arXiv subjects

Zihao Zhang

Publications and source records attributed to Zihao Zhang.

At least 91 records · Page 5Linked to original sources

arXiv2025

Enhancing Code LLMs with Reinforcement Learning in Code Generation: A Survey

With the rapid evolution of large language models (LLM), reinforcement learning (RL) has emerged as a pivotal technique for code generation and optimization in various domains. This paper presents a systematic survey of the application of RL in code optimization and generation, highlighting its role in enhancing compiler optimization, resource allocation, and the development of frameworks and tools. Subsequent sections first delve into the intricate processes of compiler optimization, where RL algorithms are leveraged to improve efficiency and resource utilization. The discussion then progresses to the function of RL in resource allocation, emphasizing register allocation and system optimization. We also explore the burgeoning role of frameworks and tools in code generation, examining how RL can be integrated to bolster their capabilities. This survey aims to serve as a comprehensive resource for researchers and practitioners interested in harnessing the power of RL to advance code generation and optimization techniques.

cs.SE↗

arXiv2025

World-Consistent Data Generation for Vision-and-Language Navigation

Vision-and-Language Navigation (VLN) is a challenging task that requires an agent to navigate through photorealistic environments following natural-language instructions. One main obstacle existing in VLN is data scarcity, leading to poor generalization performance over unseen environments. Though data argumentation is a promising way for scaling up the dataset, how to generate VLN data both diverse and world-consistent remains problematic. To cope with this issue, we propose the world-consistent data generation (WCGEN), an efficacious data-augmentation framework satisfying both diversity and world-consistency, aimed at enhancing the generalization of agents to novel environments. Roughly, our framework consists of two stages, the trajectory stage which leverages a point-cloud based technique to ensure spatial coherency among viewpoints, and the viewpoint stage which adopts a novel angle synthesis method to guarantee spatial and wraparound consistency within the entire observation. By accurately predicting viewpoint changes with 3D knowledge, our approach maintains the world-consistency during the generation procedure. Experiments on a wide range of datasets verify the effectiveness of our method, demonstrating that our data augmentation strategy enables agents to achieve new state-of-the-art results on all navigation tasks, and is capable of enhancing the VLN agents' generalization ability to unseen environments.

cs.CV↗

arXiv2025

Closed-Form Decomposition for Simplicial Cones and PDBarv Algorithm for Lattice Point Counting

Counting lattice points within a rational polytope is a foundational problem with applications across mathematics and computer science. A key approach is Barvinok's algorithm, which decomposes the lattice point generating function of cones to that of unimodular cones. However, standard implementations face difficulties: the original primal method struggles with points on cone boundaries, while the alternative dual method can be slow for certain cone types. This paper introduces two main contributions. First, We derive a closed-form expression for these generating functions using arbitrary lattice point decompositions, enabling more effective primal space decomposition. Second, by decomposing both the cone and its dual cone starting from the side with a smaller index, we develop a novel algorithm called \textup{PDBarv}. This hybrid approach integrates the primal and dual Barvinok algorithms with a novel acceleration strategy, achieving an average computational performance improvement of over 20\% in dimension 5 and even better in higher dimensions.

math.CO↗

arXiv2025

PlanGenLLMs: A Modern Survey of LLM Planning Capabilities

LLMs have immense potential for generating plans, transforming an initial world state into a desired goal state. A large body of research has explored the use of LLMs for various planning tasks, from web navigation to travel planning and database querying. However, many of these systems are tailored to specific problems, making it challenging to compare them or determine the best approach for new tasks. There is also a lack of clear and consistent evaluation criteria. Our survey aims to offer a comprehensive overview of current LLM planners to fill this gap. It builds on foundational work by Kartam and Wilkins (1990) and examines six key performance criteria: completeness, executability, optimality, representation, generalization, and efficiency. For each, we provide a thorough analysis of representative works and highlight their strengths and weaknesses. Our paper also identifies crucial future directions, making it a valuable resource for both practitioners and newcomers interested in leveraging LLM planning to support agentic workflows.

cs.AI↗

arXiv2025

Structural stability of supersonic spiral flows with large angular velocity for the Euler-Poisson system

This paper concerns the structural stability of smooth cylindrically symmetric supersonic spiral flows with large angular velocity for the steady Euler-Poisson system in a concentric cylinder. We establish the existence and uniqueness of some smooth supersonic Euler-Poisson flows with nonzero angular velocity and vorticity including both cylindrical spiral flows and axisymmetric spiral flows. The deformation-curl-Poisson decomposition for the steady Euler-Poisson system is utilized to deal with the hyperbolic-elliptic mixed structure in the supersonic region. For smooth cylindrical supersonic spiral flows, the key point lies on the well-posedness of a boundary value problem for a linear second order hyperbolic-elliptic coupled system, which is achieved by finding an appropriate multiplier to obtain the important basic energy estimates. The nonlinear structural stability is established by designing a two-layer iteration and combining the estimates for the hyperbolic-elliptic system and the transport equations. For smooth axisymmetric supersonic spiral flows, we use the special structure of the steady Euler-Poisson system to derive a priori estimates of the linearized second order elliptic system, which enable us to establish the structural stability of the background supersonic flow within the class of axisymmetric flows.

math.AP↗

arXiv2025

Risk-Informed Diffusion Transformer for Long-Tail Trajectory Prediction in the Crash Scenario

Trajectory prediction methods have been widely applied in autonomous driving technologies. Although the overall performance accuracy of trajectory prediction is relatively high, the lack of trajectory data in critical scenarios in the training data leads to the long-tail phenomenon. Normally, the trajectories of the tail data are more critical and more difficult to predict and may include rare scenarios such as crashes. To solve this problem, we extracted the trajectory data from real-world crash scenarios, which contain more long-tail data. Meanwhile, based on the trajectory data in this scenario, we integrated graph-based risk information and diffusion with transformer and proposed the Risk-Informed Diffusion Transformer (RI-DiT) trajectory prediction method. Extensive experiments were conducted on trajectory data in the real-world crash scenario, and the results show that the algorithm we proposed has good performance. When predicting the data of the tail 10\% (Top 10\%), the minADE and minFDE indicators are 0.016/2.667 m. At the same time, we showed the trajectory conditions of different long-tail distributions. The distribution of trajectory data is closer to the tail, the less smooth the trajectory is. Through the trajectory data in real-world crash scenarios, Our work expands the methods to overcome the long-tail challenges in trajectory prediction. Our method, RI-DiT, integrates inverse time to collision (ITTC) and the feature of traffic flow, which can predict long-tail trajectories more accurately and improve the safety of autonomous driving systems.

cs.LG↗

arXiv2025

EDEN: Enhanced Diffusion for High-quality Large-motion Video Frame Interpolation

Handling complex or nonlinear motion patterns has long posed challenges for video frame interpolation. Although recent advances in diffusion-based methods offer improvements over traditional optical flow-based approaches, they still struggle to generate sharp, temporally consistent frames in scenarios with large motion. To address this limitation, we introduce EDEN, an Enhanced Diffusion for high-quality large-motion vidEo frame iNterpolation. Our approach first utilizes a transformer-based tokenizer to produce refined latent representations of the intermediate frames for diffusion models. We then enhance the diffusion transformer with temporal attention across the process and incorporate a start-end frame difference embedding to guide the generation of dynamic motion. Extensive experiments demonstrate that EDEN achieves state-of-the-art results across popular benchmarks, including nearly a 10% LPIPS reduction on DAVIS and SNU-FILM, and an 8% improvement on DAIN-HD.

cs.CV↗

arXiv2025

Object-Level Verbalized Confidence Calibration in Vision-Language Models via Semantic Perturbation

Vision-language models (VLMs) excel in various multimodal tasks but frequently suffer from poor calibration, resulting in misalignment between their verbalized confidence and response correctness. This miscalibration undermines user trust, especially when models confidently provide incorrect or fabricated information. In this work, we propose a novel Confidence Calibration through Semantic Perturbation (CSP) framework to improve the calibration of verbalized confidence for VLMs in response to object-centric queries. We first introduce a perturbed dataset where Gaussian noise is applied to the key object regions to simulate visual uncertainty at different confidence levels, establishing an explicit mapping between visual ambiguity and confidence levels. We further enhance calibration through a two-stage training process combining supervised fine-tuning on the perturbed dataset with subsequent preference optimization. Extensive experiments on popular benchmarks demonstrate that our method significantly improves the alignment between verbalized confidence and response correctness while maintaining or enhancing overall task performance. These results highlight the potential of semantic perturbation as a practical tool for improving the reliability and interpretability of VLMs.

cs.CV↗

arXiv2025

NTIRE 2025 Challenge on Real-World Face Restoration: Methods and Results

This paper provides a review of the NTIRE 2025 challenge on real-world face restoration, highlighting the proposed solutions and the resulting outcomes. The challenge focuses on generating natural, realistic outputs while maintaining identity consistency. Its goal is to advance state-of-the-art solutions for perceptual quality and realism, without imposing constraints on computational resources or training data. The track of the challenge evaluates performance using a weighted image quality assessment (IQA) score and employs the AdaFace model as an identity checker. The competition attracted 141 registrants, with 13 teams submitting valid models, and ultimately, 10 teams achieved a valid score in the final ranking. This collaborative effort advances the performance of real-world face restoration while offering an in-depth overview of the latest trends in the field.

cs.CV↗

arXiv2025

Visual Consensus Prompting for Co-Salient Object Detection

Existing co-salient object detection (CoSOD) methods generally employ a three-stage architecture (i.e., encoding, consensus extraction & dispersion, and prediction) along with a typical full fine-tuning paradigm. Although they yield certain benefits, they exhibit two notable limitations: 1) This architecture relies on encoded features to facilitate consensus extraction, but the meticulously extracted consensus does not provide timely guidance to the encoding stage. 2) This paradigm involves globally updating all parameters of the model, which is parameter-inefficient and hinders the effective representation of knowledge within the foundation model for this task. Therefore, in this paper, we propose an interaction-effective and parameter-efficient concise architecture for the CoSOD task, addressing two key limitations. It introduces, for the first time, a parameter-efficient prompt tuning paradigm and seamlessly embeds consensus into the prompts to formulate task-specific Visual Consensus Prompts (VCP). Our VCP aims to induce the frozen foundation model to perform better on CoSOD tasks by formulating task-specific visual consensus prompts with minimized tunable parameters. Concretely, the primary insight of the purposeful Consensus Prompt Generator (CPG) is to enforce limited tunable parameters to focus on co-salient representations and generate consensus prompts. The formulated Consensus Prompt Disperser (CPD) leverages consensus prompts to form task-specific visual consensus prompts, thereby arousing the powerful potential of pre-trained models in addressing CoSOD tasks. Extensive experiments demonstrate that our concise VCP outperforms 13 cutting-edge full fine-tuning models, achieving the new state of the art (with 6.8% improvement in F_m metrics on the most challenging CoCA dataset). Source code has been available at https://github.com/WJ-CV/VCP.

cs.CV↗

arXiv2025

DynMoLE: Boosting Mixture of LoRA Experts Fine-Tuning with a Hybrid Routing Mechanism

Instruction-based fine-tuning of large language models (LLMs) has achieved remarkable success in various natural language processing (NLP) tasks. Parameter-efficient fine-tuning (PEFT) methods, such as Mixture of LoRA Experts (MoLE), combine the efficiency of Low-Rank Adaptation (LoRA) with the versatility of Mixture of Experts (MoE) models, demonstrating significant potential for handling multiple downstream tasks. However, the existing routing mechanisms for MoLE often involve a trade-off between computational efficiency and predictive accuracy, and they fail to fully address the diverse expert selection demands across different transformer layers. In this work, we propose DynMoLE, a hybrid routing strategy that dynamically adjusts expert selection based on the Tsallis entropy of the router's probability distribution. This approach mitigates router uncertainty, enhances stability, and promotes more equitable expert participation, leading to faster convergence and improved model performance. Additionally, we introduce an auxiliary loss based on Tsallis entropy to further guide the model toward convergence with reduced uncertainty, thereby improving training stability and performance. Our extensive experiments on commonsense reasoning benchmarks demonstrate that DynMoLE achieves substantial performance improvements, outperforming LoRA by 9.6% and surpassing the state-of-the-art MoLE method, MoLA, by 2.3%. We also conduct a comprehensive ablation study to evaluate the contributions of DynMoLE's key components.

cs.CL↗

arXiv2025

Hankel Determinants for Convolution of Power Series: An Extension of Cigler's Results

Cigler considered certain shifted Hankel determinants of convolution powers of Catalan numbers and conjectured identities for these determinants. Recently, Fulmek gave a bijective proof of Cigler's conjecture. Cigler then provided a computational proof. We extend Cigler's determinant identities to the convolution of general power series $F(x)$, where $F(x)$ satisfies a certain type of quadratic equation. As an application, we present the Hankel determinant identities of convolution powers of Motzkin numbers.

math.CO↗

arXiv2025

Structural stability of cylindrical supersonic solutions to the steady Euler-Poisson system

This paper concerns the structural stability of smooth cylindrically symmetric supersonic Euler-Poisson flows in nozzles. Both three-dimensional and axisymmetric perturbations are considered. On one hand, we establish the existence and uniqueness of three-dimensional smooth supersonic solutions to the potential flow model of the steady Euler-Poisson system. On the other hand, the existence and uniqueness of smooth supersonic flows with nonzero vorticity to the steady axisymmetric Euler-Poisson system are proved. The problem is reduced to solve a nonlinear boundary value problem for a hyperbolic-elliptic mixed system. One of the key ingredients in the analysis of three-dimensional supersonic irrotational flows is the well-posedness theory for a linear second order hyperbolic-elliptic coupled system, which is achieved by using the multiplier method and the reflection technique to derive the energy estimates. For smooth axisymmetric supersonic flows with nonzero vorticity, the deformation-curl-Poisson decomposition is utilized to reformulate the steady axisymmetric Euler-Poisson system as a deformation-curl-Poisson system together with several transport equations, so that one can design a two-layer iteration scheme to establish the nonlinear structural stability of the background supersonic flow within the class of axisymmetric rotational flows.

math.AP↗

arXiv2025

Style Evolving along Chain-of-Thought for Unknown-Domain Object Detection

Recently, a task of Single-Domain Generalized Object Detection (Single-DGOD) is proposed, aiming to generalize a detector to multiple unknown domains never seen before during training. Due to the unavailability of target-domain data, some methods leverage the multimodal capabilities of vision-language models, using textual prompts to estimate cross-domain information, enhancing the model's generalization capability. These methods typically use a single textual prompt, often referred to as the one-step prompt method. However, when dealing with complex styles such as the combination of rain and night, we observe that the performance of the one-step prompt method tends to be relatively weak. The reason may be that many scenes incorporate not just a single style but a combination of multiple styles. The one-step prompt method may not effectively synthesize combined information involving various styles. To address this limitation, we propose a new method, i.e., Style Evolving along Chain-of-Thought, which aims to progressively integrate and expand style information along the chain of thought, enabling the continual evolution of styles. Specifically, by progressively refining style descriptions and guiding the diverse evolution of styles, this approach enables more accurate simulation of various style characteristics and helps the model gradually learn and adapt to subtle differences between styles. Additionally, it exposes the model to a broader range of style features with different data distributions, thereby enhancing its generalization capability in unseen domains. The significant performance gains over five adverse-weather scenarios and the Real to Art benchmark demonstrate the superiorities of our method.

cs.CV↗

arXiv2025

MAC-VO: Metrics-aware Covariance for Learning-based Stereo Visual Odometry

We propose the MAC-VO, a novel learning-based stereo VO that leverages the learned metrics-aware matching uncertainty for dual purposes: selecting keypoint and weighing the residual in pose graph optimization. Compared to traditional geometric methods prioritizing texture-affluent features like edges, our keypoint selector employs the learned uncertainty to filter out the low-quality features based on global inconsistency. In contrast to the learning-based algorithms that model the scale-agnostic diagonal weight matrix for covariance, we design a metrics-aware covariance model to capture the spatial error during keypoint registration and the correlations between different axes. Integrating this covariance model into pose graph optimization enhances the robustness and reliability of pose estimation, particularly in challenging environments with varying illumination, feature density, and motion patterns. On public benchmark datasets, MAC-VO outperforms existing VO algorithms and even some SLAM algorithms in challenging environments. The covariance map also provides valuable information about the reliability of the estimated poses, which can benefit decision-making for autonomous systems.

cs.RO↗

arXiv2025

A thermal-noise-resilient microwave quantum network traversing 4 K

Quantum communication at microwave frequencies has been fundamentally constrained by the susceptibility of microwave photons to thermal noise, hindering their application in scalable quantum networks. Here we demonstrate a thermal-noise-resilient microwave quantum network that establishes coherent coupling between two superconducting qubits through a 4 K thermalized niobium-titanium transmission line. By overcoupling the communication channel to a cold load at 10 mK, we suppress the effective thermal occupancy of the channel to 0.06 photons through radiative cooling -- a two-order-of-magnitude reduction below ambient thermal noise. We then decouple the cold load and rapidly transfer microwave quantum states through the channel while it rethermalizes, achieving a 58.5% state transfer fidelity and a 52.3% Bell entanglement fidelity, both exceeding the classical communication threshold. Our architecture overcomes the temperature-compatibility barrier for microwave quantum systems, providing a scalable framework for distributed quantum computing and enabling hybrid quantum networks with higher-temperature semiconductor or photonic platforms.

quant-ph↗

arXiv2025

Constructing $(h,d)$ cooperative MSR codes with sub-packetization $(d-k+h)(d-k+1)^{\lceil n/2 \rceil}$

We address the multi-node failure repair challenges for MDS array codes. Presently, two primary models are employed for multi-node repairs: the centralized model where all failed nodes are restored in a singular data center, and the cooperative model where failed nodes acquire data from auxiliary nodes and collaborate amongst themselves for the repair process.This paper focuses on the cooperative model, and we provide explicit constructions of optimal MDS array codes with $d$ helper nodes under this model. The sub-packetization level of our new codes is $(d-k+h)(d-k+1)^{\lceil n/2 \rceil}$ where $h$ is the number of failed nodes, $k$ the number of information nodes and $n$ the code length. This improves upon recent constructions given by Liu \emph{et al.} (IEEE Transactions on Information Theory, Vol. 69, 2023).

cs.IT↗

arXiv2025

Lower Bounds on the Sub-Packetization of Optimal-Access MSR Codes for Multiple-Node Repair

We establish lower bounds on the sub-packetization of optimal-access MSR codes in the context of multiple-node failures. These bounds generalize the tight bounds for single-node failure presented by Balaji et al. (IEEE Transactions on Information Theory, vol. 68, no. 10, 2022). Moreover, we utilize generating functions to provide a more refined analysis, further strengthening these bounds.

cs.IT↗