Yanshu Li

Orcid: 0009-0002-4054-606X

According to our database1, Yanshu Li authored at least 40 papers between 2019 and 2026.

Collaborative distances:
  • Dijkstra number2 of four.
  • Erdős number3 of four.

Timeline

Legend:

Book  In proceedings  Article  PhD thesis  Dataset  Other 

Links

On csauthors.net:

Bibliography

2026
Personalize Your Large Vision-language Models With In-context Prompt Tuning.
CoRR, May, 2026

TRACES: Proactive Safety Auditing for Multi-Turn LLM Agents via Trajectory-State Modeling.
CoRR, May, 2026

MM-StanceDet: Retrieval-Augmented Multi-modal Multi-agent Stance Detection.
CoRR, April, 2026

DeCo-DETR: Decoupled Cognition DETR for efficient Open-Vocabulary Object Detection.
CoRR, April, 2026

Not All Directions Matter: Toward Structured and Task-Aware Low-Rank Adaptation.
CoRR, March, 2026

RTD-Guard: A Black-Box Textual Adversarial Detection Framework via Replacement Token Detection.
CoRR, March, 2026

Steering Vector Fields for Context-Aware Inference-Time Control in Large Language Models.
CoRR, February, 2026

RoadBench: A Vision-Language Foundation Model and Benchmark for Road Damage Understanding.
Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, 2026

Self-Supervised Visual Prompting for Cross-Domain Road Damage Detection.
Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, 2026

Make LVLMs Focus: Context-Aware Attention Modulation for Better Multimodal In-Context Learning.
Proceedings of the Fortieth AAAI Conference on Artificial Intelligence, 2026

CATP: Contextually Adaptive Token Pruning for Efficient and Enhanced Multimodal In-Context Learning.
Proceedings of the Fortieth AAAI Conference on Artificial Intelligence, 2026

2025
Evaluating Parameter Efficient Methods for RLVR.
CoRR, December, 2025

TeleAI-Safety: A comprehensive LLM jailbreaking benchmark towards attacks, defenses, and evaluations.
CoRR, December, 2025

LLM-Powered Text-Attributed Graph Anomaly Detection via Retrieval-Augmented Reasoning.
CoRR, November, 2025

Read the Scene, Not the Script: Outcome-Aware Safety for LLMs.
CoRR, October, 2025

JEPA-T: Joint-Embedding Predictive Architecture with Text Fusion for Image Generation.
CoRR, October, 2025

Towards Generalizable Implicit In-Context Learning with Attention Routing.
CoRR, September, 2025

TRiCo: Triadic Game-Theoretic Co-Training for Robust Semi-Supervised Learning.
CoRR, September, 2025

A Comprehensive Review of AI Agents: Transforming Possibilities in Technology and Beyond.
CoRR, August, 2025

Never Compromise to Vulnerabilities: A Comprehensive Survey on AI Governance.
CoRR, August, 2025

Latent Chain-of-Thought? Decoding the Depth-Recurrent Transformer.
CoRR, July, 2025

Thinking with Images for Multimodal Reasoning: Foundations, Methods, and Future Frontiers.
CoRR, June, 2025

ViP<sup>2</sup>-CLIP: Visual-Perception Prompting with Unified Alignment for Zero-Shot Anomaly Detection.
CoRR, May, 2025

CAMA: Enhancing Multimodal In-Context Learning with Context-Aware Modulated Attention.
CoRR, May, 2025

M2IV: Towards Efficient and Fine-grained Multimodal In-Context Learning in Large Vision-Language Models.
CoRR, April, 2025

Advancing Multimodal In-Context Learning in Large Vision-Language Models with Task-aware Demonstrations.
CoRR, March, 2025

M-ABSA: A Multilingual Dataset for Aspect-Based Sentiment Analysis.
CoRR, February, 2025

Draw with Thought: Unleashing Multimodal Reasoning for Scientific Diagram Generation.
Proceedings of the 33rd ACM International Conference on Multimedia, 2025

ReLoop: "Seeing Twice and Thinking Backwards" via Closed-loop Training to Mitigate Hallucinations in Multimodal understanding.
Proceedings of the Findings of the Association for Computational Linguistics: EMNLP 2025, 2025

M-ABSA: A Multilingual Dataset for Aspect-Based Sentiment Analysis.
Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, 2025

TACO: Enhancing Multimodal In-context Learning via Task Mapping-Guided Sequence Configuration.
Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, 2025

A Jailbreak Prompt Detector Based on Selective Perturbation and Contrastive Learning.
Proceedings of the 28th International Conference on Computer Supported Cooperative Work in Design, 2025

2024
MedAide: Towards an Omni Medical Aide via Specialized LLM-based Multi-Agent Collaboration.
CoRR, 2024

ConflictBank: A Benchmark for Evaluating the Influence of Knowledge Conflicts in LLM.
CoRR, 2024

ConflictBank: A Benchmark for Evaluating the Influence of Knowledge Conflicts in LLMs.
Proceedings of the Advances in Neural Information Processing Systems 37: Annual Conference on Neural Information Processing Systems 2024, 2024

2023
ASGNet: Adaptive Semantic Gate Networks for Log-Based Anomaly Diagnosis.
Proceedings of the Neural Information Processing - 30th International Conference, 2023

2022
Thermal Error Prediction and Compensation of Digital Twin Laser Cutting Based on T-XGBoost.
Sensors, 2022

Exploring real-time fault detection of high-speed train traction motor based on machine learning and wavelet analysis.
Neural Comput. Appl., 2022

2021
Study on Total Factor Productivity and Absolute β Convergence of High-tech Industries in China.
Proceedings of the IPEC 2021: 2nd Asia-Pacific Conference on Image Processing, 2021

2019
Analysis of disease organ as a novel phenotype towards disease genetics understanding.
J. Biomed. Informatics, 2019


  Loading...