arXiv subjects

Xiao Liang

Publications and source records attributed to Xiao Liang.

At least 127 records · Page 7Linked to original sources

arXiv2025

Uncertainty-Driven Expert Control: Enhancing the Reliability of Medical Vision-Language Models

The rapid advancements in Vision Language Models (VLMs) have prompted the development of multi-modal medical assistant systems. Despite this progress, current models still have inherent probabilistic uncertainties, often producing erroneous or unverified responses-an issue with serious implications in medical applications. Existing methods aim to enhance the performance of Medical Vision Language Model (MedVLM) by adjusting model structure, fine-tuning with high-quality data, or through preference fine-tuning. However, these training-dependent strategies are costly and still lack sufficient alignment with clinical expertise. To address these issues, we propose an expert-in-the-loop framework named Expert-Controlled Classifier-Free Guidance (Expert-CFG) to align MedVLM with clinical expertise without additional training. This framework introduces an uncertainty estimation strategy to identify unreliable outputs. It then retrieves relevant references to assist experts in highlighting key terms and applies classifier-free guidance to refine the token embeddings of MedVLM, ensuring that the adjusted outputs are correct and align with expert highlights. Evaluations across three medical visual question answering benchmarks demonstrate that the proposed Expert-CFG, with 4.2B parameters and limited expert annotations, outperforms state-of-the-art models with 13B parameters. The results demonstrate the feasibility of deploying such a system in resource-limited settings for clinical use.

cs.CV↗

arXiv2025

CheXPO: Preference Optimization for Chest X-ray VLMs with Counterfactual Rationale

Vision-language models (VLMs) are prone to hallucinations that critically compromise reliability in medical applications. While preference optimization can mitigate these hallucinations through clinical feedback, its implementation faces challenges such as clinically irrelevant training samples, imbalanced data distributions, and prohibitive expert annotation costs. To address these challenges, we introduce CheXPO, a Chest X-ray Preference Optimization strategy that combines confidence-similarity joint mining with counterfactual rationale. Our approach begins by synthesizing a unified, fine-grained multi-task chest X-ray visual instruction dataset across different question types for supervised fine-tuning (SFT). We then identify hard examples through token-level confidence analysis of SFT failures and use similarity-based retrieval to expand hard examples for balancing preference sample distributions, while synthetic counterfactual rationales provide fine-grained clinical preferences, eliminating the need for additional expert input. Experiments show that CheXPO achieves 8.93% relative performance gain using only 5% of SFT samples, reaching state-of-the-art performance across diverse clinical tasks and providing a scalable, interpretable solution for real-world radiology applications.

cs.CV↗

arXiv2025

SAILViT: Towards Robust and Generalizable Visual Backbones for MLLMs via Gradual Feature Refinement

Vision Transformers (ViTs) are essential as foundation backbones in establishing the visual comprehension capabilities of Multimodal Large Language Models (MLLMs). Although most ViTs achieve impressive performance through image-text pair-based contrastive learning or self-supervised mechanisms, they struggle to engage in connector-based co-training directly with LLMs due to potential parameter initialization conflicts and modality semantic gaps. To address the above challenges, this paper proposes SAILViT, a gradual feature learning-enhanced ViT for facilitating MLLMs to break through performance bottlenecks in complex multimodal interactions. SAILViT achieves coarse-to-fine-grained feature alignment and world knowledge infusion with gradual feature refinement, which better serves target training demands. We perform thorough empirical analyses to confirm the powerful robustness and generalizability of SAILViT across different dimensions, including parameter sizes, model architectures, training strategies, and data scales. Equipped with SAILViT, existing MLLMs show significant and consistent performance improvements on the OpenCompass benchmark across extensive downstream tasks. SAILViT series models are released at https://huggingface.co/BytedanceDouyinContent.

cs.CV↗

arXiv2025

From System 1 to System 2: A Survey of Reasoning Large Language Models

Achieving human-level intelligence requires refining the transition from the fast, intuitive System 1 to the slower, more deliberate System 2 reasoning. While System 1 excels in quick, heuristic decisions, System 2 relies on logical reasoning for more accurate judgments and reduced biases. Foundational Large Language Models (LLMs) excel at fast decision-making but lack the depth for complex reasoning, as they have not yet fully embraced the step-by-step analysis characteristic of true System 2 thinking. Recently, reasoning LLMs like OpenAI's o1/o3 and DeepSeek's R1 have demonstrated expert-level performance in fields such as mathematics and coding, closely mimicking the deliberate reasoning of System 2 and showcasing human-like cognitive abilities. This survey begins with a brief overview of the progress in foundational LLMs and the early development of System 2 technologies, exploring how their combination has paved the way for reasoning LLMs. Next, we discuss how to construct reasoning LLMs, analyzing their features, the core methods enabling advanced reasoning, and the evolution of various reasoning LLMs. Additionally, we provide an overview of reasoning benchmarks, offering an in-depth comparison of the performance of representative reasoning LLMs. Finally, we explore promising directions for advancing reasoning LLMs and maintain a real-time \href{https://github.com/zzli2022/Awesome-Slow-Reason-System}{GitHub Repository} to track the latest developments. We hope this survey will serve as a valuable resource to inspire innovation and drive progress in this rapidly evolving field.

cs.AI↗

arXiv2025

TL;DR: Too Long, Do Re-weighting for Efficient LLM Reasoning Compression

Large Language Models (LLMs) have recently achieved remarkable progress by leveraging Reinforcement Learning and extended Chain-of-Thought (CoT) techniques. However, the challenge of performing efficient language reasoning--especially during inference with extremely long outputs--has drawn increasing attention from the research community. In this work, we propose a dynamic ratio-based training pipeline that does not rely on sophisticated data annotations or interpolation between multiple models. We continuously balance the weights between the model's System-1 and System-2 data to eliminate redundant reasoning processes while preserving the model's reasoning capability. We validate our approach across models on DeepSeek-R1-Distill-7B and DeepSeek-R1-Distill-14B and on a diverse set of benchmarks with varying difficulty levels. Our method significantly reduces the number of output tokens by nearly 40% while maintaining the accuracy of the reasoning. Our code and data will be available soon.

cs.CL↗

arXiv2025

SwS: Self-aware Weakness-driven Problem Synthesis in Reinforcement Learning for LLM Reasoning

Reinforcement Learning with Verifiable Rewards (RLVR) has proven effective for training large language models (LLMs) on complex reasoning tasks, such as mathematical problem solving. A prerequisite for the scalability of RLVR is a high-quality problem set with precise and verifiable answers. However, the scarcity of well-crafted human-labeled math problems and limited-verification answers in existing distillation-oriented synthetic datasets limit their effectiveness in RL. Additionally, most problem synthesis strategies indiscriminately expand the problem set without considering the model's capabilities, leading to low efficiency in generating useful questions. To mitigate this issue, we introduce a Self-aware Weakness-driven problem Synthesis framework (SwS) that systematically identifies model deficiencies and leverages them for problem augmentation. Specifically, we define weaknesses as questions that the model consistently fails to learn through its iterative sampling during RL training. We then extract the core concepts from these failure cases and synthesize new problems to strengthen the model's weak areas in subsequent augmented training, enabling it to focus on and gradually overcome its weaknesses. Without relying on external knowledge distillation, our framework enables robust generalization byempowering the model to self-identify and address its weaknesses in RL, yielding average performance gains of 10.0% and 7.7% on 7B and 32B models across eight mainstream reasoning benchmarks.

cs.LG↗

arXiv2025

Scalable Vision Language Model Training via High Quality Data Curation

In this paper, we introduce SAIL-VL (ScAlable Vision Language Model TraIning via High QuaLity Data Curation), an open-source vision language model (VLM) series achieving state-of-the-art (SOTA) performance in 2B and 8B parameters. The following three key improvements contribute to SAIL-VL's leading performance: (1) Scalable high-quality visual understanding data construction: We implement a data construction pipeline to enable hundred-million-scale high-quality recaption data annotation. The resulted dataset SAIL-Caption is validated to be of the highest data quality compared with opensource datasets. (2) Scalable Pretraining with High-Quality Visual Understanding Data: We scale SAIL-VL's pretraining budget up to 655B tokens and show that even a 2B VLM benefits from scaled up training data sizes, exhibiting logarithmic data size scaling laws in benchmark performance. (3) Scalable SFT via data quantity and complexity scaling: We curate a high-quality SFT dataset collection with leading data quantity scaling effectiveness and demonstrate that training with progressively higher-complexity data surpasses baseline one-stage training by a large margin. SAIL-VL series models achieve the highest average score in 18 widely used VLM benchmarks in our evaluation, with the 2B model takes the top position over VLMs of comparable sizes on OpenCompass 2024 (https://rank.opencompass.org.cn/leaderboard-multimodal), demonstrating robust visual comprehension abilities. SAIL-VL series models are released at HuggingFace (https://huggingface.co/BytedanceDouyinContent).

cs.CV↗

arXiv2025

MorphoCopter: Design, Modeling, and Control of a New Transformable Quad-Bi Copter

This paper presents a novel morphing quadrotor, named MorphoCopter, covering its design, modeling, control, and experimental tests. It features a unique single rotary joint that enables rapid transformation into an ultra-narrow profile. Although quadrotors have seen widespread adoption in applications such as cinematography, agriculture, and disaster management with increasingly sophisticated control systems, their hardware configurations have remained largely unchanged, limiting their capabilities in certain environments. Our design addresses this by enabling the hardware configuration to change on the fly when required. In standard flight mode, the MorphoCopter adopts an X configuration, functioning as a traditional quadcopter, but can quickly fold into a stacked bicopters arrangement or any configuration in between. Existing morphing designs often sacrifice controllability in compact configurations or rely on complex multi-joint systems. Moreover, our design achieves a greater width reduction than any existing solution. We develop a new inertia and control-action aware adaptive control system that maintains robust performance across all rotary-joint configurations. The prototype can reduce its width from 447 mm to 138 mm (nearly 70\% reduction) in just a few seconds. We validated the MorphoCopter through rigorous simulations and a comprehensive series of flight experiments, including robustness tests, trajectory tracking, and narrow-gap passing tests.

cs.RO↗

arXiv2025

Brightness-Invariant Tracking Estimation in Tagged MRI

Magnetic resonance (MR) tagging is an imaging technique for noninvasively tracking tissue motion in vivo by creating a visible pattern of magnetization saturation (tags) that deforms with the tissue. Due to longitudinal relaxation and progression to steady-state, the tags and tissue brightnesses change over time, which makes tracking with optical flow methods error-prone. Although Fourier methods can alleviate these problems, they are also sensitive to brightness changes as well as spectral spreading due to motion. To address these problems, we introduce the brightness-invariant tracking estimation (BRITE) technique for tagged MRI. BRITE disentangles the anatomy from the tag pattern in the observed tagged image sequence and simultaneously estimates the Lagrangian motion. The inherent ill-posedness of this problem is addressed by leveraging the expressive power of denoising diffusion probabilistic models to represent the probabilistic distribution of the underlying anatomy and the flexibility of physics-informed neural networks to estimate biologically-plausible motion. A set of tagged MR images of a gel phantom was acquired with various tag periods and imaging flip angles to demonstrate the impact of brightness variations and to validate our method. The results show that BRITE achieves more accurate motion and strain estimates as compared to other state of the art methods, while also being resistant to tag fading.

eess.IV↗

arXiv2025

Single-shot 3D characterization the spatiotemporal optical vortex via a spatiotemporal wavefront sensor (STWFS)

The advent of spatiotemporal wave packets (STWPs), represented by spatiotemporal optical vortices (STOVs), has paved the way for the exploration in optics and photonics. To date, despite considerable efforts, a comprehensive and efficient practical means to characterizing wave packets with such complex structures is still lacking. In this study, we introduced a new method designed to achieve high-precision and high-throughput spatiotemporal wave packet measurements using a user-friendly set up. This method is based on a quadriwave lateral shearing interferometric wavefront sensor that utilizes wavelength division multiplexing, termed the "spatiotemporal wavefront sensor (STWFS)." Using this method, we have fabricated a compact prototype with 295 * 295 spatial pixels * 36 wavelength channels of 0.5 nm spectral resolution in a single frame. This STWFS enabled, for the first time, single-shot self-referenced spatiotemporal three-dimensional (3D) optical field characterizations of STOV pulses with transverse orbital angular momenta L of 1 and 2, and obtained the dynamic visualization of the focused propagation of STOV pulses. Furthermore, the STWFS provides a 1.87 nm (0.95%) root mean square (RMS) absolute accuracy for spatiotemporal phase reconstruction. This achievement represents the highest performance compared with other three-dimensional spatiotemporal metrology methods. As a spatiotemporal optical field characterization method, the STWFS offers ultrafast 3D diagnostics, contributing to spatiotemporal photonics and broader applications across different fields, such as light-matter interactions and optical communications.

physics.optics↗

arXiv2025

Toward Near-Space Communication Network in the 6G and Beyond Era

Near-space communication network (NS-ComNet), as an indispensable component of sixth-generation (6G) and beyond mobile communication systems and the space-air-ground-sea integrated network (SAGSIN), demonstrates unique advantages in wide-area coverage, long-endurance high-altitude operation, and highly flexible deployment. This paper presents a comprehensive review of NS-ComNet for 6G and beyond era. Specifically, by contrasting satellite, low-altitude unmanned-aerial-vehicle (UAV), and terrestrial communications, we first elucidate the background and motivation for integrating NS-ComNet into 6G network architectures. Subsequently, we review the developmental status of near-space platforms, including high-altitude balloons, solar-powered UAVs, and stratospheric airships, and analyze critical challenges faced by NS-ComNet. To address these challenges, the research focuses on key enabling technologies such as topology design, resource and handover management, multi-objective joint optimization, etc., with particular emphasis on artificial intelligence techniques for NS-ComNet. Finally, envisioning future intelligent collaborative networks that integrate NS-ComNet with satellite-UAV-terrestrial systems, we explore promising directions. This paper aims to provide technical insights and research foundations for the systematic construction of NS-ComNet and its deep deployment in the 6G and beyond era.

eess.SP↗

arXiv2025

Optimization-free Smooth Control Barrier Function for Polygonal Collision Avoidance

Polygonal collision avoidance (PCA) is short for the problem of collision avoidance between two polygons (i.e., polytopes in planar) that own their dynamic equations. This problem suffers the inherent difficulty in dealing with non-smooth boundaries and recently optimization-defined metrics, such as signed distance field (SDF) and its variants, have been proposed as control barrier functions (CBFs) to tackle PCA problems. In contrast, we propose an optimization-free smooth CBF method in this paper, which is computationally efficient and proved to be nonconservative. It is achieved by three main steps: a lower bound of SDF is expressed as a nested Boolean logic composition first, then its smooth approximation is established by applying the latest log-sum-exp method, after which a specified CBF-based safety filter is proposed to address this class of problems. To illustrate its wide applications, the optimization-free smooth CBF method is extended to solve distributed collision avoidance of two underactuated nonholonomic vehicles and drive an underactuated container crane to avoid a moving obstacle respectively, for which numerical simulations are also performed.

math.OC↗

arXiv2025

Production of doubly charmed tetraquark $T_{cc}$ via photon-photon fusion at electron-positron colliders

Within a phenomenological diquark fragmentation model, we study the production of doubly charmed tetraquark $T_{cc}$ via photon-photon fusion at electron-positron colliders. The production of $T_{cc}$ is divided into two steps: the perturbative production of heavy $(cc)$-diquark and its nonperturbative hadronization. Two diquark configurations of $(cc)[^3S_1]_{\bar{3}}$ and $(cc)[^1S_0]_{6}$ are considered, and the $(cc)[^3S_1]_{\bar{3}}$ state dominates the produciotn of $T_{cc}$. We discuss two hadronization models of $(cc)[^3S_1]_{\bar{3}}$ intermediate state into the tetraquark $T_{cc}$. It is found that it is promising to observe the tetraquark $T_{cc}$ via photon-photon fusion process both at the Circular Electron Positron Collider (CEPC) and the International Linear Collider (ILC). We find that the cross sections are sensitive to constituent charm quark mass of diquark, and they also have strong dependence on the hadronization models.

hep-ph↗

arXiv2025

ProT-GFDM: A Generative Fractional Diffusion Model for Protein Generation

This work introduces the generative fractional diffusion model for protein generation (ProT-GFDM), a novel generative framework that employs fractional stochastic dynamics for protein backbone structure modeling. This approach builds on the continuous-time score-based generative diffusion modeling paradigm, where data are progressively transformed into noise via a stochastic differential equation and reversed to generate structured samples. Unlike classical methods that rely on standard Brownian motion, ProT-GFDM employs a fractional stochastic process with superdiffusive properties to improve the capture of long-range dependencies in protein structures. Trained on protein fragments from the Protein Data Bank, ProT-GFDM outperforms conventional score-based models, achieving a 7.19% increase in density, a 5.66% improvement in coverage, and a 1.01% reduction in the Frechet inception distance. By integrating fractional dynamics with computationally efficient sampling, the proposed framework advances generative modeling for structured biological data, with implications for protein design and computational drug discovery.

q-bio.QM↗

arXiv2025

Automatic BLAS Offloading on Unified Memory Architecture: A Study on NVIDIA Grace-Hopper

Porting codes to GPU often requires major efforts. While several tools exist for automatically offload numerical libraries such as BLAS and LAPACK, they often prove impractical due to the high cost of mandatory data transfer. The new unified memory architecture in NVIDIA Grace-Hopper allows high bandwidth cache-coherent memory access of all memory from both CPU and GPU, potentially eliminating bottleneck faced in conventional architecture. This breakthrough opens up new avenues for application development and porting strategies. In this study, we introduce a new tool for automatic BLAS offload, the tool leverages the high speed cache coherent NVLink C2C interconnect in Grace-Hopper, and enables performant GPU offload for BLAS heavy applications with no code changes or recompilation. The tool was tested on two quantum chemistry or physics codes, great performance benefits were observed.

cs.DC↗

arXiv2025

RINGO: Real-time Navigation with a Guiding Trajectory for Aerial Manipulators in Unknown Environments

Motion planning for aerial manipulators in constrained environments has typically been limited to known environments or simplified to that of multi-rotors, which leads to poor adaptability and overly conservative trajectories. This paper presents RINGO: Real-time Navigation with a Guiding Trajectory, a novel planning framework that enables aerial manipulators to navigate unknown environments in real time. The proposed method simultaneously considers the positions of both the multi-rotor and the end-effector. A pre-obtained multi-rotor trajectory serves as a guiding reference, allowing the end-effector to generate a smooth, collision-free, and workspace-compatible trajectory. Leveraging the convex hull property of B-spline curves, we theoretically guarantee that the trajectory remains within the reachable workspace. To the best of our knowledge, this is the first work that enables real-time navigation of aerial manipulators in unknown environments. The simulation and experimental results show the effectiveness of the proposed method. The proposed method generates less conservative trajectories than approaches that consider only the multi-rotor.

cs.RO↗

arXiv2025

Adaptive RISE Control for Dual-Arm Unmanned Aerial Manipulator Systems with Deep Neural Networks

The unmanned aerial manipulator system, consisting of a multirotor UAV (unmanned aerial vehicle) and a manipulator, has attracted considerable interest from researchers. Nevertheless, the operation of a dual-arm manipulator poses a dynamic challenge, as the CoM (center of mass) of the system changes with manipulator movement, potentially impacting the multirotor UAV. Additionally, unmodeled effects, parameter uncertainties, and external disturbances can significantly degrade control performance, leading to unforeseen dangers. To tackle these issues, this paper proposes a nonlinear adaptive RISE (robust integral of the sign of the error) controller based on DNN (deep neural network). The first step involves establishing the kinematic and dynamic model of the dual-arm aerial manipulator. Subsequently, the adaptive RISE controller is proposed with a DNN feedforward term to effectively address both internal and external challenges. By employing Lyapunov techniques, the asymptotic convergence of the tracking error signals are guaranteed rigorously. Notably, this paper marks a pioneering effort by presenting the first DNN-based adaptive RISE controller design accompanied by a comprehensive stability analysis. To validate the practicality and robustness of the proposed control approach, several groups of actual hardware experiments are conducted. The results confirm the efficacy of the developed methodology in handling real-world scenarios, thereby offering valuable insights into the performance of the dual-arm aerial manipulator system.

cs.RO↗

arXiv2025

The Black-Box Simulation Barrier Persists in a Fully Quantum World

Zero-Knowledge (ZK) protocols have been intensely studied due to their fundamental importance and versatility. However, quantum information's inherent differences significantly alter the landscape, necessitating a re-examination of ZK designs. A crucial aspect is round complexity, linked to $\textit{simulation}$, which forms the foundation of ZK definition and security proofs. In the $\textit{post-quantum}$ setting, where honest parties and channels are classical but adversaries quantum, Chia et al. [FOCS'21] showed constant-round $\textit{black-box-simulatable}$ ZK arguments (BBZK) for $\mathbf{NP}$ are impossible unless $\mathbf{NP} \subseteq \mathbf{BQP}$. But this problem remains open when all parties and communication are quantum. Indeed, this problem interests the broader theory of quantum computing. Investigating how quantum power alters tasks like the $\textit{unconditional}$ security of QKD and incorporating OT in MiniQCrypt has been crucial. Moreover, quantum communication has enabled round compression for commitments and interactive arguments. Along this line, understanding if quantum computing could fundamentally change ZK protocols is vital. We resolved this problem by proving that only languages in $\mathbf{BQP}$ admit constant-round $\textit{fully-quantum}$ BBZK. This result holds significant implications. Firstly, it illuminates the nature of quantum zero-knowledge and provides valuable insights for designing future protocols in the quantum realm. Secondly, it relates ZK round complexity with the intriguing problem of $\mathbf{BQP}$ vs $\mathbf{QMA}$, which is out of the reach of previous analogue impossibility results in the classical or post-quantum setting. Lastly, it justifies the need for the $\textit{non-black-box}$ simulation techniques or the relaxed security notions employed in existing constant-round fully-quantum BBZK protocols.

quant-ph↗