500AI
← People

Wenxuan Huang

  • Multimodal AI
  • Language models
  • Information retrieval

Selected work

5
  1. Vision-R1: Incentivizing Reasoning Capability in Multimodal Large Language ModelsFirst author · 2026
  2. Vision-DeepResearch: Incentivizing DeepResearch Capability in Multimodal Large Language ModelsFirst author · 2026
  3. Vision-DeepResearch Benchmark: Rethinking Visual and Textual Search for Multimodal Large Language ModelsFirst author · 2026
  4. Dynamic-LLaVA: Efficient Multimodal Large Language Models via Dynamic Vision-language Context SparsificationFirst author · 2025
  5. A General and Efficient Training for Transformer via Token ExpansionFirst author · 2024