Cho-Jui Hsieh

4 papers UCLA, LMArena

• Don’t Think Longer, Think Wisely: Optimizing Thinking Dynamics for Large Reasoning Models
• On the Loss of Context Awareness in General Instruction Fine-tuning
• Sparse MeZO: Less Parameters for Better Performance in Zeroth-Order LLM Fine-Tuning
• Unlabeled Data Improves Fine-Grained Image Zero-shot Classification with Multimodal LLMs