Foundation Models
2026
7
- Parameter-Efficient Fine-Tuning (PEFT): From Adapter to LoRA
- Why Language Models Hallucinate
- The Essence of LLM Reasoning and Training: From Surrogates to Reinforcement Learning Geometry
- What Does the Loss Landscape of LLMs Look Like?
- Compression for AGI: Compression as Intelligence
- Neural Scaling Laws: From Kaplan to Chinchilla
- From LLM to VLM: How Language Models Learn Visual Understanding
2025
3