arXiv subjects

Qiang Zhu

Publications and source records attributed to Qiang Zhu.

At least 37 records · Page 2Linked to original sources

arXiv2026

CARL: Constraint-Aware Reinforcement Learning for Planning with LLMs

Despite their strong reasoning capabilities and extensive world knowledge, Large Language Models (LLMs) frequently generate plans that violate task constraints, undermining their reliability in real-world applications. This deficiency arises from a lack of systematic mechanisms to incorporate constraint information during the generation process. While existing approaches attempt to mitigate this by relying on external tools or task decomposition, they fail to enhance the model's intrinsic constraint awareness. To address this, we propose Constraint-Aware Reinforcement Learning (CARL), a novel RL framework designed to strengthen LLMs' intrinsic focus on constraints. CARL introduces a constraint-aware reward by comparing the model's output distributions under constrained and unconstrained inputs, encouraging constraint focus and penalizing neglect. Compatible with various RL frameworks and requiring no external solvers or top models, CARL enables scalable, end-to-end constraint-aware planning. Extensive experiments on BlocksWorld, TravelPlanner, and T-Eval demonstrate that CARL significantly outperforms standard Reinforcement Fine-Tuning (RFT) baselines and state-of-the-art reasoning models, exhibiting a markedly increased focus on constraints.

cs.AI↗

arXiv2026

STAPO: Selective Trajectory-Aware Policy Optimization for LLM Agent Training

Reinforcement Learning (RL) is the dominant paradigm for training Large Language Model (LLM) agents on long-horizon tasks. However, sparse and delayed rewards often lead to trajectory neglect, in which agents lose focus on the task goal and interaction history at intermediate steps. Prior work has explored step-level supervision using Shannon-entropy-based uncertainty signals, which conflate inherent state complexity with agent confidence and therefore provide unreliable estimates of decision reliability. To address this issue, we propose normalized entropy, which measures confidence deviations relative to an agent's average behavior under a given state, thereby strengthening the association between low-quality actions and trajectory neglect. Building on this insight, we introduce Selective Trajectory-Aware Policy Optimization (STAPO), a hierarchical group-based RL framework. STAPO leverages normalized entropy to locate outlier steps associated with trajectory neglect and optimizes them via a joint mechanism of trajectory-aware reward and trajectory-independent penalty, enhancing trajectory awareness while preserving training stability. Extensive experiments on ALFWorld, WebShop, and Search-Augmented QA demonstrate that STAPO achieves state-of-the-art performance while substantially alleviating trajectory neglect, validating its effectiveness and robustness for agentic tasks.

cs.AI↗

arXiv2026

Accelerated Inorganic Electrides Discovery by Generative Models and Hierarchical Screening

Electrides are exotic compounds in which excess electrons occupy interstitial regions of the crystal lattice and serve as anions, exhibiting exceptional properties such as low work function, high electron mobility, and strong catalytic activity. Although they show promise for diverse applications, identifying new electrides remains challenging due to the difficulty of achieving energetically favorable electron localization in crystal cavities. Here, we present an accelerated materials discovery framework that combines physical principles, diffusion-based materials generation with hierarchical thermodynamic and electronic structure screening. Using this workflow, we systematically explored 1,510 binary and 6,654 ternary chemical compositions containing excess valence electrons from electropositive alkaline, alkaline-earth, and early transition metals, and then filtered them with a high throughput validation on both thermodynamical stability and electronic structure analysis. As a result, we have identified 264 new electron rich compounds within 0.05 eV/atom above the convex hull at the density functional theory (DFT) level, including 13 thermodynamically stable electrides. Our approach demonstrates a generalizable strategy for targeted materials discovery in a vast chemical space.

cond-mat.mtrl-sci↗

arXiv2026

Confidence Calibration for Multimodal LLMs: An Empirical Study through Medical VQA

Multimodal Large Language Models (MLLMs) show great potential in medical tasks, but their elicited confidence often misaligns with actual accuracy, potentially leading to misdiagnosis or overlooking correct advice. This study presents the first comprehensive analysis of the relationship between accuracy and confidence in medical MLLMs. It proposes a novel method that combines Multi-Strategy Fusion-Based Interrogation (MS-FBI) with auxiliary expert LLM assessment, aiming to improve confidence calibration in Medical Visual Question Answering (VQA). Experiments demonstrate that our method reduces the Expected Calibration Error (ECE) by an average of 40\% across three Medical VQA datasets, significantly enhancing MLLMs' reliability. The findings highlight the importance of domain-specific calibration for MLLMs in healthcare, offering a more trustworthy solution for AI-assisted diagnosis.

cs.CV↗

arXiv2026

NTIRE 2025 Challenge on Image Super-Resolution (x4): Methods and Results

This paper presents the NTIRE 2025 image super-resolution ($\times$4) challenge, one of the associated competitions of the 10th NTIRE Workshop at CVPR 2025. The challenge aims to recover high-resolution (HR) images from low-resolution (LR) counterparts generated through bicubic downsampling with a $\times$4 scaling factor. The objective is to develop effective network designs or solutions that achieve state-of-the-art SR performance. To reflect the dual objectives of image SR research, the challenge includes two sub-tracks: (1) a restoration track, emphasizes pixel-wise accuracy and ranks submissions based on PSNR; (2) a perceptual track, focuses on visual realism and ranks results by a perceptual score. A total of 286 participants registered for the competition, with 25 teams submitting valid entries. This report summarizes the challenge design, datasets, evaluation protocol, the main results, and methods of each team. The challenge serves as a benchmark to advance the state of the art and foster progress in image SR.

cs.CV↗

arXiv2026

UCPO: Uncertainty-Aware Policy Optimization

The key to building trustworthy large language models (LLMs) lies in endowing them with inherent uncertainty expression capabilities, thereby mitigating overconfident errors in high-stakes applications. However, existing RL paradigms such as GRPO often suffer from Advantage Bias due to binary decision spaces and static uncertainty rewards, inducing either excessive conservatism or overconfidence. To tackle this challenge, this paper unveils the root causes of reward hacking and overconfidence in current RL paradigms incorporating uncertainty-based rewards, based on which we propose the UnCertainty-Aware Policy Optimization (UCPO) framework. UCPO employs Ternary Advantage Decoupling to separate and independently normalize deterministic and uncertain rollouts, thereby eliminating advantage bias. Furthermore, a Dynamic Uncertainty Reward Adjustment mechanism adapts uncertainty weights in real-time according to model evolution and instance difficulty. Experimental results in mathematical reasoning and general tasks demonstrate that UCPO effectively resolves the reward imbalance, significantly improving the reliability of the model beyond their knowledge boundaries.

cs.AI↗

arXiv2026

HPGN: Hybrid Priors-Guided Network for Compressed Low-Light Image Enhancement

In practical applications, low-light images are often compressed for efficient storage and transmission. Most existing methods disregard compression artifacts removal or hardly establish a unified framework for joint task enhancement of low-light images with varying compression qualities. To address this problem, we propose an efficient hybrid priors-guided network (HPGN) that enhances compressed low-light images by integrating both compression and illumination priors. Our approach fully utilizes the JPEG quality factor (QF) and DCT quantization matrix (QM) to guide the design of efficient plug-and-play modules for joint tasks. Additionally, we employ a random QF generation strategy to guide model training, enabling a single model to enhance low-light images with different compression levels. Experimental results demonstrate the superiority of our proposed method.

eess.IV↗

arXiv2026

NTIRE 2026 3D Restoration and Reconstruction in Real-world Adverse Conditions: RealX3D Challenge Results

This paper presents a comprehensive review of the NTIRE 2026 3D Restoration and Reconstruction (3DRR) Challenge, detailing the proposed methods and results. The challenge seeks to identify robust reconstruction pipelines that are robust under real-world adverse conditions, specifically extreme low-light and smoke-degraded environments, as captured by our RealX3D benchmark. A total of 279 participants registered for the competition, of whom 33 teams submitted valid results. We thoroughly evaluate the submitted approaches against state-of-the-art baselines, revealing significant progress in 3D reconstruction under adverse conditions. Our analysis highlights shared design principles among top-performing methods and provides insights into effective strategies for handling 3D scene degradation.

cs.CV↗

arXiv2026

DOC-GS: Dual-Domain Observation and Calibration for Reliable Sparse-View Gaussian Splatting

Sparse-view reconstruction with 3D Gaussian Splatting (3DGS) is fundamentally ill-posed due to insufficient geometric supervision, often leading to severe overfitting and the emergence of structural distortions and translucent haze-like artifacts. While existing approaches attempt to alleviate this issue via dropout-based regularization, they are largely heuristic and lack a unified understanding of artifact formation. In this paper, we revisit sparse-view 3DGS reconstruction from a new perspective and identify the core challenge as the unobservability of Gaussian primitive reliability. Unreliable Gaussians are insufficiently constrained during optimization and accumulate as haze-like degradations in rendered images. Motivated by this observation, we propose a unified Dual-domain Observation and Calibration (DOC-GS) framework that models and corrects Gaussian reliability through the synergy of optimization-domain inductive bias and observation-domain evidence. Specifically, in the optimization domain, we characterize Gaussian reliability by the degree to which each primitive is constrained during training, and instantiate this signal via a Continuous Depth-Guided Dropout (CDGD) strategy, where the dropout probability serves as an explicit proxy for primitive reliability. This imposes a smooth depth-aware inductive bias to suppress weakly constrained Gaussians and improve optimization stability. In the observation domain, we establish a connection between floater artifacts and atmospheric scattering, and leverage the Dark Channel Prior (DCP) as a structural consistency cue to identify and accumulate anomalous regions. Based on cross-view aggregated evidence, we further design a reliability-driven geometric pruning strategy to remove low-confidence Gaussians.

cs.CV↗

arXiv2026

PDMP: Rethinking Balanced Multimodal Learning via Performance-Dominant Modality Prioritization

Multimodal learning has attracted increasing attention due to its practicality. However, it often suffers from insufficient optimization, where the multimodal model underperforms even compared to its unimodal counterparts. Existing methods attribute this problem to the imbalanced learning between modalities and solve it by gradient modulation. This paper argues that balanced learning is not the optimal setting for multimodal learning. On the contrary, imbalanced learning driven by the performance-dominant modality that has superior unimodal performance can contribute to better multimodal performance. And the under-optimization problem is caused by insufficient learning of the performance-dominant modality. To this end, we propose the Performance-Dominant Modality Prioritization (PDMP) strategy to assist multimodal learning. Specifically, PDMP firstly mines the performance-dominant modality via the performance ranking of the independently trained unimodal model. Then PDMP introduces asymmetric coefficients to modulate the gradients of each modality, enabling the performance-dominant modality to dominate the optimization. Since PDMP only relies on the unimodal performance ranking, it is independent of the structures and fusion methods of the multimodal model and has great potential for practical scenarios. Finally, extensive experiments on various datasets validate the superiority of PDMP.

cs.CV↗

arXiv2026

Variation-aware Flexible 3D Gaussian Editing

Indirect editing methods for 3D Gaussian Splatting (3DGS) have recently witnessed significant advancements. These approaches operate by first applying edits in the rendered 2D space and subsequently projecting the modifications back into 3D. However, this paradigm inevitably introduces cross-view inconsistencies and constrains both the flexibility and efficiency of the editing process. To address these challenges, we present VF-Editor, which enables native editing of Gaussian primitives by predicting attribute variations in a feedforward manner. To accurately and efficiently estimate these variations, we design a novel variation predictor distilled from 2D editing knowledge. The predictor encodes the input to generate a variation field and employs two learnable, parallel decoding functions to iteratively infer attribute changes for each 3D Gaussian. Thanks to its unified design, VF-Editor can seamlessly distill editing knowledge from diverse 2D editors and strategies into a single predictor, allowing for flexible and effective knowledge transfer into the 3D domain. Extensive experiments on both public and private datasets reveal the inherent limitations of indirect editing pipelines and validate the effectiveness and flexibility of our approach.

cs.GR↗

arXiv2026

Linking Perception, Confidence and Accuracy in MLLMs

Recent advances in Multi-modal Large Language Models (MLLMs) have predominantly focused on enhancing visual perception to improve accuracy. However, a critical question remains unexplored: Do models know when they do not know? Through a probing experiment, we reveal a severe confidence miscalibration problem in MLLMs. To address this, we propose Confidence-Driven Reinforcement Learning (CDRL), which uses original-noise image pairs and a novel confidence-based reward to enhance perceptual sensitivity and robustly calibrate the model's confidence. Beyond training benefits, calibrated confidence enables more effective test-time scaling as a free lunch. We further propose Confidence-Aware Test-Time Scaling (CA-TTS), which dynamically coordinates Self-Consistency, Self-Reflection, and Visual Self-Check modules guided by confidence signals. An Expert Model acts in multiple roles (e.g., Planner, Critic, Voter) to schedule these modules and provide external verification. Our integrated framework establishes new state-of-the-art results with consistent 8.8% gains across four benchmarks. More ablation studies demonstrate the effectiveness of each module and scaling superiority.

cs.CV↗

arXiv2026

Trajectory-aware Shifted State Space Models for Online Video Super-Resolution

Online video super-resolution (VSR) is an important technique for many real-world video processing applications, which aims to restore the current high-resolution video frame based on temporally previous frames. Most of the existing online VSR methods solely employ one neighboring previous frame to achieve temporal alignment, which limits long-range temporal modeling of videos. Recently, state space models (SSMs) have been proposed with linear computational complexity and a global receptive field, which significantly improve computational efficiency and performance. In this context, this paper presents a novel online VSR method based on Trajectory-aware Shifted SSMs (TS-Mamba), leveraging both long-term trajectory modeling and low-complexity Mamba to achieve efficient spatio-temporal information aggregation. Specifically, TS-Mamba first constructs the trajectories within a video to select the most similar tokens from the previous frames. Then, a Trajectory-aware Shifted Mamba Aggregation (TSMA) module consisting of proposed shifted SSMs blocks is employed to aggregate the selected tokens. The shifted SSMs blocks are designed based on Hilbert scannings and corresponding shift operations to compensate for scanning losses and strengthen the spatial continuity of Mamba. Additionally, we propose a trajectory-aware loss function to supervise the trajectory generation, ensuring the accuracy of token selection when training our model. Extensive experiments on three widely used VSR test datasets demonstrate that compared with six online VSR benchmark models, our TS-Mamba achieves state-of-the-art performance in most cases and over 22.7% complexity reduction (in MACs).

cs.CV↗

arXiv2026

Crystal Representation in the Reciprocal Space

In crystallography, a structure is typically represented by the arrangement of atoms in the direct space. Furthermore, space group symmetry and Wyckoff site notations are applied to characterize crystal structures with only a few variables. While this representation is effective for data records and human learning, it lacks one-to-one correspondence between the crystal structure and its representation. This is problematic for many applications, such as crystal structure determination, comparison, and more recently, generative model learning. To address this issue, we propose to represent crystals in a four-dimensional (4D) reciprocal space featured by their Cartesian coordinates and scattering factors, which can naturally handle translation invariance and space group symmetry with the help of structure factors. In order to achieve rotational invariance, the 4D coordinates are then transformed into a power spectrum representation under the orthogonal spherical harmonic and radial basis. Hence, this representation captures both periodicity and symmetry of the crystal structure while also providing a continuous representation of the atomic positions and cell parameters in the direct space. Its effectiveness is demonstrated by applying it to several crystal structure matching and reconstruction tasks.

cond-mat.mtrl-sci↗

arXiv2026

Enhancing Customer Contact Efficiency with Graph Neural Networks in Credit Card Fraud Detection Workflow

Credit card fraud has been a persistent issue since the last century, causing significant financial losses to the industry. The most effective way to prevent fraud is by contacting customers to verify suspicious transactions. However, while these systems are designed to detect fraudulent activity, they often mistakenly flag legitimate transactions, leading to unnecessary declines that disrupt the user experience and erode customer trust. Frequent false positives can frustrate customers, resulting in dissatisfaction, increased complaints, and a diminished sense of security. To address these limitations, we propose a fraud detection framework incorporating Relational Graph Convolutional Networks (RGCN) to enhance the accuracy and efficiency of identifying fraudulent transactions. By leveraging the relational structure of transaction data, our model reduces the need for direct customer confirmation while maintaining high detection performance. Our experiments are conducted using the IBM credit card transaction dataset to evaluate the effectiveness of this approach.

cs.LG↗

arXiv2026

Image-to-Image Translation with Diffusion Transformers and CLIP-Based Image Conditioning

Image-to-image translation aims to learn a mapping between a source and a target domain, enabling tasks such as style transfer, appearance transformation, and domain adaptation. In this work, we explore a diffusion-based framework for image-to-image translation by adapting Diffusion Transformers (DiT), which combine the denoising capabilities of diffusion models with the global modeling power of transformers. To guide the translation process, we condition the model on image embeddings extracted from a pre-trained CLIP encoder, allowing for fine-grained and structurally consistent translations without relying on text or class labels. We incorporate both a CLIP similarity loss to enforce semantic consistency and an LPIPS perceptual loss to enhance visual fidelity during training. We validate our approach on two benchmark datasets: face2comics, which translates real human faces to comic-style illustrations, and edges2shoes, which translates edge maps to realistic shoe images. Experimental results demonstrate that DiT, combined with CLIP-based conditioning and perceptual similarity objectives, achieves high-quality, semantically faithful translations, offering a promising alternative to GAN-based models for paired image-to-image translation tasks.

cs.CV↗

arXiv2026

CT-PatchTST: Channel-Time Patch Time-Series Transformer for Long-Term Renewable Energy Forecasting

Accurate forecasting of renewable energy generation is fundamental to enhancing the dynamic performance of modern power grids, especially under high renewable penetration. This paper presents Channel-Time Patch Time-Series Transformer (CT-PatchTST), a novel deep learning model designed to provide long-term, high-fidelity forecasts of wind and solar power. Unlike conventional time-series models, CT-PatchTST captures both temporal dependencies and inter-channel correlations-features that are critical for effective energy storage planning, control, and dispatch. Reliable forecasting enables proactive deployment of energy storage systems (ESSs), helping to mitigate uncertainties in renewable output, reduce system response time, and optimize storage operation based on location-specific flow and voltage conditions. Evaluated on real-world datasets from Denmark's offshore wind, onshore wind, and solar generation, CT-PatchTST outperforms existing methods in both accuracy and robustness. By enabling predictive, data-driven coordination of ESSs across integrated source-grid-load-storage systems, this work contributes to the design of more stable, responsive, and cost-efficient power networks.

cs.LG↗

arXiv2026

Crystal Generation using the Fully Differentiable Pipeline and Latent Space Optimization

We present a materials generation framework that couples a symmetry-conditioned variational autoencoder (CVAE) with a differentiable SO(3) power spectrum objective to steer candidates toward a specified local environment under the crystallographic constraints. In particular, we implement a fully differentiable pipeline to enable batch-wise optimization on both direct and latent crystallographic representations. Using the GPU acceleration, this implementation achieves about fivefold speed compared to our previous CPU workflow, while yielding comparable outcomes. In addition, we introduce the optimization strategy that alternatively performs optimization on the direct and latent crystal representations. This dual-level relaxation approach can effectively escape local minima defined by different objective gradients, thus increasing the success rate of generating complex structures satisfying the target local environments. This framework can be extended to systems consisting of multi-components and multi-environments, providing a scalable route to generate material structures with the target local environment.

cond-mat.mtrl-sci↗