arXiv subjects

Bo Liu

Publications and source records attributed to Bo Liu.

At least 199 records · Page 11Linked to original sources

arXiv2025

GEMeX-RMCoT: An Enhanced Med-VQA Dataset for Region-Aware Multimodal Chain-of-Thought Reasoning

Medical visual question answering aims to support clinical decision-making by enabling models to answer natural language questions based on medical images. While recent advances in multi-modal learning have significantly improved performance, current methods still suffer from limited answer reliability and poor interpretability, impairing the ability of clinicians and patients to understand and trust model outputs. To address these limitations, this work first proposes a Region-Aware Multimodal Chain-of-Thought (RMCoT) dataset, in which the process of producing an answer is preceded by a sequence of intermediate reasoning steps that explicitly ground relevant visual regions of the medical image, thereby providing fine-grained explainability. Furthermore, we introduce a novel verifiable reward mechanism for reinforcement learning to guide post-training, improving the alignment between the model's reasoning process and its final answer. Remarkably, our method achieves comparable performance using only one-eighth of the training data, demonstrating the efficiency and effectiveness of the proposal. The dataset is available at https://www.med-vqa.com/GEMeX/.

cs.CV↗

arXiv2025

Tunable Asymmetric Delay Attack in Quantum Clock Synchronization

Quantum clock synchronization underpins modern secure communications and critical infrastructure, yet its fundamental dependence on channel reciprocity introduces an exploitable vulnerability to asymmetric delay attacks. Current attack strategies rely on static delays, limiting their ability to target application-specific stability requirements. Here, we propose a tunable asymmetric delay attack (T-ADA) that dynamically controls delay parameters to induce manipulate synchronization accuracy. Through experimental implementation, we demonstrate how tailored attack trajectories can selectively compromise system stability across different scenarios. This work uncovers key vulnerabilities in synchronization protocols under customizable attacks and provide a foundation for developing secure and resilient quantum clock synchronization systems.

quant-ph↗

arXiv2025

Improving Rectified Flow with Boundary Conditions

Rectified Flow offers a simple and effective approach to high-quality generative modeling by learning a velocity field. However, we identify a limitation in directly modeling the velocity with an unconstrained neural network: the learned velocity often fails to satisfy certain boundary conditions, leading to inaccurate velocity field estimations that deviate from the desired ODE. This issue is particularly critical during stochastic sampling at inference, as the score function's errors are amplified near the boundary. To mitigate this, we propose a Boundary-enforced Rectified Flow Model (Boundary RF Model), in which we enforce boundary conditions with a minimal code modification. Boundary RF Model improves performance over vanilla RF model, demonstrating 8.01% improvement in FID score on ImageNet using ODE sampling and 8.98% improvement using SDE sampling.

cs.LG↗

arXiv2025

TGT: Text-Grounded Trajectories for Locally Controlled Video Generation

Text-to-video generation has advanced rapidly in visual fidelity, whereas standard methods still have limited ability to control the subject composition of generated scenes. Prior work shows that adding localized text control signals, such as bounding boxes or segmentation masks, can help. However, these methods struggle in complex scenarios and degrade in multi-object settings, offering limited precision and lacking a clear correspondence between individual trajectories and visual entities as the number of controllable objects increases. We introduce Text-Grounded Trajectories (TGT), a framework that conditions video generation on trajectories paired with localized text descriptions. We propose Location-Aware Cross-Attention (LACA) to integrate these signals and adopt a dual-CFG scheme to separately modulate local and global text guidance. In addition, we develop a data processing pipeline that produces trajectories with localized descriptions of tracked entities, and we annotate two million high quality video clips to train TGT. Together, these components enable TGT to use point trajectories as intuitive motion handles, pairing each trajectory with text to control both appearance and motion. Extensive experiments show that TGT achieves higher visual quality, more accurate text alignment, and improved motion controllability compared with prior approaches. Website: https://textgroundedtraj.github.io.

cs.CV↗

arXiv2025

Multi-View Semi-Supervised Label Distribution Learning with Local Structure Complementarity

Label distribution learning (LDL) is a paradigm that each sample is associated with a label distribution. At present, the existing approaches are proposed for the single-view LDL problem with labeled data, while the multi-view LDL problem with labeled and unlabeled data has not been considered. In this paper, we put forward the multi-view semi-supervised label distribution learning with local structure complementarity (MVSS-LDL) approach, which exploits the local nearest neighbor structure of each view and emphasizes the complementarity of local nearest neighbor structures in multiple views. Specifically speaking, we first explore the local structure of view $v$ by computing the $k$-nearest neighbors. As a result, the $k$-nearest neighbor set of each sample $\boldsymbol{x}_i$ in view $v$ is attained. Nevertheless, this $k$-nearest neighbor set describes only a part of the nearest neighbor information of sample $\boldsymbol{x}_i$. In order to obtain a more comprehensive description of sample $\boldsymbol{x}_i$'s nearest neighbors, we complement the nearest neighbor set in view $v$ by incorporating sample $\boldsymbol{x}_i$'s nearest neighbors in other views. Lastly, based on the complemented nearest neighbor set in each view, a graph learning-based multi-view semi-supervised LDL model is constructed. By considering the complementarity of local nearest neighbor structures, different views can mutually provide the local structural information to complement each other. To the best of our knowledge, this is the first attempt at multi-view LDL. Numerical studies have demonstrated that MVSS-LDL attains explicitly better classification performance than the existing single-view LDL methods.

cs.LG↗

arXiv2025

New Physics Search at the CEPC: a General Perspective

The Circular Electron-Positron Collider (CEPC), a proposed next-generation Higgs factory, provides new opportunities to explore physics beyond the Standard Model (SM). With its clean electron-positron collision environment and the ability to collect large samples of Higgs, W, and Z bosons, the CEPC enables precision measurements and searches for new physics. This white paper outlines the CEPC's discovery potential, including studies of exotic decays of the Higgs, Z, and top quarks, dark matter and dark sector phenomena, long-lived particles, supersymmetry, and neutrino-related signatures. Advanced detector technologies and reconstruction techniques, such as one-to-one correspondence reconstruction and jet origin identification, significantly improve sensitivity to rare and weakly interacting processes. The CEPC is particularly well suited to probe the electroweak phase transition and test models of electroweak baryogenesis and dark sector interactions. In addition, global fit analyses highlight the CEPC's complementary role in constraining a wide range of new physics scenarios. These features position the CEPC as a powerful tool for exploring the next frontier in fundamental particle physics in the post-Higgs discovery era.

hep-ex↗

arXiv2025

MAGREF: Masked Guidance for Any-Reference Video Generation with Subject Disentanglement

We tackle the task of any-reference video generation, which aims to synthesize videos conditioned on arbitrary types and combinations of reference subjects, together with textual prompts. This task faces persistent challenges, including identity inconsistency, entanglement among multiple reference subjects, and copy-paste artifacts. To address these issues, we introduce MAGREF, a unified and effective framework for any-reference video generation. Our approach incorporates masked guidance and a subject disentanglement mechanism, enabling flexible synthesis conditioned on diverse reference images and textual prompts. Specifically, masked guidance employs a region-aware masking mechanism combined with pixel-wise channel concatenation to preserve appearance features of multiple subjects along the channel dimension. This design preserves identity consistency and maintains the capabilities of the pre-trained backbone, without requiring any architectural changes. To mitigate subject confusion, we introduce a subject disentanglement mechanism which injects the semantic values of each subject derived from the text condition into its corresponding visual region. Additionally, we establish a four-stage data pipeline to construct diverse training pairs, effectively alleviating copy-paste artifacts. Extensive experiments on a comprehensive benchmark demonstrate that MAGREF consistently outperforms existing state-of-the-art approaches, paving the way for scalable, controllable, and high-fidelity any-reference video synthesis. Code and model can be found at: https://github.com/MAGREF-Video/MAGREF

cs.CV↗

arXiv2025

DialoSpeech: Dual-Speaker Dialogue Generation with LLM and Flow Matching

Recent advances in text-to-speech (TTS) synthesis, particularly those leveraging large language models (LLMs), have significantly improved expressiveness and naturalness. However, generating human-like, interactive dialogue speech remains challenging. Current systems face limitations due to the scarcity of dual-track data and difficulties in achieving naturalness, contextual coherence, and interactional dynamics, such as turn-taking, overlapping speech, and speaker consistency, in multi-turn conversations. To address these challenges, we propose DialoSpeech, a dual-track architecture combining a large language model with Chunked Flow Matching for expressive, human-like dialogue speech synthesis. DialoSpeech generates natural multi-turn conversations with coherent speaker turns and natural overlaps, supporting both Chinese and English and cross-lingual speech synthesis. We introduce a data processing pipeline to construct dual-track dialogue datasets, facilitating scalable training and experimental validation. Experiments show that our model outperforms baselines, offering a solution for generating human-like spoken dialogues. Audio samples are available at https://tiamojames.github.io/DialoSpeech

eess.AS↗

arXiv2025

Omni-Embed-Nemotron: A Unified Multimodal Retrieval Model for Text, Image, Audio, and Video

We present Omni-Embed-Nemotron, a unified multimodal retrieval embedding model developed to handle the increasing complexity of real-world information needs. While Retrieval-Augmented Generation (RAG) has significantly advanced language models by incorporating external knowledge, existing text-based retrievers rely on clean, structured input and struggle with the visually and semantically rich content found in real-world documents such as PDFs, slides, or videos. Recent work such as ColPali has shown that preserving document layout using image-based representations can improve retrieval quality. Building on this, and inspired by the capabilities of recent multimodal models such as Qwen2.5-Omni, we extend retrieval beyond text and images to also support audio and video modalities. Omni-Embed-Nemotron enables both cross-modal (e.g., text - video) and joint-modal (e.g., text - video+audio) retrieval using a single model. We describe the architecture, training setup, and evaluation results of Omni-Embed-Nemotron, and demonstrate its effectiveness in text, image, and video retrieval.

cs.CL↗

arXiv2025

The Era of Real-World Human Interaction: RL from User Conversations

We posit that to achieve continual model improvement and multifaceted alignment, future models must learn from natural human interaction. Current conversational models are aligned using pre-annotated, expert-generated human feedback. In this work, we introduce Reinforcement Learning from Human Interaction (RLHI), a paradigm that learns directly from in-the-wild user conversations. We develop two complementary methods: (1) RLHI with User-Guided Rewrites, which revises unsatisfactory model outputs based on users' natural-language follow-up responses, (2) RLHI with User-Based Rewards, which learns via a reward model conditioned on knowledge of the user's long-term interaction history (termed persona). Together, these methods link long-term user personas to turn-level preferences via persona-conditioned preference optimization. Trained on conversations derived from WildChat, both RLHI variants outperform strong baselines in personalization and instruction-following, and similar feedback enhances performance on reasoning benchmarks. These results suggest organic human interaction offers scalable, effective supervision for personalized alignment.

cs.AI↗

arXiv2025

Electronic-correlation-assisted charge stripe order in a Kagome superconductor

A central mystery in high-temperature cuprate superconductors is the coexistence of multiple exotic orders, which is presumably associated with strong electronic correlation. The ongoing interest in this enigmatic phenomenon is further energized when similar electronic orders and states emerge and coexist in less correlated Kagome superconductors. Here, by utilizing angle-resolved photoemission spectroscopy (ARPES), nuclear magnetic resonance (NMR) spectroscopy, scanning tunneling microscopy (STM) and first-principles calculations, we reveal the sudden emergence of a distinct short-range charge stripe order in Sn-doped CsV$_3$Sb$_5$ Kagome superconductors when the long-range $2 \times 2$ charge density wave order in pristine CsV$_3$Sb$_5$ is suppressed. This short-range stripe order features a modulation vector of approximately 1/3 along one of the three lattice directions, induces remarkable quasiparticle scattering between the original quasi-1D Kagome-d-bands and their replica of folding, and clearly suppresses the electron density of states at the Fermi level. Our first-principles calculations reveal that $3 \times 1$ supermodulation represents a hidden secondary instability in pristine CsV$_3$Sb$_5$. This instability is further enhanced by in-plane chemical pressure induced by Sn substitution, and coupled to the electronic correlation, leading to a unique charge stripe order in the system. As such, our results reveal a new route toward emergent electronic orders via cooperative interactions between the lattice and electronic degrees of freedom.

cond-mat.supr-con↗

arXiv2025

Dual-View Alignment Learning with Hierarchical-Prompt for Class-Imbalance Multi-Label Classification

Real-world datasets often exhibit class imbalance across multiple categories, manifesting as long-tailed distributions and few-shot scenarios. This is especially challenging in Class-Imbalanced Multi-Label Image Classification (CI-MLIC) tasks, where data imbalance and multi-object recognition present significant obstacles. To address these challenges, we propose a novel method termed Dual-View Alignment Learning with Hierarchical Prompt (HP-DVAL), which leverages multi-modal knowledge from vision-language pretrained (VLP) models to mitigate the class-imbalance problem in multi-label settings. Specifically, HP-DVAL employs dual-view alignment learning to transfer the powerful feature representation capabilities from VLP models by extracting complementary features for accurate image-text alignment. To better adapt VLP models for CI-MLIC tasks, we introduce a hierarchical prompt-tuning strategy that utilizes global and local prompts to learn task-specific and context-related prior knowledge. Additionally, we design a semantic consistency loss during prompt tuning to prevent learned prompts from deviating from general knowledge embedded in VLP models. The effectiveness of our approach is validated on two CI-MLIC benchmarks: MS-COCO and VOC2007. Extensive experimental results demonstrate the superiority of our method over SOTA approaches, achieving mAP improvements of 10.0\% and 5.2\% on the long-tailed multi-label image classification task, and 6.8\% and 2.9\% on the multi-label few-shot image classification task.

cs.CV↗

arXiv2025

DT-NeRF: A Diffusion and Transformer-Based Optimization Approach for Neural Radiance Fields in 3D Reconstruction

This paper proposes a Diffusion Model-Optimized Neural Radiance Field (DT-NeRF) method, aimed at enhancing detail recovery and multi-view consistency in 3D scene reconstruction. By combining diffusion models with Transformers, DT-NeRF effectively restores details under sparse viewpoints and maintains high accuracy in complex geometric scenes. Experimental results demonstrate that DT-NeRF significantly outperforms traditional NeRF and other state-of-the-art methods on the Matterport3D and ShapeNet datasets, particularly in metrics such as PSNR, SSIM, Chamfer Distance, and Fidelity. Ablation experiments further confirm the critical role of the diffusion and Transformer modules in the model's performance, with the removal of either module leading to a decline in performance. The design of DT-NeRF showcases the synergistic effect between modules, providing an efficient and accurate solution for 3D scene reconstruction. Future research may focus on further optimizing the model, exploring more advanced generative models and network architectures to enhance its performance in large-scale dynamic scenes.

cs.CV↗

arXiv2025

Unique Security and Privacy Threats of Large Language Models: A Comprehensive Survey

With the rapid development of artificial intelligence, large language models (LLMs) have made remarkable advancements in natural language processing. These models are trained on vast datasets to exhibit powerful language understanding and generation capabilities across various applications, including chatbots, and agents. However, LLMs have revealed a variety of privacy and security issues throughout their life cycle, drawing significant academic and industrial attention. Moreover, the risks faced by LLMs differ significantly from those encountered by traditional language models. Given that current surveys lack a clear taxonomy of unique threat models across diverse scenarios, we emphasize the unique privacy and security threats associated with four specific scenarios: pre-training, fine-tuning, deployment, and LLM-based agents. Addressing the characteristics of each risk, this survey outlines and analyzes potential countermeasures. Research on attack and defense situations can offer feasible research directions, enabling more areas to benefit from LLMs.

cs.CR↗

arXiv2025

Language modulates vision: Evidence from neural networks and human brain-lesion models

Comparing information structures in between deep neural networks (DNNs) and the human brain has become a key method for exploring their similarities and differences. Recent research has shown better alignment of vision-language DNN models, such as CLIP, with the activity of the human ventral occipitotemporal cortex (VOTC) than earlier vision models, supporting the idea that language modulates human visual perception. However, interpreting the results from such comparisons is inherently limited due to the "black box" nature of DNNs. To address this, we combined model-brain fitness analyses with human brain lesion data to examine how disrupting the communication pathway between the visual and language systems causally affects the ability of vision-language DNNs to explain the activity of the VOTC. Across four diverse datasets, CLIP consistently captured unique variance in VOTC neural representations, relative to both label-supervised (ResNet) and unsupervised (MoCo) models. This advantage tended to be left-lateralized at the group level, aligning with the human language network. Analyses of 33 stroke patients revealed that reduced white matter integrity between the VOTC and the language region in the left angular gyrus was correlated with decreased CLIP-brain correspondence and increased MoCo-brain correspondence, indicating a dynamic influence of language processing on the activity of the VOTC. These findings support the integration of language modulation in neurocognitive models of human vision, reinforcing concepts from vision-language DNN models. The sensitivity of model-brain similarity to specific brain lesions demonstrates that leveraging manipulation of the human brain is a promising framework for evaluating and developing brain-like computer models.

q-bio.NC↗

arXiv2025

Y-AR: A Mixed Reality CAD Tool for 3D Wire Bending

Wire bending is a technique used in manufacturing to mass-produce items such as clips, mounts, and braces. Recent advances in programmable wire bending have made this process increasingly accessible for custom fabrication. However, CNC wire benders are controlled using Computer Aided Manufacturing (CAM) software, without design tools, making custom designs challenging to produce. We present Y-AR, a Computer Aided Design (CAD) interface for 3D wire bending. Y-AR uses mixed reality to let designers create clips, mounts, and braces to physically connect objects to their surrounding environment. The interface incorporates springs as design primitives which (1) apply forces to hold objects, and (2) counter-act dimensional inaccuracies inherently caused by mid-air modeling and measurement errors in AR. Springs are a natural design element when working with metal wire-bending given its specific material properties. We demonstrate workflows to design and fabricate a range of mechanisms in Y-AR as well as structures made using free-hand design tools. We found that combining gesture-based interaction with fabrication-aware design principles allowed novice users to create functional wire connectors, even when using imprecise XR-based input. In our usability evaluation, all 12 participants successfully designed and fabricated a functional bottle holder using Y-AR.

cs.HC↗

arXiv2025

Multiple Instance Learning Framework with Masked Hard Instance Mining for Gigapixel Histopathology Image Analysis

Digitizing pathological images into gigapixel Whole Slide Images (WSIs) has opened new avenues for Computational Pathology (CPath). As positive tissue comprises only a small fraction of gigapixel WSIs, existing Multiple Instance Learning (MIL) methods typically focus on identifying salient instances via attention mechanisms. However, this leads to a bias towards easy-to-classify instances while neglecting challenging ones. Recent studies have shown that hard examples are crucial for accurately modeling discriminative boundaries. Applying such an idea at the instance level, we elaborate a novel MIL framework with masked hard instance mining (MHIM-MIL), which utilizes a Siamese structure with a consistency constraint to explore the hard instances. Using a class-aware instance probability, MHIM-MIL employs a momentum teacher to mask salient instances and implicitly mine hard instances for training the student model. To obtain diverse, non-redundant hard instances, we adopt large-scale random masking while utilizing a global recycle network to mitigate the risk of losing key features. Furthermore, the student updates the teacher using an exponential moving average, which identifies new hard instances for subsequent training iterations and stabilizes optimization. Experimental results on cancer diagnosis, subtyping, survival analysis tasks, and 12 benchmarks demonstrate that MHIM-MIL outperforms the latest methods in both performance and efficiency. The code is available at: https://github.com/DearCaat/MHIM-MIL.

cs.CV↗

arXiv2025

CoPlay: Audio-agnostic Cognitive Scaling for Acoustic Sensing

Acoustic sensing manifests great potential in various applications that encompass health monitoring, gesture interface and imaging by leveraging the speakers and microphones on smart devices. However, in ongoing research and development in acoustic sensing, one problem is often overlooked: the same speaker, when used concurrently for sensing and other traditional applications (like playing music), could cause interference in both making it impractical to use in the real world. The strong ultrasonic sensing signals mixed with music would overload the speaker's mixer. To confront this issue of overloaded signals, current solutions are clipping or down-scaling, both of which affect the music playback quality and also sensing range and accuracy. To address this challenge, we propose CoPlay, a deep learning based optimization algorithm to cognitively adapt the sensing signal. It can 1) maximize the sensing signal magnitude within the available bandwidth left by the concurrent music to optimize sensing range and accuracy and 2) minimize any consequential frequency distortion that can affect music playback. In this work, we design a deep learning model and test it on common types of sensing signals (sine wave or Frequency Modulated Continuous Wave FMCW) as inputs with various agnostic concurrent music and speech. First, we evaluated the model performance to show the quality of the generated signals. Then we conducted field studies of downstream acoustic sensing tasks in the real world. A study with 12 users proved that respiration monitoring and gesture recognition using our adapted signal achieve similar accuracy as no-concurrent-music scenarios, while clipping or down-scaling manifests worse accuracy. A qualitative study also manifests that the music play quality is not degraded, unlike traditional clipping or down-scaling methods.

cs.SD↗