arXiv subjects

Bo Liu

Publications and source records attributed to Bo Liu.

At least 217 records · Page 12Linked to original sources

arXiv2025

Character-Level Perturbations Disrupt LLM Watermarks

Large Language Model (LLM) watermarking embeds detectable signals into generated text for copyright protection, misuse prevention, and content detection. While prior studies evaluate robustness using watermark removal attacks, these methods are often suboptimal, creating the misconception that effective removal requires large perturbations or powerful adversaries. To bridge the gap, we first formalize the system model for LLM watermark, and characterize two realistic threat models constrained on limited access to the watermark detector. We then analyze how different types of perturbation vary in their attack range, i.e., the number of tokens they can affect with a single edit. We observe that character-level perturbations (e.g., typos, swaps, deletions, homoglyphs) can influence multiple tokens simultaneously by disrupting the tokenization process. We demonstrate that character-level perturbations are significantly more effective for watermark removal under the most restrictive threat model. We further propose guided removal attacks based on the Genetic Algorithm (GA) that uses a reference detector for optimization. Under a practical threat model with limited black-box queries to the watermark detector, our method demonstrates strong removal performance. Experiments confirm the superiority of character-level perturbations and the effectiveness of the GA in removing watermarks under realistic constraints. Additionally, we argue there is an adversarial dilemma when considering potential defenses: any fixed defense can be bypassed by a suitable perturbation strategy. Motivated by this principle, we propose an adaptive compound character-level attack. Experimental results show that this approach can effectively defeat the defenses. Our findings highlight significant vulnerabilities in existing LLM watermark schemes and underline the urgency for the development of new robust mechanisms.

cs.CR↗

arXiv2025

Inpainting-Guided Policy Optimization for Diffusion Large Language Models

Masked diffusion large language models (dLLMs) are emerging as promising alternatives to autoregressive LLMs, offering competitive performance while supporting unique generation capabilities such as inpainting. We explore how inpainting can inform RL algorithm design for dLLMs. Aligning LLMs with reinforcement learning faces an exploration challenge: sparse reward signals and sample waste when models fail to discover correct solutions. While this inefficiency affects LLMs broadly, dLLMs offer a distinctive opportunity--their inpainting ability can guide exploration. We introduce IGPO (Inpainting Guided Policy Optimization), an RL framework that strategically inserts partial ground-truth reasoning traces during online sampling. Unlike providing full solutions, inpainting steers exploration toward promising trajectory spaces while preserving self-generated reasoning, bridging supervised fine-tuning and reinforcement learning. We apply IGPO to group-based optimization methods such as GRPO, where exploration failures cause zero advantages and gradients. IGPO restores meaningful gradients while improving sample efficiency. We also propose supervised fine-tuning on synthetically rewritten concise traces that better align with dLLM generation patterns. With additional techniques including entropy-based filtering, our training recipe yields substantial gains across three mathematical benchmarks--GSM8K, Math500, and AMC--achieving new state-of-the-art results for full-attention masked dLLMs.

cs.LG↗

arXiv2025

An Iterative LLM Framework for SIBT utilizing RAG-based Adaptive Weight Optimization

Seed implant brachytherapy (SIBT) is an effective cancer treatment modality; however, clinical planning often relies on manual adjustment of objective function weights, leading to inefficiencies and suboptimal results. This study proposes an adaptive weight optimization framework for SIBT planning, driven by large language models (LLMs). A locally deployed DeepSeek-R1 LLM is integrated with an automatic planning algorithm in an iterative loop. Starting with fixed weights, the LLM evaluates plan quality and recommends new weights in the next iteration. This process continues until convergence criteria are met, after which the LLM conducts a comprehensive evaluation to identify the optimal plan. A clinical knowledge base, constructed and queried via retrieval-augmented generation (RAG), enhances the model's domain-specific reasoning. The proposed method was validated on 23 patient cases, showing that the LLM-assisted approach produces plans that are comparable to or exceeding clinically approved and fixed-weight plans, in terms of dose homogeneity for the clinical target volume (CTV) and sparing of organs at risk (OARs). The study demonstrates the potential use of LLMs in SIBT planning automation.

physics.med-ph↗

arXiv2025

LLaVA-Critic-R1: Your Critic Model is Secretly a Strong Policy Model

In vision-language modeling, critic models are typically trained to evaluate outputs -- assigning scalar scores or pairwise preferences -- rather than to generate responses. This separation from policy models, which produce the responses, is so entrenched that critics are rarely considered for direct policy use. In this work, we challenge this convention. We propose to reorganize preference-labeled critic datasets into verifiable training signals and perform reinforcement learning directly on a base generative model, producing LLaVA-Critic-R1, a multimodal critic trained to optimize preference judgments while retaining full generation ability. Surprisingly, LLaVA-Critic-R1 emerges not only as a top-performing critic but also as a competitive policy model -- matching or surpassing specialized reasoning VLMs trained with in-domain data across 26 visual reasoning and understanding benchmarks, with an average gain of +5.7% over its base model (Qwen-2.5-VL-7B). Extending this approach to existing strong reasoning VLMs yields LLaVA-Critic-R1+, which further advances policy performance without sacrificing critic quality, achieving a SoTA performance of 71.9 on MMMU at the 7B scale. Finally, we show that the enhanced critic ability benefits inference: applying self-critique at test time yields an average +13.8% improvement on five representative reasoning tasks without additional training. Our results reveal that RL training on critic data can produce a unified model excelling at both evaluation and generation, offering a simple path toward scalable, self-improving multimodal systems.

cs.CV↗

arXiv2025

Cross-field SNR Analysis and Tensor Channel Estimation for Multi-UAV Near-field Communications

Extremely large antenna array (ELAA) is key to enhancing spectral efficiency in 6G networks. Leveraging the distributed nature of multi-unmanned aerial vehicle (UAV) systems enables the formation of distributed ELAA, which often operate in the near-field region with spatial sparsity, rendering the conventional far-field plane wave assumption invalid. This paper investigates channel estimation for distributed near-field multi-UAV communication systems. We first derive closed-form signal-to-noise ratio (SNR) expressions under the plane wave model (PWM), spherical wave model (SWM), and a hybrid spherical-plane wave model (HSPWM), also referred to as the cross-field model, within a distributed uniform planar array (UPA) scenario. The analysis shows that HSPWM achieves a good balance between modeling accuracy and analytical tractability. Based on this, we propose two channel estimation algorithms: the spherical-domain orthogonal matching pursuit (SD-OMP) and the tensor-OMP. The SD-OMP generalizes the polar domain to jointly consider elevation, azimuth, and range. Under the HSPWM, the channel is naturally formulated as a tensor, enabling the use of tensor-OMP. Simulation results demonstrate that tensor-OMP achieves normalized mean square error (NMSE) performance comparable to SD-OMP, while offering reduced computational complexity and improved scalability.

eess.SP↗

arXiv2025

REACH: Reinforcement Learning for Efficient Allocation in Community and Heterogeneous Networks

Community GPU platforms are emerging as a cost-effective and democratized alternative to centralized GPU clusters for AI workloads, aggregating idle consumer GPUs from globally distributed and heterogeneous environments. However, their extreme hardware/software diversity, volatile availability, and variable network conditions render traditional schedulers ineffective, leading to suboptimal task completion. In this work, we present REACH (Reinforcement Learning for Efficient Allocation in Community and Heterogeneous Networks), a Transformer-based reinforcement learning framework that redefines task scheduling as a sequence scoring problem to balance performance, reliability, cost, and network efficiency. By modeling both global GPU states and task requirements, REACH learns to adaptively co-locate computation with data, prioritize critical jobs, and mitigate the impact of unreliable resources. Extensive simulation results show that REACH improves task completion rates by up to 17%, more than doubles the success rate for high-priority tasks, and reduces bandwidth penalties by over 80% compared to state-of-the-art baselines. Stress tests further demonstrate its robustness to GPU churn and network congestion, while scalability experiments confirm its effectiveness in large-scale, high-contention scenarios.

cs.NI↗

arXiv2025

Hierarchical knowledge guided fault intensity diagnosis of complex industrial systems

Fault intensity diagnosis (FID) plays a pivotal role in monitoring and maintaining mechanical devices within complex industrial systems. As current FID methods are based on chain of thought without considering dependencies among target classes. To capture and explore dependencies, we propose a hierarchical knowledge guided fault intensity diagnosis framework (HKG) inspired by the tree of thought, which is amenable to any representation learning methods. The HKG uses graph convolutional networks to map the hierarchical topological graph of class representations into a set of interdependent global hierarchical classifiers, where each node is denoted by word embeddings of a class. These global hierarchical classifiers are applied to learned deep features extracted by representation learning, allowing the entire model to be end-to-end learnable. In addition, we develop a re-weighted hierarchical knowledge correlation matrix (Re-HKCM) scheme by embedding inter-class hierarchical knowledge into a data-driven statistical correlation matrix (SCM) which effectively guides the information sharing of nodes in graphical convolutional neural networks and avoids over-smoothing issues. The Re-HKCM is derived from the SCM through a series of mathematical transformations. Extensive experiments are performed on four real-world datasets from different industrial domains (three cavitation datasets from SAMSON AG and one existing publicly) for FID, all showing superior results and outperform recent state-of-the-art FID methods.

cs.AI↗

arXiv2025

Multiply robust estimation for causal survival analysis with treatment noncompliance

Comparative effectiveness research frequently addresses a time-to-event outcome and can require unique considerations in the presence of treatment noncompliance. Motivated by the challenges in addressing noncompliance in the ADAPTABLE pragmatic clinical trial, we develop a multiply robust estimator to estimate the principal survival causal effects under the principal ignorability and monotonicity. The multiply robust estimator is consistent even if one, and sometimes two, of the required models are misspecified. We apply the multiply robust method in the ADAPTABLE trial to evaluate the effect of low- versus high-dose aspirin assignment on patients' death and hospitalization from cardiovascular diseases. We find that, comparing to low-dose assignment, assignment to the high-dose leads to differential effects among always high-dose takers, compliers, and always low-dose takers. Such treatment effect heterogeneity contributes to the null intention-to-treatment effect. We further perform a formal sensitivity analysis for investigating the robustness of our causal conclusions under violation of two identification assumptions specific to noncompliance.

stat.ME↗

arXiv2025

Denoise-then-Retrieve: Text-Conditioned Video Denoising for Video Moment Retrieval

Current text-driven Video Moment Retrieval (VMR) methods encode all video clips, including irrelevant ones, disrupting multimodal alignment and hindering optimization. To this end, we propose a denoise-then-retrieve paradigm that explicitly filters text-irrelevant clips from videos and then retrieves the target moment using purified multimodal representations. Following this paradigm, we introduce the Denoise-then-Retrieve Network (DRNet), comprising Text-Conditioned Denoising (TCD) and Text-Reconstruction Feedback (TRF) modules. TCD integrates cross-attention and structured state space blocks to dynamically identify noisy clips and produce a noise mask to purify multimodal video representations. TRF further distills a single query embedding from purified video representations and aligns it with the text embedding, serving as auxiliary supervision for denoising during training. Finally, we perform conditional retrieval using text embeddings on purified video representations for accurate VMR. Experiments on Charades-STA and QVHighlights demonstrate that our approach surpasses state-of-the-art methods on all metrics. Furthermore, our denoise-then-retrieve paradigm is adaptable and can be seamlessly integrated into advanced VMR models to boost performance.

cs.CV↗

arXiv2025

Vehicle Top Tag Assisted Vehicle-Road Cooperative Localization For Autonomous Public Buses

Accurate vehicle localization is indispensable to autonomous vehicles, but is difficult to realize in complicated application scenarios. Intersection scenarios that suffer from environmental shielding and crowded dynamic objects are especially crucial and challenging. To handle difficult intersection scenarios, the methodology of vehicle top tag assisted vehicle-road cooperative localization or for short vehicle top tag assisted localization is proposed. The proposed methodology has merits of satisfying all the feasibility, reliability, explainability, society and economy concerns. Concrete solutions of vehicle top tag detection and vehicle top tag localization that instantiate the core part of the proposed methodology are presented. Simulation results are provided to demonstrate effectiveness of the presented solutions. The proposed methodology of vehicle top tag assisted localization also has the potential to be extended to a much wider range of practical applications than our intended ones involving autonomous public buses.

cs.RO↗

arXiv2025

Uncertainty-aware Medical Diagnostic Phrase Identification and Grounding

Medical phrase grounding is crucial for identifying relevant regions in medical images based on phrase queries, facilitating accurate image analysis and diagnosis. However, current methods rely on manual extraction of key phrases from medical reports, reducing efficiency and increasing the workload for clinicians. Additionally, the lack of model confidence estimation limits clinical trust and usability. In this paper, we introduce a novel task called Medical Report Grounding (MRG), which aims to directly identify diagnostic phrases and their corresponding grounding boxes from medical reports in an end-to-end manner. To address this challenge, we propose uMedGround, a robust and reliable framework that leverages a multimodal large language model to predict diagnostic phrases by embedding a unique token, , into the vocabulary to enhance detection capabilities. A vision encoder-decoder processes the embedded token and input image to generate grounding boxes. Critically, uMedGround incorporates an uncertainty-aware prediction model, significantly improving the robustness and reliability of grounding predictions. Experimental results demonstrate that uMedGround outperforms state-of-the-art medical phrase grounding methods and fine-tuned large visual-language models, validating its effectiveness and reliability. This study represents a pioneering exploration of the MRG task, marking the first-ever endeavor in this domain. Additionally, we demonstrate the applicability of uMedGround in medical visual question answering and class-based localization tasks, where it highlights visual evidence aligned with key diagnostic phrases, supporting clinicians in interpreting various types of textual inputs, including free-text reports, visual question answering queries, and class labels.

cs.CV↗

arXiv2025

L3M+P: Lifelong Planning with Large Language Models

By combining classical planning methods with large language models (LLMs), recent research such as LLM+P has enabled agents to plan for general tasks given in natural language. However, scaling these methods to general-purpose service robots remains challenging: (1) classical planning algorithms generally require a detailed and consistent specification of the environment, which is not always readily available; and (2) existing frameworks mainly focus on isolated planning tasks, whereas robots are often meant to serve in long-term continuous deployments, and therefore must maintain a dynamic memory of the environment which can be updated with multi-modal inputs and extracted as planning knowledge for future tasks. To address these two issues, this paper introduces L3M+P (Lifelong LLM+P), a framework that uses an external knowledge graph as a representation of the world state. The graph can be updated from multiple sources of information, including sensory input and natural language interactions with humans. L3M+P enforces rules for the expected format of the absolute world state graph to maintain consistency between graph updates. At planning time, given a natural language description of a task, L3M+P retrieves context from the knowledge graph and generates a problem definition for classical planners. Evaluated on household robot simulators and on a real-world service robot, L3M+P achieves significant improvement over baseline methods both on accurately registering natural language state changes and on correctly generating plans, thanks to the knowledge graph retrieval and verification.

cs.RO↗

arXiv2025

Benchmarking Massively Parallelized Multi-Task Reinforcement Learning for Robotics Tasks

Multi-task Reinforcement Learning (MTRL) has emerged as a critical training paradigm for applying reinforcement learning (RL) to a set of complex real-world robotic tasks, which demands a generalizable and robust policy. At the same time, \emph{massively parallelized training} has gained popularity, not only for significantly accelerating data collection through GPU-accelerated simulation but also for enabling diverse data collection across multiple tasks by simulating heterogeneous scenes in parallel. However, existing MTRL research has largely been limited to off-policy methods like SAC in the low-parallelization regime. MTRL could capitalize on the higher asymptotic performance of on-policy algorithms, whose batches require data from the current policy, and as a result, take advantage of massive parallelization offered by GPU-accelerated simulation. To bridge this gap, we introduce a massively parallelized $\textbf{M}$ulti-$\textbf{T}$ask $\textbf{Bench}$mark for robotics (MTBench), an open-sourced benchmark featuring a broad distribution of 50 manipulation tasks and 20 locomotion tasks, implemented using the GPU-accelerated simulator IsaacGym. MTBench also includes four base RL algorithms combined with seven state-of-the-art MTRL algorithms and architectures, providing a unified framework for evaluating their performance. Our extensive experiments highlight the superior speed of evaluating MTRL approaches using MTBench, while also uncovering unique challenges that arise from combining massive parallelism with MTRL. Code is available at https://github.com/Viraj-Joshi/MTBench

cs.RO↗

arXiv2025

Pseudomagnetic Control of Light Waves in the Electrically Tunable Photonic Crystals with Deformation Engineering

With the demonstrations of pseudo-magnetism in optical systems, the pursuits of its practical applications require not only the use of pseudomagnetic fields to create functional optical devices but also a reliable method to manipulate pseudo-magnetism-affected light waves. Here, we experimentally demonstrate an ultracompact Si-based cavity formed by triaxially deformed photonic honeycomb lattices. The triaxial deformation could lead to Landau quantization, showing the possibilities of realizing the localization and resonating of photons with pseudomagnetic fields. Through adopting the Si waveguides for directional coupling, we successfully obtain the transmission spectra for the proposed cavities in the photonic integrated circuits. This opens a novel avenue for highly efficient excitations and detections of Landau-quantized photonic density of states, totally on chip. Moreover, we verify a linear electrical tunability of -0.018 THz/mW for the pseudo-magnetism-induced optical resonant states, fulfilling the manipulation of photons without varying deformations. Our work introduces a mechanism for performing tunable light waves in triaxial deformation-engineered systems, which enriches the design principles of integrated optical devices.

physics.optics↗

arXiv2025

A Global-Local Optimization Approach for Asynchronous SAR ADC Design

This paper presents a system-level optimization framework for automated asynchronous SAR ADC design, addressing the limitations of block-level methods in terms of suboptimal performance and manual effort. The proposed approach integrates a fast global optimizer with a multi-fidelity local optimizer to efficiently handle high-dimensionality and expensive simulation cost. Experimental results from 12 design cases, covering 7- and 12-bit resolutions and a frequency range of 100 kHz to 250 MHz, demonstrate highly competitive performance compared with prior works.

math.OC↗

arXiv2025

An AI-driven EDA Algorithm-Empowered VCO and LDO Co-Design Method

Traditionally, the output noise and power supply rejection of low-dropout regulators (LDOs) are optimized to minimize power supply fluctuations, reducing their impact on the low-frequency noise of target voltage-controlled oscillators (VCOs). However, this sequential design approach does not fully address the trade-offs between high-frequency and LDO-induced low-frequency phase noise. To overcome this limitation, this paper presents a co-design method for low phase-noise LC-tank VCOs powered by LDOs. It is difficult to carry out the co-design using traditional manual design techniques. Hence, an efficient AI-driven EDA algorithm is used. To validate the proposed method, a 5.6 GHz LC-tank VCO with an integrated LDO is designed using a 65 nm CMOS process. Simulations show that the co-design method improves phase noise by 1.2 dB at a 1 MHz offset and reduces dynamic power consumption by 28.8%, with FoM increased by 2.4 dBc/Hz compared to the conventional sequential design method.

eess.SP↗

arXiv2025

DGSSA: Domain generalization with structural and stylistic augmentation for retinal vessel segmentation

Retinal vascular morphology is crucial for diagnosing diseases such as diabetes, glaucoma, and hypertension, making accurate segmentation of retinal vessels essential for early intervention. Traditional segmentation methods assume that training and testing data share similar distributions, which can lead to poor performance on unseen domains due to domain shifts caused by variations in imaging devices and patient demographics. This paper presents a novel approach, DGSSA, for retinal vessel image segmentation that enhances model generalization by combining structural and style augmentation strategies. We utilize a space colonization algorithm to generate diverse vascular-like structures that closely mimic actual retinal vessels, which are then used to generate pseudo-retinal images with an improved Pix2Pix model, allowing the segmentation model to learn a broader range of structure distributions. Additionally, we utilize PixMix to implement random photometric augmentations and introduce uncertainty perturbations, thereby enriching stylistic diversity and significantly enhancing the model's adaptability to varying imaging conditions. Our framework has been rigorously evaluated on four challenging datasets-DRIVE, CHASEDB, HRF, and STARE-demonstrating state-of-the-art performance that surpasses existing methods. This validates the effectiveness of our proposed approach, highlighting its potential for clinical application in automated retinal vessel analysis.

eess.IV↗

arXiv2025

StreakNet-Arch: An Anti-scattering Network-based Architecture for Underwater Carrier LiDAR-Radar Imaging

In this paper, we introduce StreakNet-Arch, a real-time, end-to-end binary-classification framework based on our self-developed Underwater Carrier LiDAR-Radar (UCLR) that embeds Self-Attention and our novel Double Branch Cross Attention (DBC-Attention) to enhance scatter suppression. Under controlled water tank validation conditions, StreakNet-Arch with Self-Attention or DBC-Attention outperforms traditional bandpass filtering and achieves higher $F_1$ scores than learning-based MP networks and CNNs at comparable model size and complexity. Real-time benchmarks on an NVIDIA RTX 3060 show a constant Average Imaging Time (54 to 84 ms) regardless of frame count, versus a linear increase (58 to 1,257 ms) for conventional methods. To facilitate further research, we contribute a publicly available streak-tube camera image dataset contains 2,695,168 real-world underwater 3D point cloud data. More importantly, we validate our UCLR system in a South China Sea trial, reaching an error of 46mm for 3D target at 1,000 m depth and 20 m range. Source code and data are available at https://github.com/BestAnHongjun/StreakNet .

cs.CV↗