arXiv subjects

Xin Zhao

Publications and source records attributed to Xin Zhao.

At least 73 records · Page 4Linked to original sources

arXiv2025

Wav2Sem: Plug-and-Play Audio Semantic Decoupling for 3D Speech-Driven Facial Animation

In 3D speech-driven facial animation generation, existing methods commonly employ pre-trained self-supervised audio models as encoders. However, due to the prevalence of phonetically similar syllables with distinct lip shapes in language, these near-homophone syllables tend to exhibit significant coupling in self-supervised audio feature spaces, leading to the averaging effect in subsequent lip motion generation. To address this issue, this paper proposes a plug-and-play semantic decorrelation module-Wav2Sem. This module extracts semantic features corresponding to the entire audio sequence, leveraging the added semantic information to decorrelate audio encodings within the feature space, thereby achieving more expressive audio features. Extensive experiments across multiple Speech-driven models indicate that the Wav2Sem module effectively decouples audio features, significantly alleviating the averaging effect of phonetically similar syllables in lip shape generation, thereby enhancing the precision and naturalness of facial animations. Our source code is available at https://github.com/wslh852/Wav2Sem.git.

cs.SD↗

arXiv2025

Position Dependent Prediction Combination For Intra-Frame Video Coding

Intra-frame prediction in the High Efficiency Video Coding (HEVC) standard can be empirically improved by applying sets of recursive two-dimensional filters to the predicted values. However, this approach does not allow (or complicates significantly) the parallel computation of pixel predictions. In this work we analyze why the recursive filters are effective, and use the results to derive sets of non-recursive predictors that have superior performance. We present an extension to HEVC intra prediction that combines values predicted using non-filtered and filtered (smoothed) reference samples, depending on the prediction mode, and block size. Simulations using the HEVC common test conditions show that a 2.0% bit rate average reduction can be achieved compared to HEVC, for All Intra (AI) configurations.

eess.IV↗

arXiv2025

Flexible Sampling for Long-tailed Skin Lesion Classification

Most of the medical tasks naturally exhibit a long-tailed distribution due to the complex patient-level conditions and the existence of rare diseases. Existing long-tailed learning methods usually treat each class equally to re-balance the long-tailed distribution. However, considering that some challenging classes may present diverse intra-class distributions, re-balancing all classes equally may lead to a significant performance drop. To address this, in this paper, we propose a curriculum learning-based framework called Flexible Sampling for the long-tailed skin lesion classification task. Specifically, we initially sample a subset of training data as anchor points based on the individual class prototypes. Then, these anchor points are used to pre-train an inference model to evaluate the per-class learning difficulty. Finally, we use a curriculum sampling module to dynamically query new samples from the rest training samples with the learning difficulty-aware sampling probability. We evaluated our model against several state-of-the-art methods on the ISIC dataset. The results with two long-tailed settings have demonstrated the superiority of our proposed training strategy, which achieves a new benchmark for long-tailed skin lesion classification.

cs.CV↗

arXiv2025

Highly Efficient Non-Separable Transforms for Next Generation Video Coding

For the last few decades, the application of signal-adaptive transform coding to video compression has been stymied by the large computational complexity of matrix-based solutions. In this paper, we propose a novel parametric approach to greatly reduce the complexity without degrading the compression performance. In our approach, instead of following the conventional technique of identifying full transform matrices that yield best compression efficiency, we look for the best transform parameters defining a new class of transforms, called HyGTs, which have low complexity implementations that are easy to parallelize. The proposed HyGTs are implemented as an extension of High Efficiency Video Coding (HEVC), and our comprehensive experimental results demonstrate that proposed HyGTs improve average coding gain by 6% bit rate reduction, while using 6.8 times less memory than KLT matrices.

eess.IV↗

arXiv2025

C-3PO: Compact Plug-and-Play Proxy Optimization to Achieve Human-like Retrieval-Augmented Generation

Retrieval-augmented generation (RAG) systems face a fundamental challenge in aligning independently developed retrievers and large language models (LLMs). Existing approaches typically involve modifying either component or introducing simple intermediate modules, resulting in practical limitations and sub-optimal performance. Inspired by human search behavior -- typically involving a back-and-forth process of proposing search queries and reviewing documents, we propose C-3PO, a proxy-centric framework that facilitates communication between retrievers and LLMs through a lightweight multi-agent system. Our framework implements three specialized agents that collaboratively optimize the entire RAG pipeline without altering the retriever and LLMs. These agents work together to assess the need for retrieval, generate effective queries, and select information suitable for the LLMs. To enable effective multi-agent coordination, we develop a tree-structured rollout approach for reward credit assignment in reinforcement learning. Extensive experiments in both in-domain and out-of-distribution scenarios demonstrate that C-3PO significantly enhances RAG performance while maintaining plug-and-play flexibility and superior generalization capabilities.

cs.CL↗

arXiv2025

FIOVA: A Multi-Annotator Benchmark for Human-Aligned Video Captioning

Despite rapid progress in large vision-language models (LVLMs), existing video caption benchmarks remain limited in evaluating their alignment with human understanding. Most rely on a single annotation per video and lexical similarity-based metrics, failing to capture the variability in human perception and the cognitive importance of events. These limitations hinder accurate diagnosis of model capabilities in producing coherent, complete, and human-aligned descriptions. To address this, we introduce FIOVA (Five-In-One Video Annotations), a human-centric benchmark tailored for evaluation. It comprises 3,002 real-world videos (about 33.6s each), each annotated independently by five annotators. This design enables modeling of semantic diversity and inter-subjective agreement, offering a richer foundation for measuring human-machine alignment. We further propose FIOVA-DQ, an event-level evaluation metric that incorporates cognitive weights derived from annotator consensus, providing fine-grained assessment of event relevance and semantic coverage. Leveraging FIOVA, we conduct a comprehensive evaluation of nine representative LVLMs and introduce a complexity-aware analysis framework based on inter-annotator variation (CV). This reveals consistency gaps across difficulty levels and identifies structural issues such as event under-description and template convergence. Our results highlight FIOVA's diagnostic value for understanding LVLM behavior under varying complexity, setting a new standard for cognitively aligned evaluation in long-video captioning. The benchmark, annotations, metric, and model outputs are publicly released to support future evaluation-driven research in video understanding. More detailed information can be found at https://huuuuusy.github.io/fiova/.

cs.CV↗

arXiv2025

ARMOR: Adaptive Meshing with Reinforcement Optimization for Real-time 3D Monitoring in Unexposed Scenes

Unexposed environments, such as lava tubes, mines, and tunnels, are among the most complex yet strategically significant domains for scientific exploration and infrastructure development. Accurate and real-time 3D meshing of these environments is essential for applications including automated structural assessment, robotic-assisted inspection, and safety monitoring. Implicit neural Signed Distance Fields (SDFs) have shown promising capabilities in online meshing; however, existing methods often suffer from large projection errors and rely on fixed reconstruction parameters, limiting their adaptability to complex and unstructured underground environments such as tunnels, caves, and lava tubes. To address these challenges, this paper proposes ARMOR, a scene-adaptive and reinforcement learning-based framework for real-time 3D meshing in unexposed environments. The proposed method was validated across more than 3,000 meters of underground environments, including engineered tunnels, natural caves, and lava tubes. Experimental results demonstrate that ARMOR achieves superior performance in real-time mesh reconstruction, reducing geometric error by 3.96\% compared to state-of-the-art baselines, while maintaining real-time efficiency. The method exhibits improved robustness, accuracy, and adaptability, indicating its potential for advanced 3D monitoring and mapping in challenging unexposed scenarios. The project page can be found at: https://yizhezhang0418.github.io/armor.github.io/

cs.RO↗

arXiv2025

Large Language Models to Accelerate Organic Chemistry Synthesis

Chemical synthesis, as a foundational methodology in the creation of transformative molecules, exerts substantial influence across diverse sectors from life sciences to materials and energy. Current chemical synthesis practices emphasize laborious and costly trial-and-error workflows, underscoring the urgent need for advanced AI assistants. Nowadays, large language models (LLMs), typified by GPT-4, have been introduced as an efficient tool to facilitate scientific research. Here, we present Chemma, a fully fine-tuned LLM with 1.28 million pairs of Q&A about reactions, as an assistant to accelerate organic chemistry synthesis. Chemma surpasses the best-known results in multiple chemical tasks, e.g., single-step retrosynthesis and yield prediction, which highlights the potential of general AI for organic chemistry. Via predicting yields across the experimental reaction space, Chemma significantly improves the reaction exploration capability of Bayesian optimization. More importantly, integrated in an active learning framework, Chemma exhibits advanced potential for autonomous experimental exploration and optimization in open reaction spaces. For an unreported Suzuki-Miyaura cross-coupling reaction of cyclic aminoboronates and aryl halides for the synthesis of $α$-Aryl N-heterocycles, the human-AI collaboration successfully explored suitable ligand and solvent (1,4-dioxane) within only 15 runs, achieving an isolated yield of 67%. These results reveal that, without quantum-chemical calculations, Chemma can comprehend and extract chemical insights from reaction data, in a manner akin to human experts. This work opens avenues for accelerating organic chemistry synthesis with adapted large language models.

physics.chem-ph↗

arXiv2025

Eco-efficiency as a Catalyst for Citizen Co-production: Evidence from Chinese Cities

We examine whether higher eco-efficiency encourages local governments to co-produce environmental solutions with citizens. Using Chinese provincial data and advanced textual analysis, we find that high eco-efficiency strongly predicts more collaborative responses to environmental complaints. Causal inference suggests that crossing a threshold of eco-efficiency increases co-production probabilities by about 24 percentage points, indicating eco-efficiency's potential as a catalyst for participatory environmental governance.

econ.GN↗

arXiv2025

POD: Predictive Object Detection with Single-Frame FMCW LiDAR Point Cloud

LiDAR-based 3D object detection is a fundamental task in the field of autonomous driving. This paper explores the unique advantage of Frequency Modulated Continuous Wave (FMCW) LiDAR in autonomous perception. Given a single frame FMCW point cloud with radial velocity measurements, we expect that our object detector can detect the short-term future locations of objects using only the current frame sensor data and demonstrate a fast ability to respond to intermediate danger. To achieve this, we extend the standard object detection task to a novel task named predictive object detection (POD), which aims to predict the short-term future location and dimensions of objects based solely on current observations. Typically, a motion prediction task requires historical sensor information to process the temporal contexts of each object, while our detector's avoidance of multi-frame historical information enables a much faster response time to potential dangers. The core advantage of FMCW LiDAR lies in the radial velocity associated with every reflected point. We propose a novel POD framework, the core idea of which is to generate a virtual future point using a ray casting mechanism, create virtual two-frame point clouds with the current and virtual future frames, and encode these two-frame voxel features with a sparse 4D encoder. Subsequently, the 4D voxel features are separated by temporal indices and remapped into two Bird's Eye View (BEV) features: one decoded for standard current frame object detection and the other for future predictive object detection. Extensive experiments on our in-house dataset demonstrate the state-of-the-art standard and predictive detection performance of the proposed POD framework.

cs.CV↗

arXiv2025

ConfEviSurrogate: A Conformalized Evidential Surrogate Model for Uncertainty Quantification

Surrogate models, crucial for approximating complex simulation data across sciences, inherently carry uncertainties that range from simulation noise to model prediction errors. Without rigorous uncertainty quantification, predictions become unreliable and hence hinder analysis. While methods like Monte Carlo dropout and ensemble models exist, they are often costly, fail to isolate uncertainty types, and lack guaranteed coverage in prediction intervals. To address this, we introduce ConfEviSurrogate, a novel Conformalized Evidential Surrogate Model that can efficiently learn high-order evidential distributions, directly predict simulation outcomes, separate uncertainty sources, and provide prediction intervals. A conformal prediction-based calibration step further enhances interval reliability to ensure coverage and improve efficiency. Our ConfEviSurrogate demonstrates accurate predictions and robust uncertainty estimates in diverse simulations, including cosmology, ocean dynamics, and fluid dynamics.

stat.ML↗

arXiv2025

Mechanisms of Dual-Band Emission in Sb-Doped Rare-Earth Phosphates Revealed

The Sb$^{3+}$ ion has garnered significant interest due to its effectiveness in boosting the optical properties of host materials. Among the interesting phenomena is the commonly observed dual-band emission, which has often been interpreted by adopting the phenomenological model that explains the dual-band emission (``ultraviolet band'' and ``visible band'') in Sb-doped $L$PO$_{4}$ ($L$ = Sc, Y, Lu). However, the model for Sb-doped $L$PO$_{4}$ series itself has not been well understood theoretically. In this work, we employ first-principles calculations combined with group-theory analysis to clarify the underlying physical mechanism behind dual-band emission in Sb-doped $L$PO$_{4}$ series. We demonstrate that the dual-band arises from two excited-state equilibrium structures, one exhibits a relatively small distortion with respect to the ground-state equilibrium structure, while the other displays a significantly larger distortion, characteristic of an ``off-center'' configuration. The deviations from the ground-state configuration are dominated by two distinct vibrational modes, $b_2$ and $e$ modes, involving the Jahn-Teller effect and the pseudo Jahn-Teller effect, respectively. Furthermore, charge transition levels and energy barriers calculated using the climbing image nudged elastic band (CI-NEB) method have aided in understanding the relaxation between the two excited-state configurations and the property changes across the Sc, Y, and Lu series. These insights provide a basis for understanding the exotic properties of Sb$^{3+}$ in other hosts and may facilitate the design of optical materials in a broader range of systems involving Sb$^{3+}$ ions.

cond-mat.mtrl-sci↗

arXiv2025

Phase transitions in a holographic s+d model from the 4D Einstein-Gauss-Bonnet gravity

In this work, the phase structure of a holographic s+d model with quartic potential terms from the 4D Einstein-Gauss-Bonnet gravity is studied in the probe limit. We first show the $q_d-μ$ phase diagram with a very small value of the Gauss-Bonnet coefficient $α=1\times10^{-7}$ and in absence of the quartic terms to locate the suitable choice of the value of $q_d$, where the system admits coexistent s+d solutions. Then we consider various values of the Gauss-Bonnet coefficient $α$ and present the $α-μ$ phase diagram to show the influence of the Gauss-Bonnet term on the phase structure. We also give an example of the reentrant phase transition which is also realized in the holographic s+s and s+p models. After that we confirm the universality of the influence of the quartic term with coefficient $λ_d$ on the d-wave solutions, which is similar to the case of s-wave and p-wave solutions previously studied in the s+p model. Finally we give the dependence of the special values of the quartic term coefficient $λ_d$ on the Gauss-Bonnet coefficient $α$, below which the d-wave condensate grows to an opposite direction at the (quasi-)critical point, which is useful in realizing 1st order phase transitions in further studies of the holographic d-wave superfluids.

hep-th↗

arXiv2025

Optimizing AUV speed dynamics with a data-driven Koopman operator approach

Autonomous Underwater Vehicles (AUVs) play an essential role in modern ocean exploration, and their speed control systems are fundamental to their efficient operation. Like many other robotic systems, AUVs exhibit multivariable nonlinear dynamics and face various constraints, including state limitations, input constraints, and constraints on the increment input, making controller design challenging and requiring significant effort and time. This paper addresses these challenges by employing a data-driven Koopman operator theory combined with Model Predictive Control (MPC), which takes into account the aforementioned constraints. The proposed approach not only ensures the performance of the AUV under state and input limitations but also considers the variation in incremental input to prevent rapid and potentially damaging changes to the vehicle's operation. Additionally, we develop a platform based on ROS2 and Gazebo to validate the effectiveness of the proposed algorithms, providing new control strategies for underwater vehicles against the complex and dynamic nature of underwater environments.

eess.SY↗

arXiv2025

Every FLOP Counts: Scaling a 300B Mixture-of-Experts LING LLM without Premium GPUs

In this technical report, we tackle the challenges of training large-scale Mixture of Experts (MoE) models, focusing on overcoming cost inefficiency and resource limitations prevalent in such systems. To address these issues, we present two differently sized MoE large language models (LLMs), namely Ling-Lite and Ling-Plus (referred to as "Bailing" in Chinese, spelled Bǎilíng in Pinyin). Ling-Lite contains 16.8 billion parameters with 2.75 billion activated parameters, while Ling-Plus boasts 290 billion parameters with 28.8 billion activated parameters. Both models exhibit comparable performance to leading industry benchmarks. This report offers actionable insights to improve the efficiency and accessibility of AI development in resource-constrained settings, promoting more scalable and sustainable technologies. Specifically, to reduce training costs for large-scale MoE models, we propose innovative methods for (1) optimization of model architecture and training processes, (2) refinement of training anomaly handling, and (3) enhancement of model evaluation efficiency. Additionally, leveraging high-quality data generated from knowledge graphs, our models demonstrate superior capabilities in tool use compared to other models. Ultimately, our experimental findings demonstrate that a 300B MoE LLM can be effectively trained on lower-performance devices while achieving comparable performance to models of a similar scale, including dense and MoE models. Compared to high-performance devices, utilizing a lower-specification hardware system during the pre-training phase demonstrates significant cost savings, reducing computing costs by approximately 20%. The models can be accessed at https://huggingface.co/inclusionAI.

cs.LG↗

arXiv2025

Progress of the TianQin project

TianQin is a future space-based gravitational wave observatory targeting the frequency window of $10^{-4}$ Hz $\sim 1$ Hz. A large variety of gravitational wave sources are expected in this frequency band, including the merger of massive black hole binaries, the inspiral of extreme/intermediate mass ratio systems, stellar-mass black hole binaries, Galactic compact binaries, and so on. TianQin will consist of three Earth orbiting satellites on nearly identical orbits with orbital radii of about $10^5$ km. The satellites will form a normal triangle constellation whose plane is nearly perpendicular to the ecliptic plane. The TianQin project has been progressing smoothly following the ``0123" technology roadmap. In step ``0", the TianQin laser ranging station has been constructed and it has successfully ranged to all the five retro-reflectors on the Moon. In step ``1", the drag-free control technology has been tested and demonstrated using the TianQin-1 satellite. In step ``2", the inter-satellite laser interferometry technology will be tested using the pair of TianQin-2 satellites. The TianQin-2 mission has been officially approved and the satellites will be launched around 2026. In step ``3", i.e., the TianQin-3 mission, three identical satellites will be launched around 2035 to form the space-based gravitational wave detector, TianQin, and to start gravitational wave detection in space.

gr-qc↗

arXiv2025

Overview of EXL-50 Research Progress and Future Plan

XuanLong-50 (EXL-50) is the first medium-size spherical torus (ST) in China, with the toroidal field at major radius at 50 cm around 0.5T. CS-free and non-inductive current drive via electron cyclotron resonance heating (ECRH) was the main physics research issue for EXL-50. Discharges with plasma currents of 50 kA - 180 kA were routinely obtained in EXL-50, with the current flattop sustained for up to or beyond 2 s. The current drive effectiveness on EXL-50 was as high as 1 A/W for low-density discharges using 28GHz ECRH alone for heating power less than 200 kW. The plasma current reached Ip>80 kA for high-density (5*10e18m-2) discharges with 150 kW 28GHz ECRH. Higher performance discharge (Ip of about 120 kA and core density of about 1*10e19m-3) was achieved with 150 kW 50GHz ECRH. The plasma current in EXL-50 was mainly carried by the energetic electrons.Multi-fluid equilibrium model has been successfully applied to reconstruct the magnetic flux surface and the measured plasma parameters of the EXL-50 equilibrium. The physics mechanisms for the solenoid-free ECRH current drive and the energetic electrons has also been investigated. Preliminary experimental results show that 100 kW of lower hybrid current drive (LHCD) waves can drive 20 kA of plasma current. Several boron injection systems were installed and tested in EXL-50, including B2H6 gas puffing, boron powder injection, boron pellet injection. The research plan of EXL-50U, which is the upgrade machine of EXL-50, is also presented.

physics.plasm-ph↗

arXiv2025

Buster: Implanting Semantic Backdoor into Text Encoder to Mitigate NSFW Content Generation

The rise of deep learning models in the digital era has raised substantial concerns regarding the generation of Not-Safe-for-Work (NSFW) content. Existing defense methods primarily involve model fine-tuning and post-hoc content moderation. Nevertheless, these approaches largely lack scalability in eliminating harmful content, degrade the quality of benign image generation, or incur high inference costs. To address these challenges, we propose an innovative framework named \textit{Buster}, which injects backdoors into the text encoder to prevent NSFW content generation. Buster leverages deep semantic information rather than explicit prompts as triggers, redirecting NSFW prompts towards targeted benign prompts. Additionally, Buster employs energy-based training data generation through Langevin dynamics for adversarial knowledge augmentation, thereby ensuring robustness in harmful concept definition. This approach demonstrates exceptional resilience and scalability in mitigating NSFW content. Particularly, Buster fine-tunes the text encoder of Text-to-Image models within merely five minutes, showcasing its efficiency. Our extensive experiments denote that Buster outperforms nine state-of-the-art baselines, achieving a superior NSFW content removal rate of at least 91.2\% while preserving the quality of harmless images.

cs.CV↗