Zhiwei Zhang
- AgentTTS: Large Language Model Agent for Test-time Compute-optimal Scaling Strategy in Complex Tasks
- Can Large Multimodal Models Understand Agricultural Scenes? Benchmarking with AgroMind
- GTPBD: A Fine-Grained Global Terraced Parcel and Boundary Dataset
- VFRTok: Variable Frame Rates Video Tokenizer with Duration-Proportional Information Assumption
- When Thinking Fails: The Pitfalls of Reasoning for Instruction-Following in LLMs