• Jan. 2024 | Infobatch: Dataset Pruning On The Fly
• Jul. 2023 | ZSCL: Fine-tuning Vision-Language Models without Zero-Shot Transfer Degradation
• Jul. 2023 | CAME Optimizer: Adam Performance with Adafactor Memory Requirements
• May 2023 | Sequence Schedule: Can We Use LLM to Speedup LLM Inference?