SL
Shiguo Lian
cs.CVcs.AIcs.CLcs.LGcs.ROcs.CRcs.MMcs.HCcs.SDcs.GR
On Valency
published · living versionsW_79rv7cx8·v1 · currentpublished
VISAGENT: An Agent-Based End-to-End Voice Interaction System
with Xiang Wang, Zhaoxiang Liu, Xiang Chen, Liqiang He +1
1 version
Preprints & journals
79 papers in the corpus · 2007–2026LaVGuard: Selective Decoding for Contextual Value Drift2610.29135v1 · Jiale Dai, Liuxian Ma, Hongcan Deng et al.2026 · 0 citationsarXiv
VISAGENT: An Agent-Based End-to-End Voice Interaction System2610.26168v1 · Xiang Wang, Zhaoxiang Liu, Xiang Chen et al.2026 · 0 citationsarXivon Valency
LoopREG: Representation Supervision Enables Test-Time Recurrent Depth in Diffusion Transformers2610.17877v1 · Zipeng Wang, Anping Xiong, Jing Zhang et al.2026 · 0 citationsarXiv
OpenViTac: Learning and Benchmarking Visuo-Tactile Policies in a Unified Sim-and-Real Framework2610.10384v1 · Yifan Wu, Qin Li, Nan Min et al.2026 · 0 citationsarXiv
VISTA: Value-Informed Event Appraisal for Multimodal Emotion Conflict2609.37324v1 · Jiale Dai, Liuxian Ma, Xiaoke Niu et al.2026 · 0 citationsarXiv
Is Multimodal Speculative Decoding Ready for Diffusion-Based Parallel Drafting? A Survey and Empirical Diagnosis2608.20743v2 · Yantao Li, Huanlin Gao, Fang Zhao et al.2026 · 0 citationsarXiv
EOVSAM: Efficient Open-Vocabulary Segmentation with SAM 3 in One Pass2608.02284v1 · Haomin Peng, Yongkang Li, Zhaoxiang Liu et al.2026 · 0 citationsarXiv
OTCache: Optimal Transport for Geometry-Aware Caching in Diffusion Models2606.31026v1 · Huanlin Gao, Fang Zhao, Qiang Hui et al.2026 · 0 citationsarXiv
Token-Operations-Oriented Inference Optimization Techniques for Large Models2606.20295v2 · Shiguo Lian, Kai Wang, Zhaoxiang Liu et al.2026 · 0 citationsarXiv
HiMPO: Hindsight-Informed Memory Policy Optimization for Less-Entangled Credit in Long-Horizon Agents2606.16285v3 · Jiangze Yan, Yi Shen, Wenjing Zhang et al.2026 · 0 citationsarXiv
MediaClaw: Multimodal Intelligent-Agent Platform Technical Report2605.14771v1 · Shaoan Zhao, Huanlin Gao, Qiang Hui et al.2026 · 0 citationsarXiv
GLM-5 Serving Parameter Tuning for OpenClaw: Single-Deployment MaaS Inference Optimization for Long-Context Agent Workloads2607.02518v1 · Minjie Hua, Ning Wang, Peijun Yang et al.2026 · 0 citationsarXiv
Mixture of Heterogeneous Grouped Experts for Language Modeling2604.23108v2 · Zhicheng Ma, Xiang Liu, Zhaoxiang Liu et al.2026 · 0 citationsarXiv
KAConvNet: Kolmogorov-Arnold Convolutional Networks for Vision Recognition2604.23320v1 · Zhaoxiang Liu, Zhicheng Ma, Kaikai Zhao et al.2026 · 0 citationsarXiv
A Systematic Security Evaluation of OpenClaw and Its Variants2604.03131v1 · Yuhang Wang, Haichang Gao, Zhenxing Niu et al.2026 · 0 citationsarXiv
TIR-Agent: Training an Explorative and Efficient Agent for Image Restoration2603.27742v2 · Guoli Jia, Yisheng Zhang, Haote Hu et al.2026 · 1 citationarXiv
Chain-of-Trajectories: Unlocking the Intrinsic Generative Optimality of Diffusion Models via Graph-Theoretic Planning2603.14704v1 · Ping Chen, Xiang Liu, Xingpeng Zhang et al.2026 · 0 citationsarXiv
HEAL: Hindsight Entropy-Assisted Learning for Reasoning Distillation2603.10359v2 · Wenjing Zhang, Jiangze Yan, Jieyun Huang et al.2026 · 0 citationsarXiv
Beyond Geometry: Artistic Disparity Synthesis for Immersive 2D-to-3D2603.05906v1 · Ping Chen, Zezhou Chen, Xingpeng Zhang et al.2026 · 0 citationsProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2026, pp. 27114-27123
PaLMR: Towards Faithful Visual Reasoning via Multimodal Process Alignment2603.06652v2 · Yantao Li, Qiang Hui, Chenyang Yan et al.2026 · 0 citationsCVPR 2026 Findings
From Assistant to Double Agent: Formalizing and Benchmarking Attacks on OpenClaw for Personalized Local AI Agent2602.08412v2 · Yuhang Wang, Feiming Xu, Zheng Lin et al.2026 · 0 citationsarXiv
MeanCache: From Instantaneous to Average Velocity for Accelerating Flow Matching Inference2601.19961v3 · Huanlin Gao, Ping Chen, Fuyuan Shi et al.2026 · 0 citationsICLR 2026
HiMo-CLIP: Modeling Semantic Hierarchy and Monotonicity in Vision-Language Alignment2511.06653v1 · Ruijia Wu, Ping Chen, Fei Shen et al.2025 · 3 citationsAAAI2026
LeMiCa: Lexicographic Minimax Path Caching for Efficient Diffusion-Based Video Generation2511.00090v3 · Huanlin Gao, Ping Chen, Fuyuan Shi et al.2025 · 1 citationarXiv
PSTF-AttControl: Per-Subject-Tuning-Free Personalized Image Generation with Controllable Face Attributes2510.25084v1 · Xiang liu, Zhaoxiang Liu, Huan Hu et al.2025 · 0 citationsImage and Vision Computing, 105790 (2025)
Fuzzy Reasoning Chain (FRC): An Innovative Reasoning Framework from Fuzziness to Clarity2509.22054v1 · Ping Chen, Xiang Liu, Zhaoxiang Liu et al.2025 · 0 citationsFindings of the Association for Computational Linguistics: EMNLP 2025, pages 10230-10240, Suzhou, China. Association for Computational Linguistics
Hierarchical Deep Fusion Framework for Multi-dimensional Facial Forgery Detection -- The 2024 Global Deepfake Image Detection Challenge2509.13107v1 · Kohou Wang, Huan Hu, Xiang Liu et al.2025 · 0 citationsarXiv
MITS: A Large-Scale Multimodal Benchmark Dataset for Intelligent Traffic Surveillance2509.09730v1 · Kaikai Zhao, Zhaoxiang Liu, Peng Wang et al.2025 · 1 citationarXiv
iLearnRobot: An Interactive Learning-Based Multi-Modal Robot with Continuous Improvement2507.22896v1 · Kohou Wang, ZhaoXiang Liu, Lin Bai et al.2025 · 0 citationsarXiv
SLearnLLM: A Self-Learning Framework for Efficient Domain-Specific Adaptation of Large Language Models2505.17470v1 · Xiang Liu, Zhaoxiang Liu, Peng Wang et al.2025 · 2 citationsarXiv
Quantitative Analysis of Performance Drop in DeepSeek Model Quantization2505.02390v2 · Enbo Zhao, Yi Shen, Shuming Shi et al.2025 · 0 citationsarXiv
A Large Vision-Language Model based Environment Perception System for Visually Impaired People2504.18027v1 · Zezhou Chen, Zhaoxiang Liu, Kai Wang et al.2025 · 3 citationsarXiv
Safety Evaluation and Enhancement of DeepSeek Models in Chinese Contexts2503.16529v2 · Wenjing Zhang, Xuejiao Lei, Zhaoxiang Liu et al.2025 · 0 citationsarXiv
A Multimodal Benchmark Dataset and Model for Crop Disease Diagnosis2503.06973v1 · Xiang Liu, Zhaoxiang Liu, Huan Hu et al.2025 · 19 citationsarXiv
DAST: Difficulty-Adaptive Slow-Thinking for Large Reasoning Models2503.04472v3 · Yi Shen, Jian Zhang, Jieyun Huang et al.2025 · 3 citationsarXiv
Optimizing for the Shortest Path in Denoising Diffusion Model2503.03265v3 · Ping Chen, Xingpeng Zhang, Zhaoxiang Liu et al.2025 · 3 citationsProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2025, pp. 18021-18030
Safety Evaluation of DeepSeek Models in Chinese Contexts2502.11137v3 · Wenjing Zhang, Xuejiao Lei, Zhaoxiang Liu et al.2025 · 2 citationsarXiv
Quantifying the Capability Boundary of DeepSeek Models: An Application-Driven Performance Analysis2502.11164v5 · Kaikai Zhao, Zhaoxiang Liu, Xuejiao Lei et al.2025 · 1 citationarXiv
GlitchMiner: Mining Glitch Tokens in Large Language Models via Gradient-based Discrete Optimization2410.15052v5 · Zihui Wu, Haichang Gao, Ping Wang et al.2024 · 0 citationsarXiv
Piculet: Specialized Models-Guided Hallucination Decrease for MultiModal Large Language Models2408.01003v1 · Kohou Wang, Xiang Liu, Zhaoxiang Liu et al.2024 · 0 citationsarXiv
Methodology of Adapting Large English Language Models for Specific Cultural Contexts2406.18192v2 · Wenjing Zhang, Siqi Xiao, Xuejiao Lei et al.2024 · 1 citationarXiv
What is the best model? Application-driven Evaluation for Large Language Models2406.10307v1 · Shiguo Lian, Kaikai Zhao, Xinhui Liu et al.2024 · 4 citationsarXiv
CHiSafetyBench: A Chinese Hierarchical Safety Benchmark for Large Language Models2406.10311v2 · Wenjing Zhang, Xuejiao Lei, Zhaoxiang Liu et al.2024 · 1 citationarXiv
TP3M: Transformer-based Pseudo 3D Image Matching with Reference Image2405.08434v2 · Liming Han, Zhaoxiang Liu, Shiguo Lian2024 · 2 citations2024 IEEE International Conference on Robotics and Automation (ICRA), 3962-3968
Patch-wise Auto-Encoder for Visual Anomaly Detection2308.00429v2 · Yajie Cui, Zhaoxiang Liu, Shiguo Lian2023 · 2 citations2023 IEEE International Conference on Image Processing (ICIP), Kuala Lumpur, Malaysia, 2023, pp. 870-874
Semi-supervised Object Detection: A Survey on Recent Research and Progress2306.14106v1 · Yanyang Wang, Zhaoxiang Liu, Shiguo Lian2023 · 5 citationsarXiv
Application-Driven AI Paradigm for Person Counting in Various Scenarios2303.13788v1 · Minjie Hua, Yibing Nan, Shiguo Lian2023 · 0 citationsarXiv
Application-Driven AI Paradigm for Hand-Held Action Detection2210.06682v1 · Kohou Wang, Zhaoxiang Liu, Shiguo Lian2022 · 0 citationsarXiv
Vision-Based Defect Classification and Weight Estimation of Rice Kernels2210.02665v1 · Xiang Wang, Kai Wang, Xiaohong Li et al.2022 · 8 citationsarXiv
Application-Driven AI Paradigm for Human Action Recognition2209.15271v1 · Zezhou Chen, Yajie Cui, Kaikai Zhao et al.2022 · 0 citationsarXiv
Career total: 329 works. 79 are in this corpus.Showing the 50 most recent.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.