Searcharxiv⌕ Search

arXiv subjects

Shaobo Liu

Publications and source records attributed to Shaobo Liu.

At least 19 recordsLinked to original sources

Why Deterministic PRM Guidance Underperforms in Discrete Diffusion Reasoning

Discrete diffusion language models (dLLMs) expose a denoised solution at every step, which makes process reward model (PRM) guidance look like a way to spend compute at test time. We show that once denoising, PRM scoring, and outcome reward model (ORM) scoring are charged in the same budget of forward passes, its deterministic form loses to a much simpler baseline. Our PRMs score intermediate denoising states and are trained on the correctness of the final answer. On Dream-v0-Instruct-7B with 8 candidates per GSM8K problem, keeping the candidate with the highest PRM score at every scoring step reaches 65.18%, while independent sampling plus an ORM reranker trained for the task reaches 75.13%. The gap grows to 12.69 percentage points (pp) with 32 candidates, and is 9.85 pp on MATH and 12.16 pp on MBPP. We trace it to two separable failures. First, guidance prunes on a weak signal: on GSM8K, PRM ROC-AUC falls from 0.77 to 0.54 as the mask ratio rises, a decay that persists when states are relabeled with fresh rollouts, and pruning lowers the best accuracy reachable from the candidate pool from 81.05% for independent samples to 67.30%. Second, on GSM8K and MATH, the PRM is a poor final judge: a sequential Monte Carlo sampler at the same budget restores that ceiling to 77.89%, yet selecting with the PRM gives 65.48%, on par with deterministic guidance, while a PRM retrained on final states matches the ORM on identical candidates. MBPP separates the two: there the PRM reaches 65.47% when reranking finished programs, on par with the ORM, but 50.88% when it guides denoising. The results point to two targets for dLLM guidance: keep correct partial solutions alive through early denoising, and leave the final choice to a verifier trained on final states. We release the corpus of denoising states with outcome labels and evaluation toolkit for reproducible comparisons at matched compute.

cs.AI↗

Same Bytes, Different Authority: Reserved-Token Representations in Chat-Template Prompt Injection

Prompt injection against LLM agents becomes much stronger when the injected instruction is wrapped in the model's own chat template. A forged template marker such as <|im_start|> can reach the model either as a single reserved control token or as a sequence of ordinary subword tokens. The two decode to exactly the same text, and because tokenization runs on the server, the defender rather than the attacker decides which one the model receives. We use this to measure how much of the injected instruction's authority comes from the reserved token's learned representation. Encoding the forged markers as subwords, with the text held fixed and a control for the extra tokens this adds, lowers attack success on the InjecAgent benchmark by 39 to 66 percentage points on three of four open-weight families, and the gap carries over to multi-turn agent tasks in AgentDojo. On Qwen3-8B the gap is 8 points, because without reserved ids the model still recognises the forged turn from its text by reasoning; suppressing the reasoning block widens the gap to 50. The authority sits in the single learned vector at the marker position: the mean of the marker's subword vectors does not reproduce it, the vector of the nearest ordinary token restores the attack on Llama-3.1, and an adaptive attacker who searches for non-reserved markers finds such embedding neighbours on three of four families. In every base and instruction-tuned pair we test, instruction tuning strengthens the model's preference for reserved markers. The standard mitigation, a tokenizer option that encodes special tokens as ordinary subwords, applies only to tokens a configuration declares special, so in 33 of 67 distinct tokenizer configurations, covering 255 of the 400 most-downloaded chat models on Hugging Face, it leaves intact the tool-protocol tokens through which agents read untrusted tool output, and the gap persists on that channel.

cs.CR↗

SLCA-GRPO: Resolving Cross-Segment Credit Misattribution in Tool-Calling RL

Tool-calling agents produce heterogeneous outputs, interleaving structured tool invocations with user-facing natural language summaries. This output heterogeneity presents a structural failure mode in standard on-policy Reinforcement Learning (RL): algorithms like GRPO indiscriminately broadcast a homogeneous trajectory-level scalar advantage to all tokens. Consequently, gradient noise from summary generation leaks into tool-decision tokens, causing cross-segment credit misattribution and brittle optimization. In this work, we propose SLCA-GRPO, a framework incorporating Segment-Locked Credit Assignment (SLCA). To enable scalable exploration without costly real APIs and stable training, we first construct the Schema-Guided LLM Simulator (SGLS) as foundational training infrastructure. Building on this, SLCA decouples advantage estimation at the structural segment level within a single group of rollouts, without requiring additional rollouts from intermediate states. Supported by Hierarchical Rewards (HierR), SLCA routes execution advantages to tool tokens and preference advantages to summary tokens, eliminating advantage contamination (the dominant cross-segment credit misattribution channel) within each policy update. On a 7B backbone, SLCA-GRPO accelerates convergence and outperforms standard GRPO, ToolPO, and RLTR by +2.53 pp on in-domain evaluation, +1.36 pp on the Berkeley Function-Calling Leaderboard (BFCL), and +9.15 pp on $τ^2$-Bench under the same training budgets, achieving higher accuracy with reduced tool redundancy and costs.

cs.AI↗

CrossMambaTuning: Synergistic Spatial and Cross-Layer Adaptation for Machine Vision Compression

To reduce deployment cost and retraining overhead, adapting pretrained learned image compression (LIC) models to downstream machine vision tasks has attracted growing attention. However, existing methods typically insert fine-tuning modules independently into frozen backbones, lacking explicit mechanisms for cross-layer coordination. To address this limitation, we propose a novel framework named CrossMambaTuning, which integrates State Space Models with cross-layer interaction mechanisms for parameter-efficient fine-tuning. Specifically, we design an efficient Mamba adapter equipped with task-specific prompts and multi-scale branching to precisely capture both local features and global dependencies. Furthermore, we introduce a Scale-Invariant Cross-Layer Adapter (SICA) utilizing a parameter-sharing strategy to fuse task information across different scales and reduce redundancy. Extensive experiments demonstrate that CrossMambaTuning achieves state-of-the-art (SOTA) performance on multiple machine vision tasks, reducing parameter overhead by 72\% compared to SOTA methods. Code is available at https://github.com/rsr1123/CrossMambaTuning.

cs.CV↗

RefineSVG: Visual Feedback-Driven Reinforcement Learning for Image-to-SVG Generation

We propose RefineSVG, a single-step closed-loop visual feedback framework that enables multimodal large language models (MLLMs) to perform high-fidelity image-to-SVG generation through self-correction. Existing MLLM-based approaches rely on single-pass open-loop inference, where the model receives visual input only once and must generate thousands of SVG code tokens without intermediate verification. This paradigm inevitably leads to geometric drift, error accumulation, and visual hallucination on complex images. RefineSVG overcomes this limitation by invoking an external rendering engine after an initial SVG generation pass to compare the rendered output against the target image. The comparison yields a multi-dimensional visual residual map (Diff-Map) that is fed back to the model as a ReAct-style correction signal, driving a targeted correction step. To support this render-observe-correct interaction, we further introduce an SVG-oriented semantic vocabulary that compresses token sequences by over 52%. A progressive training pipeline spanning supervised fine-tuning, rejection-sampling cold-start data construction, and end-to-end agentic reinforcement learning aligns the model with closed-loop visual correction. Extensive experiments show that RefineSVG consistently outperforms existing baselines in reconstruction fidelity, structural accuracy, and code efficiency.Code is available at https://github.com/liuxiaobo66/RefineSVG.

cs.CV↗

CoSTA: Cognitive-State-Conditioned TTS Data Augmentation Using ASR Transcripts for Alzheimer's Disease Detection

Speech-based Alzheimer's Disease (AD) detection is constrained by scarce pathological speech data. To address this, we propose CoSTA, a Text-to-Speech (TTS)-based data augmentation framework. Specifically, we first develop two Cognitive-State-Conditioned (CS-Cond) TTS models by adapting CosyVoice2 and F5-TTS to synthesize speech with distinct AD and Healthy Control characteristics. Furthermore, by constructing a transcript pool comprising Manual Transcripts (MT) and 36 Automatic Speech Recognition (ASR) transcripts, we investigate the impact of text sources on TTS-based augmentation. We also perform augmentation-factor analysis and test-time augmentation. Experiments on the ADReSS dataset show that CS-Cond TTS significantly improves synthetic speech utility, and ASR-driven augmentation frequently outperforms MT-driven augmentation. Finally, CoSTA yields a 4.16% gain over the baseline, achieving an audio-only accuracy of 85.83% on the ADReSS test set and outperforming prior methods.

eess.AS↗

What and Where to Adapt: Structure-Semantics Co-Tuning for Machine Vision Compression via Synergistic Adapters

Parameter-efficient fine-tuning of pre-trained codecs is a promising direction in image compression for human and machine vision. While most existing works have primarily focused on tuning the feature structure within the encoder-decoder backbones, the adaptation of the statistical semantics within the entropy model has received limited attention despite its function of predicting the probability distribution of latent features. Our analysis reveals that naive adapter insertion into the entropy model can lead to suboptimal outcomes, underscoring that the effectiveness of adapter-based tuning depends critically on the coordination between adapter type and placement across the compression pipeline. Therefore, we introduce Structure-Semantics Co-Tuning (S2-CoT), a novel framework that achieves this coordination via two specialized, synergistic adapters: the Structural Fidelity Adapter (SFA) and the Semantic Context Adapter (SCA). SFA is integrated into the encoder-decoder to preserve high-fidelity representations by dynamically fusing spatial and frequency information; meanwhile, the SCA adapts the entropy model to align with SFA-tuned features by refining the channel context for more efficient statistical coding. Through joint optimization, S2-CoT turns potential performance degradation into synergistic gains, achieving state-of-the-art results across four diverse base codecs with only a small fraction of trainable parameters, closely matching full fine-tuning performance. Code is available at https://github.com/Brock-bit4/S2-CoT.

cs.CV↗

Towards pedestrian head tracking: A benchmark dataset and a multi-source data fusion network

Pedestrian detection and tracking in crowded video sequences have many applications, including autonomous driving, robot navigation and pedestrian flow analysis. However, detecting and tracking pedestrians in high-density crowds face many challenges, including intra-class occlusions, complex motions, and diverse poses. Although artificial intelligence (AI) models have achieved great progress in head detection, head tracking datasets and methods are extremely lacking. Existing head datasets have limited coverage of complex pedestrian flows and scenes (e.g., pedestrian interactions, occlusions, and object interference). It is of great importance to develop new head tracking datasets and methods. To address these challenges, we present a Chinese Large-scale Cross-scene Pedestrian Head Tracking dataset (Cchead) and a Multi-source Data Fusion Network (MDFN). The dataset has features that are of considerable interest, including 10 diverse scenes of 50,528 frames with about 2,366,249 heads and 2,358 tracks. Our dataset contains diverse pedestrian moving speeds, directions, and complex crowd pedestrian flows with collision avoidance behaviors. Existing state-of-the-art (SOTA) algorithms are tested and compared on the Cchead dataset. MDFN is the first end-to-end convolutional neural network (CNN)-based head detection and tracking network that jointly trains Red, Green, Blue (RGB) frames, pixel-level motion information, depth maps, and density maps in videos. Ablation experiments confirm the significance of multi-source data fusion. Compared with SOTA pedestrian detection and tracking methods, MDFN achieves superior performance across three datasets: Cchead, Restaurant and Crowd of Heads Dataset (CroHD). To promote further development, we share our source code and trained models for global researchers: https://github.com/kailaisun/Cchead.

eess.IV↗

SPA: Towards A Computational Friendly Cloud-Base and On-Devices Collaboration Seq2seq Personalized Generation with Casual Inference

Large language models(LLMs) have shown its outperforming ability on various tasks and question answering. However, LLMs require substantial memory storage on low-resource devices. More critically, the computational speed on these devices is also severely limited. In this paper, we propose SPA(Side Plugin Adaption), a lightweight architecture for fast on-devices inference on the constraints of strict on-devices computation and memory constraints. Compared with other on-devices seq2seq generation, SPA could make a fast and stable inference on low-resource constraints, allowing it to obtain cost effiency. Our method establish an interaction between a pretrained LLMs on-cloud and additive parameters on-devices, which could provide the knowledge on both pretrained LLMs and featured personal feature. Further more, SPA provides a framework to keep feature-base parameters on low computational devices while leave the parameters containing general information on the high computational devices.

cs.CL↗

Sliding two-dimensional superconductivity and charge-density-wave state in a bulk crystal

Superconductivity in the two-dimensional (2D) limit is a fertile ground for exotic quantum phenomena-many of which remain elusive in their 3D counterparts. While studies of 2D superconductivity have predominantly focused on mono- or few-layer systems, we demonstrate an alternative route-interlayer sliding in bulk crystals. Through a precisely controlled growth strategy, we engineer interlayer sliding in bulk 3R-NbSe2, deliberately disrupting [001] mirror symmetry and drastically suppressing interlayer coupling. Remarkably, this structural manipulation stabilizes Ising-type superconductivity coexisting with an unconventional charge-density-wave (CDW) state akin to that of monolayer 2H-NbSe2. The sliding phase exhibits a pronounced suppression of the upper critical field at low temperatures, revealing a delicate competition between Ising and Rashba spin-orbit coupling (SOC) in the globally noncentrosymmetric lattice. Intriguingly, the superconducting state displays two-fold symmetry, a signature that may arise from asymmetric SOC or a multi-component pairing order parameter. Our work establishes interlayer sliding as a symmetry-breaking tool to promote 2D superconductivity in bulk materials-without resorting to extrinsic intercalation or doping. More broadly, this approach sets a paradigm for unlocking hidden quantum states in layered materials, offering a new dimension in design of quantum matter.

cond-mat.supr-con↗

Privacy-Preserving Hybrid Ensemble Model for Network Anomaly Detection: Balancing Security and Data Protection

Privacy-preserving network anomaly detection has become an essential area of research due to growing concerns over the protection of sensitive data. Traditional anomaly detection models often prioritize accuracy while neglecting the critical aspect of privacy. In this work, we propose a hybrid ensemble model that incorporates privacy-preserving techniques to address both detection accuracy and data protection. Our model combines the strengths of several machine learning algorithms, including K-Nearest Neighbors (KNN), Support Vector Machines (SVM), XGBoost, and Artificial Neural Networks (ANN), to create a robust system capable of identifying network anomalies while ensuring privacy. The proposed approach integrates advanced preprocessing techniques that enhance data quality and address the challenges of small sample sizes and imbalanced datasets. By embedding privacy measures into the model design, our solution offers a significant advancement over existing methods, ensuring both enhanced detection performance and strong privacy safeguards.

cs.LG↗

Research on Key Technologies for Cross-Cloud Federated Training of Large Language Models

With the rapid development of natural language processing technology, large language models have demonstrated exceptional performance in various application scenarios. However, training these models requires significant computational resources and data processing capabilities. Cross-cloud federated training offers a new approach to addressing the resource bottlenecks of a single cloud platform, allowing the computational resources of multiple clouds to collaboratively complete the training tasks of large models. This study analyzes the key technologies of cross-cloud federated training, including data partitioning and distribution, communication optimization, model aggregation algorithms, and the compatibility of heterogeneous cloud platforms. Additionally, the study examines data security and privacy protection strategies in cross-cloud training, particularly the application of data encryption and differential privacy techniques. Through experimental validation, the proposed technical framework demonstrates enhanced training efficiency, ensured data security, and reduced training costs, highlighting the broad application prospects of cross-cloud federated training.

cs.LG↗

TRIZ Method for Urban Building Energy Optimization: GWO-SARIMA-LSTM Forecasting model

With the advancement of global climate change and sustainable development goals, urban building energy consumption optimization and carbon emission reduction have become the focus of research. Traditional energy consumption prediction methods often lack accuracy and adaptability due to their inability to fully consider complex energy consumption patterns, especially in dealing with seasonal fluctuations and dynamic changes. This study proposes a hybrid deep learning model that combines TRIZ innovation theory with GWO, SARIMA and LSTM to improve the accuracy of building energy consumption prediction. TRIZ plays a key role in model design, providing innovative solutions to achieve an effective balance between energy efficiency, cost and comfort by systematically analyzing the contradictions in energy consumption optimization. GWO is used to optimize the parameters of the model to ensure that the model maintains high accuracy under different conditions. The SARIMA model focuses on capturing seasonal trends in the data, while the LSTM model handles short-term and long-term dependencies in the data, further improving the accuracy of the prediction. The main contribution of this research is the development of a robust model that leverages the strengths of TRIZ and advanced deep learning techniques, improving the accuracy of energy consumption predictions. Our experiments demonstrate a significant 15% reduction in prediction error compared to existing models. This innovative approach not only enhances urban energy management but also provides a new framework for optimizing energy use and reducing carbon emissions, contributing to sustainable development.

cs.LG↗

Balancing Innovation and Privacy: Data Security Strategies in Natural Language Processing Applications

This research addresses privacy protection in Natural Language Processing (NLP) by introducing a novel algorithm based on differential privacy, aimed at safeguarding user data in common applications such as chatbots, sentiment analysis, and machine translation. With the widespread application of NLP technology, the security and privacy protection of user data have become important issues that need to be solved urgently. This paper proposes a new privacy protection algorithm designed to effectively prevent the leakage of user sensitive information. By introducing a differential privacy mechanism, our model ensures the accuracy and reliability of data analysis results while adding random noise. This method not only reduces the risk caused by data leakage but also achieves effective processing of data while protecting user privacy. Compared to traditional privacy methods like data anonymization and homomorphic encryption, our approach offers significant advantages in terms of computational efficiency and scalability while maintaining high accuracy in data analysis. The proposed algorithm's efficacy is demonstrated through performance metrics such as accuracy (0.89), precision (0.85), and recall (0.88), outperforming other methods in balancing privacy and utility. As privacy protection regulations become increasingly stringent, enterprises and developers must take effective measures to deal with privacy risks. Our research provides an important reference for the application of privacy protection technology in the field of NLP, emphasizing the need to achieve a balance between technological innovation and user privacy. In the future, with the continuous advancement of technology, privacy protection will become a core element of data-driven applications and promote the healthy development of the entire industry.

cs.CR↗

Applying Hybrid Graph Neural Networks to Strengthen Credit Risk Analysis

This paper presents a novel approach to credit risk prediction by employing Graph Convolutional Neural Networks (GCNNs) to assess the creditworthiness of borrowers. Leveraging the power of big data and artificial intelligence, the proposed method addresses the challenges faced by traditional credit risk assessment models, particularly in handling imbalanced datasets and extracting meaningful features from complex relationships. The paper begins by transforming raw borrower data into graph-structured data, where borrowers and their relationships are represented as nodes and edges, respectively. A classic subgraph convolutional model is then applied to extract local features, followed by the introduction of a hybrid GCNN model that integrates both local and global convolutional operators to capture a comprehensive representation of node features. The hybrid model incorporates an attention mechanism to adaptively select features, mitigating issues of over-smoothing and insufficient feature consideration. The study demonstrates the potential of GCNNs in improving the accuracy of credit risk prediction, offering a robust solution for financial institutions seeking to enhance their lending decision-making processes.

cs.LG↗

Multi-Scenario Combination Based on Multi-Agent Reinforcement Learning to Optimize the Advertising Recommendation System

This paper explores multi-scenario optimization on large platforms using multi-agent reinforcement learning (MARL). We address this by treating scenarios like search, recommendation, and advertising as a cooperative, partially observable multi-agent decision problem. We introduce the Multi-Agent Recurrent Deterministic Policy Gradient (MARDPG) algorithm, which aligns different scenarios under a shared objective and allows for strategy communication to boost overall performance. Our results show marked improvements in metrics such as click-through rate (CTR), conversion rate, and total sales, confirming our method's efficacy in practical settings.

cs.LG↗

A Multivariate Equivalence Test Based on Mahalanobis Distance with a Data-Driven Margin

Multivariate equivalence testing is needed in a variety of scenarios for drug development. For example, drug products obtained from natural sources may contain many components for which the individual effects and/or their interactions on clinical efficacy and safety cannot be completely characterized. Such lack of sufficient characterization poses a challenge for both generic drug developers to demonstrate and regulatory authorities to determine the sameness of a proposed generic product to its reference product. Another case is to ensure batch-to-batch consistency of naturally derived products containing a vast number of components, such as botanical products. The equivalence or sameness between products containing many components that cannot be individually evaluated needs to be studied in a holistic manner. Multivariate equivalence test based on Mahalanobis distance may be suitable to evaluate many variables holistically. Existing studies based on such method assumed either a predetermined constant margin, for which a consensus is difficult to achieve, or a margin derived from the data, where, however, the randomness is ignored during the testing. In this study, we propose a multivariate equivalence test based on Mahalanobis distance with a data-drive margin with the randomness in the margin considered. Several possible implementations are compared with existing approaches via extensive simulation studies.

stat.ME↗

Research on Driver Facial Fatigue Detection Based on Yolov8 Model

In a society where traffic accidents frequently occur, fatigue driving has emerged as a grave issue. Fatigue driving detection technology, especially those based on the YOLOv8 deep learning model, has seen extensive research and application as an effective preventive measure. This paper discusses in depth the methods and technologies utilized in the YOLOv8 model to detect driver fatigue, elaborates on the current research status both domestically and internationally, and systematically introduces the processing methods and algorithm principles for various datasets. This study aims to provide a robust technical solution for preventing and detecting fatigue driving, thereby contributing significantly to reducing traffic accidents and safeguarding lives.

cs.CV↗