- Can an LLM Learn to See? Fine-Tuning Qwen 0.5B for Vision Tasks with SFT + GRPO
- Self-Rewarding Language Model
- QLoRA: Efficient Finetuning of Quantized LLMs
- LongLoRA: Efficient Fine tuning of Long Context Large Language Models
- LoRA: Low-Rank Adaptation of Large Language Models
- Getting Started with Distributed Data Parallel in PyTorch: A Beginner's Guide
- FlashAttention: Fast and Memory Efficient Exact Attention
- I-JEPA: Self-Supervised Learning from Images with a Joint-Embedding Predictive Architecture
- Break-A-Scene: Extracting Multiple Concepts from a Single Image