate by 56% compared with strong diffusion-based planners. Real-world deployment further demonstrates improved perceived safety and driving smoothness in complex urban traffic.

cs.CV↗

arXiv2026

Fluid Antennas Meet Rate-Splitting Multiple Access: A New Path Forward for 6G Networks

Future sixth-generation (6G) networks require high spectral efficiency (SE), massive connectivity, and stringent reliability under imperfect channel state information at the transmitter. Rate-splitting multiple access (RSMA) addresses part of this challenge by flexibly managing interference through common and private message streams, while fluid antenna systems (FAS) offer low-cost spatial diversity by dynamically reconfiguring antenna positions within a compact aperture. In this paper, we first classify FAS-enabled multiple access systems from the perspectives of FAS deployment, objectives, and antenna configuration, along with some comparisons with benchmark schemes, thereby exhibiting the inherent efficiency of FAS-RSMA. Moreover, we reveal the mutually enhancing mechanism between FAS and RSMA: FAS strengthens the weakest effective link and improves the beamforming design in RSMA, whereas RSMA turns FAS-induced spatial diversity into robust interference management under diverse channel conditions. In addition, we identify representative 6G scenarios and highlight major research challenges in joint beamforming-antenna position design, channel estimation, and hardware design. Furthermore, case studies quantify the gains of FAS-RSMA over the fixed-position antenna (FPA) system with RSMA and NOMA baselines, which validates that FAS-RSMA is a strong candidate for interference-limited access in 6G systems.

eess.SP↗

arXiv2026

VidAudio-Bench: Benchmarking V2A and VT2A Generation across Four Audio Categories

Video-to-Audio (V2A) generation is essential for immersive multimedia experiences, yet its evaluation remains underexplored. Existing benchmarks typically assess diverse audio types under a unified protocol, overlooking the fine-grained requirements of distinct audio categories. To address this gap, we propose VidAudio-Bench, a multi-task benchmark for V2A evaluation with four key features: (1) Broad Coverage: It encompasses four representative audio categories - sound effects, music, speech, and singing - under both V2A and Video-Text-to-Audio (VT2A) settings. (2) Extensive Evaluation: It comprises 1,634 video-text pairs and benchmarks 11 state-of-the-art generation models. (3) Comprehensive Metrics: It introduces 13 task-specific, reference-free metrics to systematically assess audio quality, video-audio consistency, and text-audio consistency. (4) Human Alignment: It validates all metrics through subjective studies, demonstrating strong consistency with human preferences. Experimental results reveal that current V2A models perform poorly in speech and singing compared to sound effects. Our VT2A results further highlight a fundamental tension between instruction following and visually grounded generation: stronger visual conditioning improves video-audio alignment, but often at the cost of generating the intended audio category. These findings establish VidAudio-Bench as a comprehensive and scalable framework for diagnosing V2A systems and provide new insights into multimodal audio generation.

cs.SD↗