Junhao Song

Orcid: 0009-0009-5178-0258

Affiliations:
  • Imperial College London, Department of Computing, London, UK


According to our database1, Junhao Song authored at least 21 papers between 2024 and 2026.

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

Timeline

Legend:

Book  In proceedings  Article  PhD thesis  Dataset  Other 

Links

Online presence:

On csauthors.net:

Bibliography

2026
Exploring efficiency frontiers of thinking budget in medical reasoning: Scaling laws between computational resources and reasoning quality.
J. Biomed. Informatics, 2026

2025
Is GPT-OSS All You Need? Benchmarking Large Language Models for Financial Intelligence and the Surprising Efficiency Paradox.
CoRR, December, 2025

47B Mixture-of-Experts Beats 671B Dense Models on Chinese Medical Examinations.
CoRR, November, 2025

AutoSurvey2: Empowering Researchers with Next Level Automated Literature Surveys.
CoRR, October, 2025

Towards Alignment-Centric Paradigm: A Survey of Instruction Tuning in Large Language Models.
CoRR, August, 2025

Is GPT-OSS Good? A Comprehensive Evaluation of OpenAI's Latest Open Source Models.
CoRR, August, 2025

Mixture of Experts in Large Language Models.
CoRR, July, 2025

Multimodal Representation Learning and Fusion.
CoRR, June, 2025

Achieving Trustworthy Real-Time Decision Support Systems with Low-Latency Interpretable AI Models.
CoRR, June, 2025

Predicting ICU In-Hospital Mortality Using Adaptive Transformer Layer Fusion.
CoRR, June, 2025

Active Learning Methods for Efficient Data Utilization and Model Performance Enhancement.
CoRR, April, 2025

Feature Alignment and Representation Transfer in Knowledge Distillation for Large Language Models.
CoRR, April, 2025

Advanced Deep Learning Methods for Protein Structure Prediction and Design.
CoRR, March, 2025

Generative Adversarial Networks Bridging Art and Machine Intelligence.
CoRR, February, 2025

ReChar: Revitalising Characters with Structure Preserved and User-Specified Aesthetic Enhancements.
Proceedings of the SIGGRAPH Asia 2025 Technical Communications, 2025

MERMAID: Multi-perspective Self-reflective Agents with Generative Augmentation for Emotion Recognition.
Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, 2025

2024
Deep Learning Model Security: Threats and Defenses.
CoRR, 2024

Deep Learning, Machine Learning, Advancing Big Data Analytics and Management.
CoRR, 2024

A Comprehensive Guide to Explainable AI: From Classical Models to LLMs.
CoRR, 2024

Navigating Public Sentiment in the Circular Economy through Topic Modelling and Hyperparameter Optimisation.
CoRR, 2024

SAIS: A Novel Bio-Inspired Artificial Immune System Based on Symbiotic Paradigm.
Proceedings of the Genetic and Evolutionary Computation Conference Companion, 2024


  Loading...