Topics

List of Topics

1. Reasoning Enhancement

• Chain-of-Thought (CoT) based advanced reasoning

• Test-time correction and self-correction mechanisms

• Long-context efficiency

• Test-time scaling

• Multi-step reasoning and logical inference capabilities

2. Domain-Specific LLM

• Vertical LLMs for healthcare, finance, legal domains

• Continual Pre-training (CPT) for domain adaptation

• Tool Calling Agent development

• Domain-specific knowledge integration and maintenance

3. Multimodal LLM

• Vision-Language-Action (VLA) models

• Visual Chain of Thought (VCoT) reasoning

• GUI Agent for interface automation

• 3D scene understanding and manipulation

• Wireless signal integration with language models

4. Trustworthy AI

• Hallucination detection and prevention

• Explainable AI (XAI) and interpretability

• Uncertainty calibration and confidence estimation

• Cross-modality bias detection and mitigation

• Safety guardrails and ethical AI frameworks

5. Evaluation Framework

• Comprehensive LLM assessment methodologies

• Agentic evaluation in dynamic environments

• Multimodal capability benchmarking

• Reasoning process quality evaluation

• Open-source evaluation platform development