Shuhang Lin

According to our database1, Shuhang Lin authored at least 18 papers between 2021 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
DenseSteer: Steering Small Language Models towards Dense Math Reasoning.
CoRR, May, 2026

Conformal Path Reasoning: Trustworthy Knowledge Graph Question Answering via Path-Level Calibration.
CoRR, May, 2026

Meet Dynamic Individual Preferences: Resolving Conflicting Human Value with Paired Fine-Tuning.
CoRR, April, 2026

RAGRouter-Bench: A Dataset and Benchmark for Adaptive RAG Routing.
CoRR, February, 2026

2025
OmniRouter: Budget and Performance Controllable Multi-LLM Routing.
SIGKDD Explor., December, 2025

CTkvr: KV Cache Retrieval for Long-Context LLMs via Centroid then Token Indexing.
CoRR, December, 2025

Cache Mechanism for Agent RAG Systems.
CoRR, November, 2025

LiteCUA: Computer as MCP Server for Computer-Use Agent on AIOS.
CoRR, May, 2025

Know the Ropes: A Heuristic Strategy for LLM-based Multi-Agent System Design.
CoRR, May, 2025

ECCOS: Efficient Capability and Cost Coordinated Scheduling for Multi-LLM Serving.
CoRR, February, 2025

Layer-Level Self-Exposure and Patch: Affirmative Token Mitigation for Jailbreak Attack Defense.
CoRR, January, 2025

Layer-Level Self-Exposure and Patch: Affirmative Token Mitigation for Jailbreak Attack Defense.
Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies, 2025

MPO: An Efficient Post-Processing Framework for Mixing Diverse Preference Alignment.
Proceedings of the Forty-second International Conference on Machine Learning, 2025

FactTest: Factuality Testing in Large Language Models with Finite-Sample and Distribution-Free Guarantees.
Proceedings of the Forty-second International Conference on Machine Learning, 2025

Invisible Prompts, Visible Threats: Malicious Font Injection in External Resources for Large Language Models.
Proceedings of the Findings of the Association for Computational Linguistics: EMNLP 2025, 2025

Disentangling Logic: The Role of Context in Large Language Model Reasoning Capabilities.
Proceedings of the Findings of the Association for Computational Linguistics, 2025

2024
BattleAgent: Multi-modal Dynamic Emulation on Historical Battles to Complement Historical Analysis.
Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing: EMNLP 2024, 2024

2021
Keyword Extraction Based on Semantic Similarity Metric and Multi-Feature Computing.
Proceedings of the 7th International Conference on Big Data Computing and Communications, 2021


  Loading...